skills/magnus919_agent-skills
1
0
Fork 0
mirror of https://github.com/magnus919/agent-skills.git synced 2026-09-11 19:47:12 +03:00
Code Issues Packages Projects Releases Wiki Activity
218 Commits 11 Branches 10 Tags
7ae6a72308da44cc6e306f368bfb67adf059c3c8
Commit Graph
36 Commits
Author SHA1 Message Date
Magnus Hedemark 7ae6a72308 Merge branch 'main' into docs/issue-72-exit-conditions 2026-07-11 17:15:47 -04:00
Magnus Hedemark a2298afe08 Merge branch 'main' into docs/issue-70-use-when-sections 2026-07-11 17:15:28 -04:00
Magnus Hedemark 4827413f31 Merge branch 'main' into fix/issue-69-confirmation-gates 2026-07-11 17:15:04 -04:00
Magnus Hedemark f0efb25d91 docs(skills): define completion and exit conditions 2026-07-11 17:02:59 -04:00
Magnus Hedemark 87051aeba8 docs(skills): define use-when guidance 2026-07-11 17:02:57 -04:00
Magnus Hedemark 0546ddcb9d docs(skills): standardize confirmation gates 2026-07-11 17:02:54 -04:00
Magnus Hedemark 7704ded9c0 feat(flaresolverr): add browser challenge CLI skill 2026-07-11 17:01:03 -04:00
Magnus Hedemark d6bc6ffe8b feat: add comprehensive Kubernetes agent skill 2026-07-11 16:27:12 -04:00
Jasper (AI Assistant) 637c12d832 fix: align skill audit conventions (#101) 2026-07-11 15:40:50 -04:00
Magnus Hedemark f340dc1c62 feat: add portable docker-compose skill 2026-07-11 07:58:31 -04:00
Magnus Hedemark 3a4aad40bf feat: add agent-council — multi-agent structured debate system 
Spawns a panel of expert agents to debate any question with
convergence-aware iteration and typed synthesis output.

- PydanticAI + PydanticGraph-based Python package
- 5-phase debate protocol: compose → premortem → position →
  cross-examine (iterative, eval-driven) → synthesis
- Convergence detection: confidence dispersion, argument
  novelty, concession rate — stops when diminishing returns
- Typed output schemas (Pydantic models) for every phase
- CLI tool with markdown and JSON output modes
- Custom persona file support
- Bootstrap detection: sys.executable -m pip install fallback
- agentskills.io compatible SKILL.md with triggers

Signed-off-by: Magnus Hedemark <magnus919@pm.me>
 2026-07-09 22:55:30 -04:00
Magnus Hedemark 0c772a16b9 Add README.md requirement to AGENTS.md governance 
- Added 'Human-readable README' row to the Format Compliance table
- New README Format section defining 6 required sections + style guidance
- Added README validation to the Validate Your Output checklist
- References data-scientist/README.md as the canonical format example
 2026-07-09 22:36:49 -04:00
Magnus Hedemark e4a11880d1 feat: add pydanticai skill — PydanticAI & PydanticGraph expert reference 
Comprehensive agent skill covering:
- Agent creation, function tools, dependency injection, instructions
- 20+ capability system with on-demand (deferred) loading
- Lifecycle hooks system (before/after/wrap for all phases)
- 16 model providers, FallbackModel, ConcurrencyLimitedModel
- Structured output, streaming, output functions
- Multi-agent delegation and programmatic hand-off
- PydanticGraph: both BaseNode (class-based) and GraphBuilder (function-based)
  with parallel execution, joins/reducers, decisions, Mermaid rendering
- Testing with TestModel/FunctionModel and eval framework
- MCP integration, durable execution, UI adapters
- 8 comprehensive reference files + API quick reference

Signed-off-by: Magnus Hedemark <magnus919@pm.me>
 2026-07-08 23:50:36 -04:00
Magnus Hedemark 4a73657522 feat: add langgraph expert skill — multi-agent patterns, scaffolds, evals, and production guidance 
Comprehensive LangGraph skill covering:
- Core architecture: Graph API, Functional API, state management, agent loops
- Three multi-agent patterns: supervisor (~94% accuracy), swarm (~40% fewer LLM calls),
  hierarchical teams (subgraphs with nested state)
- Persistence: checkpointers vs stores, per-invocation/per-thread/stateless modes
- Production: Agent Server deployment, LangSmith observability, 8 failure modes
- Evals: routing accuracy, resolution coverage, LLM-as-judge methodology
- Troubleshooting: symptom→cause→fix tables per pattern
- 3 Python scripts: supervisor scaffold, swarm scaffold, eval generator
- 3 runnable templates: supervisor, swarm, subgraph composition

Ships 8 reference files, 3 scripts, and 3 templates.
 2026-07-08 14:54:53 -04:00
Magnus Hedemark 3f03c6e327 feat: add product-discovery skill — Phase 0 methodology for requirements discovery upstream of SDD 
Covers stakeholder mapping, question patterns, gap detection, conflict
resolution, transcript-to-spec distillation, AI-conducted discovery,
power dynamics, and time-constrained discovery. Ships 8 references and
5 templates.
 2026-07-06 13:29:44 -04:00
Magnus Hedemark 980f87050d feat: spec-driven-development v1.2.0 — SDD methodology for AI software factories 2026-07-06 00:09:07 -04:00
Magnus Hedemark 0b9150540f feat: add crowdsec skill — comprehensive IPS/IDPS/WAF reference 2026-07-05 22:06:37 -04:00
Magnus Hedemark c05bf92312 feat: add color-management skill (squash with fortification) 2026-07-05 16:06:04 -04:00
Magnus Hedemark 71b6335766 feat: add traefik — comprehensive Traefik v3 reverse proxy skill 
Deploy, configure, secure, and maintain Traefik v3 with full coverage of
static configuration, Docker provider labels, HTTP/TCP/UDP routing, all 25+
built-in middlewares, TLS/ACME (Let's Encrypt), API/dashboard, observability,
v2-to-v3 migration, and production deployment patterns.

