Add human-focused README.md to every skill and bundle directory

Each README is written for a human audience, explaining: - What the skill does (not what format it follows) - What benefit the user gets from installing it - Quick setup and usage patterns - When to load/trigger the skill - What scripts, references, and templates it ships data-scientist already had a README — left unchanged. 48 READMEs added across all skill and bundle directories.
2026-09-11 19:47:12 +03:00 · 2026-07-09 22:30:12 -04:00
parent 6c193ae2d8
commit 738ec715e7
48 changed files with 1561 additions and 0 deletions
@@ -0,0 +1,29 @@
+# Agent Skills — The Standard Itself
+
+This skill is the **meta-skill**: it documents the [Agent Skills](https://agentskills.io) open format itself. Every other skill in this repository follows the conventions defined here.
+
+## Why Install This Skill
+
+When your agent loads this skill, it gains the ability to **create, review, and edit valid Agent Skills-format skills**. That means:
+
+- **Your agent can build new skills on demand.** Describe a workflow you want encoded, and your agent can scaffold a valid SKILL.md with correct frontmatter, progressive disclosure structure, and agent-friendly descriptions.
+- **Existing skills stay valid.** When your agent edits a skill, it checks against the format standard — no broken frontmatter, no missing required fields.
+- **Consistency across your skill library.** Every skill in your repository follows the same conventions, making them loadable by any Agent Skills-compatible harness.
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Complete format reference: frontmatter schema, name constraints, description patterns, directory structure, and progressive disclosure model |
+| `references/` | Referenced in the body for format best practices |
+
+## When to Load This Skill
+
+- You're creating a new skill and need to know the correct format
+- You're reviewing an existing skill for format compliance
+- You want your agent to generate a valid SKILL.md scaffold
+- You're setting up conventions for a shared skill repository
+
+## Requirements
+
+None — this is a documentation skill. No scripts, no API keys, no dependencies.
@@ -0,0 +1,38 @@
+# Radarr & Sonarr Media Library Management
+
+A unified CLI skill for managing movies (Radarr) and TV series (Sonarr) from the terminal. Two CLIs, one skill wrapper.
+
+## Why Install This Skill
+
+When your agent loads this skill, it can **manage your entire *arr media library** without needing a web browser. That means:
+
+- **Ask what's in your library** — list movies, TV series, recently added content
+- **Add new media** — search for titles by name, then add them with the right quality profile
+- **Track upcoming releases** — check calendars for scheduled releases
+- **Monitor downloads** — view queue, download history, and wanted/missing episodes
+- **Troubleshoot** — check quality profiles, root folders, and system status
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Complete command reference with trigger table for every operation |
+| `scripts/radarr-cli` | CLI tool for Radarr movie management |
+| `scripts/sonarr-cli` | CLI tool for Sonarr TV series management |
+
+## Quick Start
+
+```bash
+export ARR_SERVER_RADARR="http://localhost:7878"
+export ARR_KEY_RADARR="your-radarr-api-key"
+export ARR_SERVER_SONARR="http://localhost:8989"
+export ARR_KEY_SONARR="your-sonarr-api-key"
+```
+
+## Triggers
+
+Load this skill when you hear "Radarr," "Sonarr," "the *arr stack," "add a movie," "find a TV show," "what's in my library," "upcoming releases," "download queue," or anything about media library management.
+
+## Requirements
+
+Python 3.8+ with `requests` library. API keys from each app's Settings → General.
@@ -0,0 +1,32 @@
+# AutoGen — Conversational Multi-Agent AI (Microsoft Research)
+
+An expert-level skill for building **conversational multi-agent systems** with Microsoft's AutoGen framework. Unlike graph-based or role-based orchestration, AutoGen uses **agent-to-agent conversations** as the orchestration primitive.
+
+## Why Install This Skill
+
+When your agent loads this skill, it becomes an AutoGen expert who can:
+
+- **Design agent topologies** — AssistantAgent, UserProxyAgent, GroupChat configurations
+- **Build group chat systems** — RoundRobinGroupChat and SelectorGroupChat patterns
+- **Implement nested chats** — agent-to-agent delegation for sub-tasks
+- **Configure code execution** — Docker-safe code execution for LLM-generated code
+- **Handle production concerns** — cancellation tokens, termination conditions, error recovery
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Quick-start guide, core paradigm explanation, and pattern selection |
+| `references/` | Deep dives into agent types, group chat, nested chats, code execution, tool integration, and MCP support |
+
+## Triggers
+
+Load this skill when working with AutoGen, building multi-agent chat systems, or comparing agent frameworks. Use when you need conversation-driven agent orchestration.
+
+## Framework Comparison
+
+AutoGen differs from other frameworks in the portfolio: it's conversation-driven (vs LangGraph's graph topology), uses autonomous agent-to-agent messaging (vs CrewAI's explicit role-based crews), and has built-in group chat routing (vs PydanticAI's direct delegation).
+
+## Requirements
+
+Python 3.8+ with `autogen-agentchat` and `autogen-ext` packages.
@@ -0,0 +1,30 @@
+# Brand Designer — Document and Generate Brand Identity
+
+A systematic toolkit for capturing brand identity in structured, durable form. Produces markdown specs, compiled brand books, and brand-compliant images.
+
+## Why Install This Skill
+
+When your agent loads this skill, it becomes a **brand identity specialist** who can:
+
+- **Scaffold complete brand documentation** — strategy, visual identity, voice & tone, application guidelines
+- **Validate brand consistency** — checks completeness of your brand documentation
+- **Compile brand deliverables** — one-page brand cards or full brand books
+- **Generate brand-compliant images** — reference-image-aware generation for consistent visuals
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Complete workflow guide from scaffold to delivery |
+| `templates/` | 7 brand documentation templates (strategy, visual identity, voice, application, governance, asset inventory) |
+| `scripts/brand-book` | CLI for init, validate, and compile operations |
+| `scripts/generate` | Image generation for brand cards and mockups |
+| `references/` | Canonical components reference and decision trees |
+
+## Triggers
+
+Load this when you need a brand card for press/stakeholders, visual identity documentation, brand voice guidelines, a full brand book for agency handoff, or an inventory of brand assets.
+
+## Requirements
+
+Python 3.8+ for the CLI; image generation requires a compatible backend. Templates are plain markdown.
@@ -0,0 +1,40 @@
+# Tailscale / Headscale — Self-Hosted Mesh VPN Bundle
+
+A comprehensive bundle of 7 sub-skills covering the entire self-hosted Tailscale ecosystem using Headscale as the open-source control server. Deploy, configure, and maintain your own WireGuard-based mesh VPN.
+
+## Why Install This Bundle
+
+When your agent loads this bundle, it becomes a **Tailscale/Headscale infrastructure engineer** who can handle the full lifecycle:
+
+- **Deploy Headscale** — install and configure the control server
+- **Author tailnet policies** — ACL rules, tag-based access control, user groups
+- **Manage node lifecycle** — auth keys, registration, tagging, decommissioning
+- **Configure clients** — install and connect Tailscale to your Headscale server
+- **Set up routing** — subnet routers and exit nodes
+- **Deploy DERP relays** — reliable peer-to-peer connectivity across NATs
+- **Backup and migrate** — regular backup and restoration of the control server
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Bundle umbrella — trigger-based auto-loading for 7 sub-skills |
+| `skills/` | 7 sub-skills: headscale-deploy, tailnet-policy, headscale-node-lifecycle, tailscale-client, headscale-routing, headscale-derp, headscale-backup |
+| `scripts/` | 23 shared scripts with `--json` and `--dry-run` support |
+| `references/` | 8 reference documents |
+| `templates/` | 6 templates for policy files and configs |
+
+## Quick Start
+
+1. **Deploy Headscale** first — install the control server
+2. **Configure tailnet policy** — set up ACLs before opening to users
+3. **Manage nodes** — register and tag machines on your tailnet
+4. **Install clients** — connect machines to your headscale server
+
+## Triggers
+
+Load this when you hear "Tailscale," "Headscale," "tailnet," "mesh VPN," "WireGuard mesh," or "self-hosted VPN infrastructure."
+
+## Requirements
+
+Bash, Python 3.8+, jq, curl. Access to a Headscale server or the `headscale` CLI. Tailscale client on target machines.
@@ -0,0 +1,38 @@
+# Workflow Architect — Discover and Encode Your Actual Workflow
+
+A meta-skill that helps you understand how you actually work, then generates a loadable skills bundle encoding your workflow as agent-triggerable skills. Turns implicit process into explicit, reusable capability.
+
+## Why Install This Skill
+
+When your agent loads this skill, it becomes a **process discovery specialist** who can:
+
+- **Discover your workflow** — through active interview (8-15 guided questions) or passive observation (analyzing what you actually do)
+- **Generate a skills bundle** — loadable skills with trigger conditions that encode each phase of your workflow
+- **Create a decision map** — Mermaid flowchart visualizing your workflow as your agent sees it
+- **Optionally set up a kanban board** — if your workflow has a predictable linear path
+- **Make it permanent** — generated bundle is registered in your agent's skill system for future sessions
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Bundle umbrella — two modes: active interrogation or passive observation |
+| `skills/` | 3 sub-skills: interviewer (active mode), observer (passive mode), bundle-builder (generation engine) |
+| `references/` | Workflow archetypes library, trigger condition patterns, kanban decision criteria |
+| `templates/` | 4 templates: skill skeleton, manifest, kanban setup, decision map |
+| `references/example-output/` | Two worked examples: developer pipeline, developer triage |
+
+## Two Modes
+
+- **Active Interrogation** — guided interview that asks structured questions and branches based on your answers.
+- **Passive Observation** — watches what you do in a session and infers your workflow patterns without interrupting.
+
+Both modes feed into the bundle-builder, which generates the final skills bundle.
+
+## Triggers
+
+Load this when you want to understand your own process, formalize a workflow, share it with collaborators, or give structure to a session that feels aimless.
+
+## Requirements
+
+Hermes Agent (uses skill_view, memory, session context scanning, write_file for bundle generation). Output bundles are standard Agent Skills format.
@@ -0,0 +1,29 @@
+# CLI Builder — Design Agent-Friendly CLI Tools
+
+A comprehensive design guide and scaffold for building CLI tools that **AI agents can actually use**. 10 universal design patterns grounded in real failures from building 15+ agent-facing CLIs.
+
+## Why Install This Skill
+
+When your agent loads this skill, it can **design, build, and refactor CLI tools** that agents can discover and use without human help. That means:
+
+- **Every `--help` output becomes a contract** the agent parses to understand your tool
+- **Every command supports `--json`** for machine-readable output the agent consumes
+- **Every operation is idempotent** — `--dry-run` previews changes before they happen
+- **Authentication is lazy** — help and dry-run work without credentials
+- **Errors are structured** — different exit codes for different failure modes
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | 500+ line reference: 10 design patterns, 3-phase build workflow, agent-compatibility test suite |
+| `templates/` | Python API client scaffold and bash CLI scaffold |
+| `references/` | Agent-compatibility test suite, Python API client pattern |
+
+## Triggers
+
+Load this when building a new CLI tool, refactoring an existing tool that causes agent friction, or debugging why your agent keeps failing to use a CLI properly.
+
+## Requirements
+
+Bash, Python 3.8+, jq, and a standard Unix CLI environment.
@@ -0,0 +1,30 @@
+# Color Management — ICC Profiles, Color Spaces & Gamut Analysis
+
+Expert-level color management for open-source workflows. Covers ICC profiles, working spaces, gamut mapping, and color science fundamentals.
+
+## Why Install This Skill
+
+When your agent loads this skill, it becomes a **color management specialist** who can:
+
+- **Inspect ICC profiles** — check metadata, primaries, TRC curves, and well-behaved status
+- **Convert between color spaces** — sRGB, ProPhotoRGB, ACEScg, Rec.2020, and more
+- **Analyze gamut** — check which image colors fall outside a target color space
+- **Compare sRGB variants** — understand differences between sRGB profiles from different vendors
+- **Calculate color difference** — compute dE between images or color values
+- **Generate comprehensive color reports** with visualizations
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Quick reference table mapping tasks to scripts and references |
+| `scripts/` | 6 Python scripts: profile inspect, well-behaved check, color space convert, gamut check, sRGB compare, color difference, color report |
+| `references/` | 5 reference files: overview, ICC operations, working spaces, soft-proofing workflow, tool commands, monitor calibration, dcraw pipeline |
+
+## Triggers
+
+Load this when inspecting ICC profiles, converting between color spaces, checking gamut clipping, validating working spaces, or troubleshooting color workflows.
+
+## Requirements
+
+ImageMagick, Exiftool, ArgyllCMS, LittleCMS (all platform-independent). Python scripts require Python 3.8+.
@@ -0,0 +1,35 @@
+# Confluence Wiki from the Terminal
+
+Interact with Atlassian Confluence Cloud via the REST API v2. List spaces, browse pages, view content, search with CQL, and create pages.
+
+## Why Install This Skill
+
+When your agent loads this skill, it can **navigate your Confluence documentation** without opening a browser. That means:
+
+- **Find pages across spaces** — list, search, and view content
+- **Search with CQL** — complex queries matching Jira-style filtering
+- **Create documentation** — create pages from the terminal
+- **Retrieve page body content** — extract the full text of any page
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Complete command reference with examples |
+| `scripts/confluence-cli` | CLI tool for Confluence operations |
+
+## Quick Start
+
+```bash
+export CONFLUENCE_EMAIL="your-email@example.com"
+export CONFLUENCE_API_TOKEN="your-api-token"
+export CONFLUENCE_SERVER="https://your-domain.atlassian.net"
+```
+
+## Triggers
+
+Load this when the user mentions Confluence, a space key (e.g. DEV), or asks about documentation, wiki pages, or knowledge base articles.
+
+## Requirements
+
+Python 3.8+ with `requests`. API token from id.atlassian.com (free, same token as Jira).
@@ -0,0 +1,29 @@
+# CrewAI — Role-Based Multi-Agent Orchestration
+
+An expert-level skill for building **role-based multi-agent teams** with CrewAI. Agents are defined as Roles with Goals and Backstories; crews are composed with sequential or hierarchical workflows.
+
+## Why Install This Skill
+
+When your agent loads this skill, it becomes a CrewAI expert who can:
+
+- **Design agent roles** — define agents with Role, Goal, Backstory, and tool sets
+- **Compose crews** — sequential and hierarchical process patterns
+- **Design tasks** — structured tasks with expected outputs and context
+- **Integrate tools** — custom tools, LangChain tools, and built-in tools
+- **Handle callbacks and events** — step callbacks, task events, crew completion
+- **Production considerations** — caching, memory, and deployment patterns
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Quick-start guide, core paradigm, and framework comparison |
+| `references/` | Deep dives into agent design, task patterns, crew composition, tools, callbacks, production, and framework comparisons |
+
+## Framework Comparison
+
+CrewAI is higher-abstraction than LangGraph (which is a low-level state machine) and more structured than AutoGen (which uses free-form conversations). It's best when you have well-defined roles with clear responsibilities.
+
+## Requirements
+
+Python 3.8+ with `crewai` and `crewai-tools` packages.
@@ -0,0 +1,28 @@
+# CrowdSec — Open-Source Collaborative IPS/IDPS/WAF
+
+Deploy, configure, and manage CrowdSec — the open-source security engine that detects and blocks malicious actors using behavior-based patterns and community blocklists.
+
+## Why Install This Skill
+
+When your agent loads this skill, it becomes a **CrowdSec security engineer** who can:
+
+- **Install and configure** — Security Engine on Linux or Docker, remediation components
+- **Manage with cscli** — hub collections, parsers, scenarios, and bouncers
+- **Set up the AppSec WAF** — HTTP request inspection for web applications
+- **Configure profiles and notifications** — tailored response and alerting
+- **Monitor and troubleshoot** — metrics, alerts, decisions, and health checks
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Architecture overview, installation guide, quick reference |
+| `references/` | 7 reference files: config deep dive, AppSec WAF, Docker deployment, Traefik integration, database backends, hub collections, troubleshooting |
+
+## Triggers
+
+Load this when setting up or troubleshooting CrowdSec, or when you need an IPS/IDPS/WAF for your infrastructure.
+
+## Requirements
+
+Linux server for installation. Docker for containerized deployment. Standard shell tools.
@@ -0,0 +1,29 @@
+# Data Architect — Virtual Expert for Teams Who Don't Have One
+
+A virtual data architect that helps you spot data platform problems you didn't know you had. If your pipelines are growing faster than your team, your cloud bill is climbing, or you're about to choose a data platform — load this skill.
+
+## Why Install This Skill
+
+When your agent loads this skill, it becomes a **senior data architect** who can:
+
+- **Run a QuickScan** — 5-minute diagnostics that surface common data platform gaps
+- **Discover data assets** — inventory every system producing data your team consumes
+- **Assess data maturity** — evaluate where you are on the data maturity curve
+- **Design data architectures** — data mesh, data lakehouse, streaming, real-time analytics
+- **Establish governance** — data ownership models, business glossary, data contracts
+- **Create migration plans** — structured paths from current state to target architecture
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Symptom recognition guide, QuickScan diagnostic, entry point table |
+| `references/` | Discovery framework, maturity model, architecture patterns, platform evaluation, governance, migration |
+
+## Triggers
+
+Load this when your data pipelines are growing out of control, teams disagree on data definitions, you're choosing a data platform, or you need someone who's seen this before.
+
+## Requirements
+
+No special system requirements. Designed for agentic AI assistants.
@@ -0,0 +1,28 @@
+# DSPy — Programming, Not Prompting Language Models (Stanford)
+
+An expert-level skill for **programmatic prompt optimization** with Stanford's DSPy framework. You write Python programs with typed signatures; DSPy optimizes the prompts automatically. This is the framework for prompt engineering that doesn't feel like engineering.
+
+## Why Install This Skill
+
+When your agent loads this skill, it becomes a DSPy expert who can:
+
+- **Define typed signatures** — input/output schemas with descriptions
+- **Build program modules** — Predict, ChainOfThought, ReAct, and custom Module subclasses
+- **Select optimizers** — MIPROv2, BootstrapFewShot, BootstrapFinetune — matching optimizer to bottleneck
+- **Compile programs** — transform a Python program into an optimized, prompt-efficient artifact
+- **Evaluate and iterate** — metrics, datasets, and optimization loops
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Core paradigm, optimizer cheat sheet, compilation pipeline |
+| `references/` | Signatures deep dive, module patterns, optimizer selection guide, evaluation methodology |
+
+## Framework Comparison
+
+DSPy is **not** a chain or RAG framework. It operates at the compiler layer — you define the program structure, DSPy optimizes the prompts. Use this when you want prompt engineering to be deterministic and testable, not a manual tuning exercise.
+
+## Requirements
+
+Python 3.8+ with `dspy` package.
@@ -0,0 +1,32 @@
+# EPUB — Ebook Creation, Extraction & Enrichment
+
+Expert-level EPUB handling for reading, writing, editing, and extracting knowledge from EPUB2 and EPUB3 files. Ships a CLI tool and five detailed references.
+
+## Why Install This Skill
+
+When your agent loads this skill, it becomes an **ebook format specialist** who can:
+
+- **Inspect EPUB structure** — see manifest, spine, TOC, metadata
+- **Extract clean text** — per-chapter or single-file, stripped of boilerplate
+- **Edit EPUBs non-intrusively** — metadata, chapters, spine, CSS — without breaking the file
+- **Create valid EPUBs from scratch** — scaffold new ebooks
+- **Extract knowledge with LLM mode** — facts, quotes, definitions, arguments via configurable LLM
+- **Convert EPUB2 to EPUB3** — add NAV, update namespace, keep NCX compatibility
+- **Batch process hundreds of EPUBs** — wrap any script across file globs
+- **Validate against the spec** — EPUBCheck or Python fallback
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Decision table mapping tasks to scripts, EPUB format essentials |
+| `scripts/` | 10 Python CLI scripts: info, text, scaffold, edit, images, batch, convert, validate, extract-knowledge |
+| `references/` | 8 reference files: format internals, Python libraries, spec/validation, tutorials, fixed-layout, accessibility, media overlays |
+
+## Triggers
+
+Load this when you encounter EPUB files — to read, create, edit, extract, convert, or validate them.
+
+## Requirements
+
+Python 3.8+ with `EbookLib`. Optional: `beautifulsoup4`, `epublib`, Java (for EPUBCheck), and an LLM endpoint for knowledge extraction.
@@ -0,0 +1,34 @@
+# Forgejo / Gitea CLI — Self-Hosted Git Forge
+
+Manage issues, pull requests, repositories, labels, webhooks, and Actions runners on a self-hosted Forgejo or Gitea instance — all from the terminal.
+
+## Why Install This Skill
+
+When your agent loads this skill, it can **manage your entire self-hosted Git forge** without a browser. That means:
+
+- **List, create, and search repositories** — manage your code hosting
+- **Handle issues** — list, show, create, comment, label, assign
+- **Manage pull requests** — list, diff, review, comment, merge with branch protection
+- **Configure webhooks** — list, create, delete
+- **Manage labels** — list and create custom labels
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Complete command reference with authentication setup and examples |
+| `scripts/forgejo-cli` | Python CLI tool |
+
+## Quick Start
+
+Two token profiles in `~/.hermes/.env`:
+- `FORGEJO_AGENT_TOKEN` — for automated operations (default)
+- `FORGEJO_USER_TOKEN` — for user-level operations (`--user` flag)
+
+## Triggers
+
+Load this when dealing with Forgejo, Gitea, self-hosted git forges, or any repository management on your own infrastructure.
+
+## Requirements
+
+Python 3.8+ with `requests` library. Self-hosted Forgejo or Gitea instance.
@@ -0,0 +1,36 @@
+# Ghost CMS from the Terminal
+
+Manage content on a Ghost CMS site: view site info, list and create posts and pages, manage tags — all via the Ghost Admin API (v5/v6).
+
+## Why Install This Skill
+
+When your agent loads this skill, it can **manage your Ghost CMS content** without the web editor. That means:
+
+- **List posts and pages** — by status (published, draft, scheduled)
+- **Create content** — write and publish blog posts from the terminal
+- **Manage tags** — list and browse tags
+- **Check site info** — title, URL, description, version
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Complete command reference with setup and examples |
+| `scripts/ghost-cli` | CLI tool for Ghost Admin API operations |
+
+## Quick Start
+
+```bash
+export GHOST_URL="https://your-ghost-site.com"
+export GHOST_ADMIN_KEY="your-id:your-secret"
+```
+
+API key from Ghost Admin → Integrations → Create custom integration.
+
+## Triggers
+
+Load this when working with Ghost CMS — managing posts, pages, tags, or checking site configuration.
+
+## Requirements
+
+Python 3.8+ with `requests` library.
@@ -0,0 +1,29 @@
+# Self-Hosted GitHub Actions Runners
+
+Deploy, manage, and troubleshoot self-hosted GitHub Actions runners. Covers systemd, Docker, Kubernetes (ARC), and Scale Set Client deployments.
+
+## Why Install This Skill
+
+When your agent loads this skill, it becomes a **CI/CD infrastructure engineer** who can:
+
+- **Choose the right deployment** — systemd for single machines, Docker for homelabs, ARC for Kubernetes teams
+- **Troubleshoot registration failures** — the critical ACCESS_TOKEN vs RUNNER_TOKEN distinction
+- **Design autoscaling** — ARC, Scale Set Client, ephemeral runners
+- **Harden runner security** — public repo risks, JIT tokens, runner groups
+- **Build custom runner images** — Dockerfiles with custom toolchain, Python, Ruby
+- **Solve network issues** — firewall rules, TLS, proxy configuration
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Deployment spectrum, quick reference, label strategy |
+| `references/` | 7 reference files: deployment, management, scaling, security, custom images, network, monitoring |
+
+## Triggers
+
+Load this when setting up CI, troubleshooting runner registration failures, designing autoscaling, or hardening runner security.
+
+## Requirements
+
+Linux, macOS, or Windows target hosts. Docker for containerized runners. Kubernetes for ARC deployments.
@@ -0,0 +1,37 @@
+# Project Gutenberg — Public Domain Book Toolkit
+
+Search, download, and extract clean text from 70,000+ free public-domain ebooks. Ships a portable CLI with zero external dependencies.
+
+## Why Install This Skill
+
+When your agent loads this skill, it can **work with the world's largest library of free ebooks**. That means:
+
+- **Search by title, author, or keyword** — find any public-domain book
+- **Download plain text or EPUB** — choose the format that suits your use case
+- **Extract clean content** — strips Project Gutenberg licensing boilerplate automatically
+- **Classify fiction vs non-fiction** — categorize what you find
+- **Full search-to-text pipeline** — one command from title to clean text
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Quick start, how it works, command reference |
+| `scripts/gutenberg` | Portable Python CLI — search, download, extract, classify, pipeline |
+
+## Quick Start
+
+```bash
+python3 scripts/gutenberg search "Moby Dick"
+python3 scripts/gutenberg download 2701 --format txt
+python3 scripts/gutenberg extract 2701
+python3 scripts/gutenberg pipeline "Alice's Adventures in Wonderland"
+```
+
+## Triggers
+
+Load this when someone mentions "Gutenberg," "public domain," "download a book," "classic literature," or any public-domain title or author.
+
+## Requirements
+
+Python 3.8+ with **zero external dependencies** — uses only the standard library.
@@ -0,0 +1,29 @@
+# Haystack — Production Search & NLP Pipelines (deepset)
+
+An expert-level skill for building **production search and NLP pipelines** with Haystack. Pipelines are validated DAGs with typed components and explicit connections.
+
+## Why Install This Skill
+
+When your agent loads this skill, it becomes a Haystack expert who can:
+
+- **Design pipeline DAGs** — add_component + connect with typed input/output slots
+- **Build RAG pipelines** — document indexing + query pipelines with embedding retrieval
+- **Create agentic systems** — tool-using agents with ReAct pattern
+- **Integrate generative AI** — PromptBuilder (Jinja2) + LLM generators
+- **Evaluate pipeline quality** — faithfulness, relevancy, and custom metrics
+- **Deploy with Hayhooks** — REST API deployment for production
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Core paradigm, where-to-start table, framework comparison |
+| `references/` | Deep dives into pipeline design, RAG, agents, evaluation, Hayhooks, and framework comparisons |
+
+## Framework Comparison
+
+Haystack uses explicit Pipeline DAGs (add_component + connect) — different from LangChain's LCEL pipe operator and LlamaIndex's query engines. Pipelines are validated at declaration time.
+
+## Requirements
+
+Python 3.8+ with `haystack-ai` package.
@@ -0,0 +1,30 @@
+# Hugo Theme Development
+
+Intermediate-to-advanced patterns for building and customizing Hugo CMS themes. Covers template architecture, asset pipeline, shortcodes, performance, SEO, and accessibility.
+
+## Why Install This Skill
+
+When your agent loads this skill, it becomes a **Hugo theme developer** who can:
+
+- **Set up template architecture** — baseof.html with blocks, template lookup order, partials
+- **Integrate Tailwind CSS** — v4 with `css.TailwindCSS` or v3 with PostCSS
+- **Build responsive images** — srcset, Hugo Pipes processing
+- **Create shortcodes and render hooks** — complex nested shortcodes, Mermaid, custom link/image rendering
+- **Optimize performance** — partialCached, cache TTLs, build speed
+- **Implement accessibility** — semantic HTML landmarks, ARIA patterns, keyboard navigation
+- **Configure SEO** — JSON-LD structured data, Open Graph, Twitter Cards
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Quick-start theme bootstrap, reference file index |
+| `references/` | 7 reference files: template architecture, asset pipeline, shortcodes & hooks, content & i18n, modules & performance, design & accessibility, SEO & output formats |
+
+## Triggers
+
+Load this when working on a Hugo theme or site template layer.
+
+## Requirements
+
+Hugo v0.154+. Works with any agent framework supporting the Agent Skills format.
@@ -0,0 +1,36 @@
+# Jellyfin Media Server from the Terminal
+
+Query your Jellyfin media library — recently added movies and episodes, search across your library, browse libraries, and check server stats.
+
+## Why Install This Skill
+
+When your agent loads this skill, it can **navigate your home media server** without opening a browser. That means:
+
+- **See what's new** — recently added movies and TV episodes
+- **Search your library** — find any movie, show, or episode by keyword
+- **Browse libraries** — list all configured media libraries
+- **Check server health** — server name, version, uptime, user count
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Complete command reference with setup and examples |
+| `scripts/jellyfin-cli` | CLI tool for Jellyfin API operations |
+
+## Quick Start
+
+```bash
+export JELLYFIN_URL="http://your-server:8096"
+export JELLYFIN_API_KEY="your-api-key"
+```
+
+API key from Dashboard → API Keys in the Jellyfin admin panel.
+
+## Triggers
+
+Load this when asking about Jellyfin, media server content, recently added movies or TV, or browsing your home media library.
+
+## Requirements
+
+Python 3.8+ with `requests` library. Jellyfin server with API key.
@@ -0,0 +1,39 @@
+# Jira Issue Tracker from the Terminal
+
+Interact with Atlassian Jira Cloud via the REST API v3. Search issues, view details, create issues, add comments, list projects, and transition status.
+
+## Why Install This Skill
+
+When your agent loads this skill, it can **manage your entire Jira workflow** without opening a browser. That means:
+
+- **Search issues by project, JQL, or assignee** — find anything in your tracker
+- **View full issue details** — description, status, assignee, comments
+- **Create and update issues** — new tasks, bugs, stories from the terminal
+- **Add comments** — update threads without the web UI
+- **Transition status** — move tickets through workflows
+- **List projects** — see what's available
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Complete command reference with setup and examples |
+| `scripts/jira-cli` | CLI tool for Jira REST API v3 |
+
+## Quick Start
+
+```bash
+export JIRA_EMAIL="your-email@example.com"
+export JIRA_API_TOKEN="your-api-token"
+export JIRA_SERVER="https://your-domain.atlassian.net"
+```
+
+API token from id.atlassian.com (free).
+
+## Triggers
+
+Load this when managing Jira issues, searching tickets, creating bugs, or tracking project work.
+
+## Requirements
+
+Python 3.8+ with `requests` library.
@@ -0,0 +1,29 @@
+# Jira Query Language (JQL) — Expert Reference
+
+The complete reference for writing, debugging, and optimizing JQL queries. Covers every operator, function, and pattern used in Jira issue search.
+
+## Why Install This Skill
+
+When your agent loads this skill, it becomes a **JQL expert** who can:
+
+- **Write any JQL query** — from simple field comparisons to complex date ranges and history operators
+- **Use all JQL functions** — date/time, user, sprint/version, issue, custom field, JSM functions
+- **Query history** — WAS, WAS IN, CHANGED operators for trend and sprint analysis
+- **Optimize performance** — indices, avoiding expensive clauses, best practices
+- **Build role-specific queries** — ready-made queries for developers, scrum masters, product owners, and admins
+- **Debug query problems** — common gotchas and troubleshooting patterns
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Core syntax, operators, keywords, functions catalog |
+| `references/` | Complete function catalog, role-specific query bank, gotchas & troubleshooting guide |
+
+## Triggers
+
+Load this when writing, debugging, or optimizing JQL queries; building saved filters, dashboard gadgets, or automation rules.
+
+## Requirements
+
+None — this is a reference skill. No scripts, no API keys.
@@ -0,0 +1,29 @@
+# Kanban Guru — Virtual Expert for Engineering Teams
+
+A virtual Kanban expert who can diagnose flow problems, design board configurations, set up multi-portfolio operating models, and guide Scrum-to-Kanban transitions.
+
+## Why Install This Skill
+
+When your agent loads this skill, it becomes a **senior Kanban practitioner** who can:
+
+- **Diagnose flow problems** — run a 5-minute QuickScan to find your biggest bottlenecks
+- **Calibrate WIP limits** — data-driven WIP limits based on team throughput
+- **Establish service level expectations** — probabilistic delivery forecasts from historical data
+- **Design multi-portfolio operating models** — serve multiple stakeholders without hidden competition
+- **Guide Scrum-to-Kanban transitions** — sane transition paths without cargo-culting
+- **Design board configurations** — columns, swimlanes, classes of service
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Symptom recognition guide, QuickScan diagnostic, entry point table |
+| `references/` | WIP limits, flow metrics, multi-portfolio, transition guide, cadences, classes of service, Little's Law |
+
+## Triggers
+
+Load this when your team is struggling with throughput, cycle times are unpredictable, stakeholders compete for the same engineers, or you're considering Kanban.
+
+## Requirements
+
+No special system requirements. Designed for agentic AI assistants.
@@ -0,0 +1,28 @@
+# LangChain — LLM Application Framework
+
+An expert-level skill for building LLM-powered applications with LangChain — the most widely adopted LLM orchestration framework. LCEL chains, RAG pipelines, agents, LangSmith observability, and LangServe deployment.
+
+## Why Install This Skill
+
+When your agent loads this skill, it becomes a **LangChain expert** who can:
+
+- **Build chains with LCEL** — `prompt | model | parser` composition with the Runnable interface
+- **Create agents** — `create_agent` with tools (not legacy AgentExecutor)
+- **Implement RAG pipelines** — document loading, splitting, embedding, retrieval, generation
+- **Add observability** — LangSmith tracing for production debugging
+- **Deploy with LangServe** — REST API deployment for production
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Core principles, pipeline modes, where-to-start table, quick reference |
+| `references/` | LCEL reference, RAG strategies, agent patterns, LangSmith, LangServe, framework comparisons |
+
+## Framework Comparison
+
+LangChain is the broadest LLM framework with 1000+ integrations. Its agents now run on LangGraph underneath. Use LangChain for rapid prototyping and broad integration support; drop to LangGraph when you need full state-machine control.
+
+## Requirements
+
+Python 3.8+ with `langchain`, `langchain-community`, and provider-specific packages.
@@ -0,0 +1,31 @@
+# LangGraph — Stateful Multi-Agent Orchestration
+
+Build multi-agent AI systems with LangGraph — the low-level orchestration framework for stateful, graph-based agent workflows. The foundation for agents in the LangChain ecosystem.
+
+## Why Install This Skill
+
+When your agent loads this skill, it becomes a **LangGraph architect** who can:
+
+- **Design graph topologies** — nodes, edges, state schemas, reducers
+- **Implement multi-agent patterns** — supervisor, swarm, and hierarchical orchestration
+- **Add persistence** — checkpointers and stores for long-running agents
+- **Handle production complexity** — branching, cycles, parallel execution, human-in-the-loop
+- **Evaluate agent performance** — systematic eval methodology
+- **Debug production failures** — common failure modes and how to trace them
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Quick start, design principles, pattern selection guide |
+| `scripts/` | Supervisor scaffold, swarm scaffold, eval generator |
+| `templates/` | 3 runnable template implementations |
+| `references/` | 8 reference files: architecture, each pattern in depth, evals, production failures, troubleshooting |
+
+## Triggers
+
+Load this when designing agent architectures that need cycles, conditional branching, parallel execution, or human-in-the-loop patterns.
+
+## Requirements
+
+Python 3.8+ with `langgraph`, `langchain`, and `langchain-openai` packages.
@@ -0,0 +1,36 @@
+# Last.fm — Music Data API from the Terminal
+
+Lookup user listening history, discover similar music, explore charts, manage tags, and scrobble listening events — all from your Last.fm account.
+
+## Why Install This Skill
+
+When your agent loads this skill, it can **work with your entire music listening history**. That means:
+
+- **Music discovery** — find similar artists via collaborative filtering
+- **Personal stats** — top artists, tracks, albums over any time period
+- **Charts** — global and per-country trending music
+- **Social graph** — friends' listening activity
+- **Scrobbling & loving** — record what you're listening to in real time
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Complete command reference with examples |
+| `scripts/lastfm-cli` | CLI tool for the Last.fm API |
+
+## Quick Start
+
+```bash
+export LASTFM_API_KEY="your_api_key_here"
+```
+
+Free API key from last.fm/api/account/create.
+
+## Triggers
+
+Load this for music data, listening statistics, music recommendations, similar artists, charts, or scrobbling.
+
+## Requirements
+
+Python 3.8+ with `requests` library. Free Last.fm API key.
@@ -0,0 +1,35 @@
+# Lidarr Music Library Management
+
+Manage your Lidarr music library from the terminal — search and browse artists and albums, add new artists, check calendars, view queue and download history.
+
+## Why Install This Skill
+
+When your agent loads this skill, it can **manage your entire music library** through Lidarr. That means:
+
+- **List artists and albums** — browse your curated music collection
+- **Add new artists** — search and add with MusicBrainz IDs
+- **Track upcoming albums** — calendar for scheduled releases
+- **Monitor downloads** — queue, history, wanted/ missing albums
+- **Check profiles** — quality and metadata profiles
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Complete command reference with trigger table |
+| `scripts/lidarr-cli` | CLI tool for Lidarr API |
+
+## Quick Start
+
+```bash
+export ARR_SERVER_LIDARR="http://localhost:8686"
+export ARR_KEY_LIDARR="your-lidarr-api-key"
+```
+
+## Triggers
+
+Load this when working with Lidarr, music library management, adding artists, or checking upcoming album releases.
+
+## Requirements
+
+Python 3.8+ with `requests` library. API key from Lidarr → Settings → General.
@@ -0,0 +1,29 @@
+# LlamaIndex — RAG & Agent Orchestration Framework
+
+An expert-level skill for building LLM applications over your data with LlamaIndex. RAG pipelines, multi-agent orchestration, event-driven workflows, knowledge graph construction, and production deployment.
+
+## Why Install This Skill
+
+When your agent loads this skill, it becomes a **LlamaIndex expert** who can:
+
+- **Build production RAG pipelines** — from data ingestion to deployed query engines
+- **Create agent workflows** — AgentWorkflow for tool-using agents
+- **Construct knowledge graphs** — PropertyGraphIndex for structural path traversal
+- **Optimize retrieval** — hybrid search, reranking, metadata filters, sentence window parsing
+- **Add observability** — OpenTelemetry-native tracing with Phoenix
+- **Evaluate systematically** — span-attached evaluation with ParamTuner
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | 9-phase pipeline guide, pipeline modes, quick reference |
+| `references/` | Ingest, chunk, index, retrieve, agent, workflow, deploy, evaluate — one per phase plus framework comparisons |
+
+## Framework Comparison
+
+LlamaIndex evolved from a RAG indexing library into a full workflow framework. It differs from LangChain (broader integration ecosystem) and Haystack (declarative DAG pipelines) — LlamaIndex's unique strength is its data-aware indexing and knowledge graph construction.
+
+## Requirements
+
+Python 3.8+ with `llama_index` package.
@@ -0,0 +1,28 @@
+# Nous Research Brand Identity — Image & Content Generation
+
+Generate images and content consistent with the Nous Research brand identity — a "cyber-classical" style blending neo-classical statuary, cyberpunk grunge, and retro manga illustration.
+
+## Why Install This Skill
+
+When your agent loads this skill, it can **create on-brand visuals** for the Nous / Theia / Hermes ecosystem. That means:
+
+- **Understand the brand DNA** — classical Greek myth meets cyberpunk meets retro anime
+- **Use the correct color palette** — electric blue, dark grunge, marble tones — with hex-accurate values
+- **Depict the Nous Girl mascot** — canonical poses, expressions, and accessories
+- **Generate consistent imagery** — reference-image-driven workflows for texture, grain, and style
+- **Match brand typography** — Inter, IBM Plex Sans, JetBrains Mono, distressed display faces
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Complete brand identity reference with style fusion, color palette, typography, mascot specs |
+| `assets/` | 4+ reference images: color palette card, official mascot, style reference, brand collage — usable as img2img inputs |
+
+## Triggers
+
+Load this when creating visuals in the Nous Research ecosystem — blog headers, social media, presentation slides, or brand assets.
+
+## Requirements
+
+Image generation backend for prompt-based workflows. Reference-image (img2img) workflows require an API supporting image inputs.
@@ -0,0 +1,30 @@
+# Open Knowledge Format (OKF) — Google's AI Agent Knowledge Standard
+
+Google's vendor-neutral format for representing knowledge as markdown files with YAML frontmatter, designed for AI agent consumption. Create, validate, and consume knowledge bundles.
+
+## Why Install This Skill
+
+When your agent loads this skill, it can **create and validate OKF knowledge bundles** — the emerging standard for AI agent knowledge. That means:
+
+- **Structure knowledge for AI consumption** — bundles of markdown with YAML frontmatter
+- **Validate bundle integrity** — check frontmatter, cross-links, and directory structure
+- **Create from templates** — scaffold new concepts and bundles
+- **Cross-link between concepts** — express relationships between knowledge units
+- **Distribute without vendor lock-in** — plain markdown, cloneable via git
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Core concepts, spec overview, quick start |
+| `scripts/okf-bundle-validate.py` | OKF bundle validation script |
+| `assets/` | Concept template, example bundle |
+| `references/` | Spec summary, bundle architecture, use cases |
+
+## Triggers
+
+Load this when working with OKF, creating knowledge bundles for AI agents, or converting documentation into agent-consumable format.
+
+## Requirements
+
+Python 3.8+ with PyYAML for validation. No API keys needed.
@@ -0,0 +1,36 @@
+# Open Library — Book Metadata from the Terminal
+
+Search books and authors, look up works and ISBNs, and fetch detailed metadata from the public Open Library API. No API key, no registration — just works.
+
+## Why Install This Skill
+
+When your agent loads this skill, it can **access 50M+ book records** without any setup. That means:
+
+- **Search by keyword** — find books by title, author, or subject
+- **Look up by ISBN** — get detailed metadata for any ISBN
+- **Author details** — bio, birth/death dates, top works
+- **Work and edition info** — publication dates, languages, formats
+- **Filter and sort** — by language, year, rating, or new arrivals
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Complete command reference with examples |
+| `scripts/openlibrary-cli` | CLI tool for the Open Library API |
+
+## Quick Start
+
+```bash
+openlibrary-cli search --query "dune"
+openlibrary-cli search --isbn "9780439358064"
+openlibrary-cli search-authors --query "asimov"
+```
+
+## Triggers
+
+Load this for book research, ISBN lookups, author information, or cataloging projects.
+
+## Requirements
+
+Python 3.8+ with `requests` library. No API key needed — fully public API.
@@ -0,0 +1,29 @@
+# Open Source Contributions — Be a Good Citizen
+
+Make good open source contributions — check CONTRIBUTING.md first, follow project norms, be a good citizen. Covers bug reports, feature requests, and pull requests.
+
+## Why Install This Skill
+
+When your agent loads this skill, it becomes a **model open source contributor** who knows how to:
+
+- **Read the room** — check CONTRIBUTING.md, check existing issues/PRs before acting
+- **File great bug reports** — minimal reproduction cases, clear steps, expected vs actual behavior
+- **Make good PRs** — right-sized scope, clean commits, proper messaging
+- **Handle review gracefully** — respond to feedback, update PRs, know when to follow up
+- **Work without guidelines** — defensible defaults when the project hasn't documented expectations
+- **Disclose AI assistance** — proper agent disclosure on AI-assisted contributions
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Golden rule, phase overview, default posture, agent checklist |
+| `references/` | 8 phase references + agent checklist + pitfalls + default posture (comprehensive guidance for every stage of contribution) |
+
+## Triggers
+
+Load this when filing an issue, opening a PR, or contributing to any open source project.
+
+## Requirements
+
+None. Works with any agent supporting the Agent Skills format.
@@ -0,0 +1,35 @@
+# PeerTube — Federated Video from the Terminal
+
+Browse videos, channels, and server info on any PeerTube instance. Search across the fediverse, list channels, check your account stats, and manage authentication.
+
+## Why Install This Skill
+
+When your agent loads this skill, it can **navigate the federated video universe** without a browser. That means:
+
+- **Browse videos** — recent uploads from any instance
+- **Search across instances** — find content in the fediverse
+- **Explore channels** — list channels and their videos
+- **Check server info** — instance name, description, user/video/view stats
+- **Authenticate** — OAuth2 login with token persistence
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Complete command reference with auth setup |
+| `scripts/peertube-cli` | CLI tool for PeerTube API |
+
+## Quick Start
+
+```bash
+export PEERTUBE_SERVER="https://your-instance.example.com"
+peertube-cli auth login --username "myuser" --password "mypassword"
+```
+
+## Triggers
+
+Load this for PeerTube, federated video, decentralized video platforms, or browsing PeerTube content.
+
+## Requirements
+
+Python 3.8+ with `requests` library.
@@ -0,0 +1,30 @@
+# Product Discovery — Discover Requirements from Stakeholders
+
+Discover product requirements from human stakeholders — map who to talk to, ask questions that surface hidden assumptions, detect gaps in real time, resolve conflicts, and translate conversations into structured specs.
+
+## Why Install This Skill
+
+When your agent loads this skill, it becomes a **product discovery specialist** — Phase 0 upstream of any spec-driven development pipeline. That means:
+
+- **Map stakeholders** — identify who to interview and in what order
+- **Design question stacks** — open questions that discover, not closed questions that validate
+- **Detect hidden gaps** — recognize what stakeholders aren't saying
+- **Resolve conflicts** — surface unstated differences in assumptions, risk tolerance, or incentives
+- **Distill into specs** — convert raw interview notes into structured spec input
+- **Handle AI-conducted discovery** — account for sycophancy and trust dynamics
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Pipeline overview, entry point table, core principles |
+| `references/` | 8 reference files: stakeholder mapping, question patterns, gap detection, conflict resolution, transcript-to-spec, AI-conducted discovery, power dynamics, time-constrained discovery |
+| `templates/` | 5 templates: discovery plan, interview guide, distillation worksheet, gap register, interpretation log |
+
+## Triggers
+
+Load this when starting product discovery, needing to interview stakeholders, or preparing for the SDD SPECIFY phase.
+
+## Requirements
+
+None. Agent-agnostic — works with any spec-driven or requirements pipeline.
@@ -0,0 +1,36 @@
+# Prowlarr — Indexer Hub Management
+
+Manage your Prowlarr indexer hub from the terminal — list and inspect indexers, view query/grab statistics, check health, manage connected *arr applications, and test indexer connectivity.
+
+## Why Install This Skill
+
+When your agent loads this skill, it can **manage your entire indexer infrastructure**. That means:
+
+- **List and inspect indexers** — see what indexers are configured
+- **Monitor performance** — query and grab statistics per indexer
+- **Test connectivity** — verify indexers are responding
+- **Check health** — overall system health and per-indexer status
+- **View connected apps** — which *arr applications are linked
+- **Browse search history** — see what's been searched and found
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Complete command reference with trigger table |
+| `scripts/prowlarr-cli` | CLI tool for Prowlarr API |
+
+## Quick Start
+
+```bash
+export ARR_SERVER_PROWLARR="http://localhost:9696"
+export ARR_KEY_PROWLARR="your-prowlarr-api-key"
+```
+
+## Triggers
+
+Load this when working with Prowlarr, indexers, or the *arr stack's indexer hub.
+
+## Requirements
+
+Python 3.8+ with `requests` library. API key from Prowlarr → Settings → General.
@@ -0,0 +1,31 @@
+# PydanticAI & PydanticGraph — Type-Safe AI Agents & Graph Workflows
+
+Build production-grade AI agents and graph-based state machines with PydanticAI and PydanticGraph. Agent creation, function tools, dependency injection, structured output, streaming, and graph control flow.
+
+## Why Install This Skill
+
+When your agent loads this skill, it becomes a **PydanticAI expert** who can:
+
+- **Create type-safe agents** — one-line agent creation with structured output validation
+- **Build function tools with dependencies** — RunContext for dependency injection
+- **Stream outputs** — text, events, and graph node streaming
+- **Use built-in capabilities** — Thinking, WebSearch, MCP, Hooks, and 20+ more with on-demand loading
+- **Create graph state machines** — PydanticGraph with BaseNode, GraphBuilder, parallel map/broadcast, joins with reducers
+- **Test systematically** — TestModel, FunctionModel, Pydantic Evals
+- **Deploy to production** — multi-agent patterns, MCP servers, durable execution
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Quick reference, when-to-load table, common pattern gallery |
+| `references/` | 8 reference files: core agents, capabilities/hooks, graph, models/output, patterns, testing/evals, examples, API reference, hybrid LangGraph patterns |
+| `templates/` | Runnable template implementations |
+
+## Triggers
+
+Load this whenever building agents, tool-using LLM workflows, or graph-based state machines in Python.
+
+## Requirements
+
+Python 3.10+ with `pydantic-ai` or `pydantic-ai-slim` package.
@@ -0,0 +1,37 @@
+# Raleigh Open Data — City of Raleigh Public Data
+
+Query, search, and download public datasets from the City of Raleigh Open Data portal. Access 200+ datasets — crime reports, food inspections, building permits, bike lanes, parks, zoning, traffic, budgets, and more.
+
+## Why Install This Skill
+
+When your agent loads this skill, it becomes a **Raleigh civic data specialist**. That means:
+
+- **Discover datasets** — catalog, search, and browse 200+ datasets
+- **Query with filters** — SQL-like WHERE clauses on city data
+- **Download in multiple formats** — CSV, GeoJSON, JSON
+- **Understand schema** — inspect field names, types, and sample data before querying
+- **No API key required** — all data is publicly available
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Complete command reference with examples |
+| `scripts/raleigh` | Python CLI for the ArcGIS REST API |
+| `references/` | Dataset catalog and category reference |
+
+## Quick Start
+
+```bash
+raleigh search "food inspection"
+raleigh query "Food Inspections" --where "SCORE < 70"
+raleigh download "Raleigh Dog Parks" -f csv -o dog_parks.csv
+```
+
+## Triggers
+
+Load this for any City of Raleigh data — crime, food inspections, permits, zoning, traffic, parks, or budgets.
+
+## Requirements
+
+Python 3.8+ with `requests` library. No API key required.
@@ -0,0 +1,29 @@
+# Software Architecture Analysis — Reverse Engineering to Design Document
+
+Reverse-engineer a codebase to understand its architecture, data flow, privacy posture, and feature surface — then produce a clean-room design document, PRD, or migration plan.
+
+## Why Install This Skill
+
+When your agent loads this skill, it becomes a **codebase archaeologist** who can:
+
+- **Map repository structure** — identify core components, languages, and frameworks
+- **Extract architecture** — understand how the system is actually built, not how it's documented
+- **Inventory features** — catalog every capability the system provides
+- **Identify implicit contracts** — storage operations, data flows, integration points
+- **Design clean-room alternatives** — re-imagine the system under new constraints (local-first, privacy-first, self-hosted)
+- **Produce specifications** — PRDs, design documents, migration plans with zero source code copying
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | 7-phase build workflow, trigger conditions |
+| `references/` | Phase-by-phase guidance with architecture extraction patterns, clean-room methodology |
+
+## Triggers
+
+Load this when you need to understand how a codebase works, produce a design document for a system in the same problem space, or create a clean-room specification.
+
+## Requirements
+
+Git, a programming language runtime matching the target codebase.
@@ -0,0 +1,31 @@
+# Spec-Driven Development for AI Software Factories
+
+A methodology where structured specifications are the executable input to an AI code generation pipeline. Quality gates enforce correctness at each phase.
+
+## Why Install This Skill
+
+When your agent loads this skill, it becomes a **software factory designer** who can:
+
+- **Design an SDD pipeline** — 5-phase pipeline from SPECIFY to DELIVER with 4 phase gates
+- **Write great specs** — 7 spec quality gates that separate precise specs from vague ones
+- **Choose spec methodologies** — BDD, OpenAPI, AsyncAPI, DbC, TLA+, ADRs, C4 — matched to your context
+- **Encode NFRs** — performance, security, observability requirements in machine-readable format
+- **Translate between formats** — PRD → SPEC.md → Gherkin → OpenAPI
+- **Handle gate recovery** — revision workflows when specs fail review
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Pipeline overview, loading guide, methodology quick-pick |
+| `references/` | 9 reference files: overview, pipeline, quality gates, phase gates, methodology matrix, NFR encoding, format translation, critiques, example spec |
+| `templates/` | 4 spec templates |
+| `scripts/` | 2 validation scripts |
+
+## Triggers
+
+Load this when designing a spec-driven pipeline, writing an AI-ready specification, or setting up quality gates for AI code generation.
+
+## Requirements
+
+Tool-agnostic — works with Claude Code, Cursor, Hermes Agent, Devin, OpenHands, droid, or any AI coding agent.
@@ -0,0 +1,28 @@
+# Systematic Debugging — 4-Phase Root Cause Protocol
+
+A disciplined 4-phase protocol for debugging technical issues: understand bugs before fixing. No random fixes, no symptom patching — only root cause investigation.
+
+## Why Install This Skill
+
+When your agent loads this skill, it becomes a **disciplined debugger** who follows a proven protocol. That means:
+
+- **Phase 1: Understand the bug** — reproduce, characterize, and scope before touching any code
+- **Phase 2: Find root cause** — trace symptom to source with evidence, not guesses
+- **Phase 3: Fix root cause** — one fix per root cause, validated before committing
+- **Phase 4: Verify and learn** — test the fix, check for similar issues, document the lesson
+- **Specialized patterns** — schema/environment divergence, exception chain analysis, dependency source detection, API failure characterization
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | The Iron Law, phase-by-phase protocol, specialized debugging patterns |
+| `references/` | Deep dives into each phase, specialized pattern guides, diagnostics |
+
+## Triggers
+
+Load this for ANY technical issue — test failures, production bugs, unexpected behavior, performance problems, build failures, integration issues. ESPECIALLY when under time pressure.
+
+## Requirements
+
+Platform-agnostic. Some sections cover macOS-specific sandbox debugging patterns. Requires access to source code and testing tools.
@@ -0,0 +1,37 @@
+# Tempest — Hyper-Local Weather from Your Station
+
+Query live weather data from a WeatherFlow Tempest station. Current conditions, 7-day forecast, historical observations, and real-time UDP broadcasts.
+
+## Why Install This Skill
+
+When your agent loads this skill, it can **check hyper-local weather from your own station** — more accurate than generic services. That means:
+
+- **Current conditions** — temperature, humidity, wind, rain, UV, solar radiation, barometric pressure
+- **7-day forecast** — daily and hourly outlook with precipitation probability
+- **Historical data** — past observations for analysis
+- **Real-time UDP** — local broadcast reception without cloud dependency
+- **Auto-discovery** — finds your station and sensors automatically
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Complete command reference with examples |
+| `scripts/tempest-cli` | CLI tool for WeatherFlow Tempest API |
+| `references/` | API field layout reference |
+
+## Quick Start
+
+```bash
+export TEMPEST_TOKEN="your-token-here"
+tempest-cli current
+tempest-cli forecast
+```
+
+## Triggers
+
+Load this for weather, temperature, rain, wind, humidity, forecast, or conditions from a specific Tempest station.
+
+## Requirements
+
+Python 3.8+ with `requests` library. Free token from weatherflow.com.
@@ -0,0 +1,36 @@
+# TMDb — Movie & TV Discovery from the Terminal
+
+Search movies and TV shows by keyword, discover by genre/certification/rating/date, check trending and upcoming releases, and browse genre lists.
+
+## Why Install This Skill
+
+When your agent loads this skill, it can **access the entire TMDb catalog** without a browser. That means:
+
+- **Search movies and TV** — by keyword with release year and ratings
+- **Discover by taste** — genre, certification, rating threshold, date range
+- **Find trending content** — what's popular right now
+- **Check upcoming releases** — what's coming to theaters
+- **Browse certifications** — US ratings (G, PG, PG-13, R, NC-17)
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Complete command reference with compound filter examples |
+| `scripts/tmdb-cli` | CLI tool for TMDb v3 API |
+
+## Quick Start
+
+```bash
+export TMDB_ACCESS_TOKEN="your-tmdb-access-token"
+tmdb-cli movie search --term "dune"
+tmdb-cli movie discover --genre horror --certification R
+```
+
+## Triggers
+
+Load this for movies, TV shows, film discovery, genre browsing, or media recommendations.
+
+## Requirements
+
+Python 3.8+ with `requests` library. Free API key from themoviedb.org.
@@ -0,0 +1,31 @@
+# Traefik v3 — Reverse Proxy & Load Balancer
+
+Deploy, configure, secure, and maintain Traefik v3 reverse proxy. Covers Docker provider, routing, TLS/ACME, middlewares, observability, and production deployment.
+
+## Why Install This Skill
+
+When your agent loads this skill, it becomes a **Traefik infrastructure engineer** who can:
+
+- **Deploy Traefik** — production-ready Docker Compose setup with Let's Encrypt
+- **Configure routing** — HTTP/TCP/UDP routers with Docker labels or file-based config
+- **Set up TLS** — ACME with HTTP-01, DNS-01, and TLS-ALPN-01 challenges
+- **Use all 25+ middlewares** — rate limiting, authentication, redirects, headers, circuit breakers
+- **Monitor and observe** — Prometheus/OpenTelemetry metrics, access logs, dashboard
+- **Harden deployment** — security best practices, production patterns
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Quick-start deployment, core concepts, reference index |
+| `templates/` | Production-ready Docker Compose template |
+| `scripts/` | Health check script with JSON output |
+| `references/` | 10 reference files: static config, dynamic config, all providers, routing, TLS/ACME, middlewares, observability, production, TCP/UDP, troubleshooting |
+
+## Triggers
+
+Load this when setting up or debugging a Traefik instance for reverse proxy, load balancing, or TLS termination.
+
+## Requirements
+
+Docker for containerized deployment. Standard Linux server for native installation.
@@ -0,0 +1,37 @@
+# Trakt — Media Discovery from the Terminal
+
+Discover trending, anticipated, and popular movies and TV shows via the Trakt.tv API. Read-only discovery with no user authentication needed.
+
+## Why Install This Skill
+
+When your agent loads this skill, it can **surface what's worth watching** without a browser. That means:
+
+- **Trending movies and TV** — what everyone's watching right now
+- **Most anticipated** — upcoming releases with buzz
+- **Popular content** — what's been hot recently
+- **No authentication** — just a Client ID, no OAuth flow
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Complete command reference with examples |
+| `scripts/trakt-cli` | CLI tool for Trakt.tv API v2 |
+
+## Quick Start
+
+```bash
+export TRAKT_CLIENT_ID="your-trakt-client-id"
+trakt-cli movie trending
+trakt-cli tv trending
+```
+
+Client ID from trakt.tv/oauth/applications (free, no OAuth needed).
+
+## Triggers
+
+Load this for what to watch, trending movies, popular shows, or media discovery.
+
+## Requirements
+
+Python 3.8+ with `requests` library. Free Client ID from trakt.tv.
@@ -0,0 +1,37 @@
+# Transistor.fm — Podcast Hosting from the Terminal
+
+Manage your Transistor.fm podcast shows, episodes, subscribers, and analytics — all from the terminal.
+
+## Why Install This Skill
+
+When your agent loads this skill, it can **manage your podcast hosting** without the web dashboard. That means:
+
+- **List shows** — all your podcasts with episode and subscriber counts
+- **Browse episodes** — recent episodes with publish dates
+- **Check analytics** — subscriber counts and trends
+- **Filter by show** — drill into a specific podcast's episodes
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Complete command reference with examples |
+| `scripts/transistor-cli` | CLI tool for Transistor.fm v1 REST API |
+
+## Quick Start
+
+```bash
+export TRANSISTOR_API_KEY="your-transistor-api-key"
+transistor-cli shows
+transistor-cli episodes
+```
+
+API key from Settings → API Keys in the Transistor.fm dashboard.
+
+## Triggers
+
+Load this for Transistor.fm, podcast hosting, podcast analytics, show management, or episode tracking.
+
+## Requirements
+
+Python 3.8+ with `requests` library.
@@ -0,0 +1,34 @@
+# Default Alive / Default Dead Calculator
+
+Evaluate whether a startup is on a trajectory to profitability before running out of cash. Paul Graham's Y Combinator framework as a deterministic CLI tool.
+
+## Why Install This Skill
+
+When your agent loads this skill, it can **run the single most important startup financial diagnostic**. That means:
+
+- **Compute default alive/dead status** — will revenue reach profitability before cash runs out?
+- **Calculate burn multiple** — net burn vs net new ARR (the key efficiency metric)
+- **Month-by-month projection** — see the runway month by month
+- **Identify levers** — what changes would flip DEAD to ALIVE
+- **Actionable verdict** — ALIVE / DEAD / MARGINAL with next-step guidance
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Framework explanation, quick heuristic, full script usage |
+| `scripts/default-alive.py` | Deterministic CLI calculator — Python 3.9+ with zero external dependencies |
+
+## Quick Start
+
+```bash
+python3 scripts/default-alive.py --revenue 10000 --burn 50000 --cash 500000 --growth 0.05
+```
+
+## Triggers
+
+Load this when founders ask about runway, burn rate, default alive status, whether they need to raise money, or financial sustainability analysis.
+
+## Requirements
+
+Python 3.9+ with standard library only (no external dependencies).
@@ -0,0 +1,35 @@
+# Weekly Growth Compass — YC's Startup = Growth Framework
+
+Paul Graham's "Startup = Growth" framework as an operational weekly practice. Computes growth rates, benchmarks against YC tiers, and frames every decision through the growth compass.
+
+## Why Install This Skill
+
+When your agent loads this skill, it can **make growth the compass for every startup decision**. That means:
+
+- **Compute weekly growth rates** — single period or time-series data
+- **Benchmark against YC tiers** — 1% concerning, 5-7% good, 10%+ exceptional
+- **Project compound growth** — see where you'll be in a year at current trajectory
+- **Frame decisions** — "does this serve your target growth rate?" for every initiative
+- **Estimate doubling time** — how long to 2x, 10x, 100x at current growth
+
+## What You Get
+
+| Directory | Purpose |
+|-----------|---------|
+| `SKILL.md` | Framework explanation, YC benchmarks, full script usage |
+| `scripts/growth-compass.py` | Deterministic CLI calculator — Python 3.9+ with zero external dependencies |
+
+## Quick Start
+
+```bash
+python3 scripts/growth-compass.py --current 1000 --prior 950
+python3 scripts/growth-compass.py --series "1000,1050,1100,1150,1200"
+```
+
+## Triggers
+
+Load this when founders ask about growth rate, weekly growth, startup traction, metrics, or whether they're moving fast enough.
+
+## Requirements
+
+Python 3.9+ with standard library only (no external dependencies).