Ships 10 reference files:
- static-configuration.md — complete YAML schema with all keys and defaults
- docker-provider.md — full Docker label reference with examples
- http-routing.md — all rule matchers, priority, syntax
- middleware-catalog.md — every middleware with YAML config
- tls-acme.md — ACME resolvers, challenges, TLS options, custom certs
- tcp-routing.md — TCP/UDP routing, SNI matching, TLS passthrough
- api-dashboard.md — all API endpoints, dashboard security
- observability.md — Prometheus/OTel metrics, access logs, tracing, ping
- migration-v2-to-v3.md — breaking changes and migration steps
- production-deployment.md — Docker Compose, security hardening, HA

Source: https://doc.traefik.io/traefik/
Signed-off-by: Jasper <magnus@groktop.us>
 2026-07-05 14:59:31 -04:00
Magnus Hedemark e151580319 Add github-runner skill: deploy, manage, and troubleshoot self-hosted GitHub Actions runners 
- SKILL.md with trigger table, quick reference, deployment spectrum, and pitfalls
- references/ for architecture, deployment (systemd/Docker/ARC/Scale Set Client),
  security, autoscaling, management, custom images, and network
- templates/ for docker-compose.yml and custom-runner.Dockerfile
- AGENTS.md updated with trigger row in alphabetical order
 2026-06-23 00:13:55 -04:00
Magnus Hedemark 29ecf795c4 Add design/UX/accessibility reference to hugo-theme skill 2026-06-19 15:38:54 -04:00
Magnus Hedemark 90783af84d Add hugo-theme skill: advanced Hugo CMS theme development 
Six reference files covering template architecture, asset pipeline,
shortcodes and render hooks, content organization and i18n, modules
and performance optimization, and SEO/output formats/CI/CD.
 2026-06-19 15:28:27 -04:00
Magnus Hedemark caa46d9c05 feat: add open-knowledge-format skill 
Google's Open Knowledge Format (OKF) v0.1 — an open, vendor-neutral
spec for representing knowledge as markdown files with YAML frontmatter,
designed for AI agent consumption.

- SKILL.md: core instructions, frontmatter spec, conformance criteria,
  cross-linking rules, relationship to other formats, quick start
- references/spec-summary.md: full OKF v0.1 specification reference
- references/bundle-architecture.md: directory structure and conventions
- references/use-cases.md: real-world adoption and patterns
- scripts/okf-bundle-validate.py: validate OKF bundle structure
- assets/concept-template.md: template for creating concept files
- assets/example-bundle/: minimal conformant OKF bundle
 2026-06-18 12:18:35 -04:00
Magnus Hedemark d8a11c2a4b Add yc-default-alive-calculator and yc-weekly-growth-compass skills 
Two research-grounded entrepreneurial tools based on Paul Graham's Y Combinator
frameworks, with companion CLI scripts and extensive reference material.

yc-default-alive-calculator:
- Paul Graham's 'Default Alive / Default Dead' framework as a deterministic CLI
- Month-by-month financial projection engine with growth decay modeling
- Burn multiple analysis, lever identification, and actionable verdict
- Zero external dependencies (Python 3.9+ stdlib only)
- 2 reference docs (framework deep-dive, fundraising context)

yc-weekly-growth-compass:
- Paul Graham's 'Startup = Growth' framework as an operational weekly tool
- Single-period and time-series growth rate computation
- YC benchmark classification (1% concerning -> 10%+ outstanding)
- Compound growth projections, doubling time, and decision compass
- Zero external dependencies (Python 3.9+ stdlib only)
- 2 reference docs (framework essay breakdown, compound growth table)

Both skills follow the Agent Skills open format (agentskills.io spec v1.0).
 2026-06-13 14:53:50 -04:00
Magnus Hedemark b2cb7d9672 feat: add gutenberg skill — search, download, and extract public-domain books from Project Gutenberg 
Ships a portable Python CLI (stdlib only, zero external dependencies) with:
- search: keyword search via gutendex API
- metadata: full book metadata by Gutenberg ID
- download: plain text, EPUB, or HTML format
- extract: strip PG boilerplate or extract text from EPUB
- classify: fiction vs non-fiction classification
- pipeline: full search → download → extract → classify workflow

AgentSkills.io compliant with SKILL.md, scripts/gutenberg, and
references/epub-extraction.md for progressive disclosure.
 2026-06-13 14:24:19 -04:00
Magnus Hedemark 9afed5d704 Add raleigh skill — CLI for City of Raleigh Open Data portal 
Query, search, and download from 170+ public datasets via the
ArcGIS REST API. Ships a zero-dependency Python CLI with:
catalog, search, info, query, download, and categories commands.

Includes:
- SKILL.md with trigger conditions and reference table
- references/dataset-catalog.md — full 170+ dataset inventory
- references/api-reference.md — ArcGIS REST API documentation
- scripts/raleigh — executable CLI tool
 2026-06-12 00:02:03 -04:00
Magnus Hedemark 79cf37a44a feat: add workflow-architect bundle — meta-skill for workflow discovery and skills bundle generation 
A new Agent Skills bundle that helps users discover their actual workflow
through two modes:

- Active interrogation: guided 8-15 question interview that adapts based on
  answers, building a structured model of the user's workflow phases,
  branching signals, tool preferences, and friction points

- Passive observation: loads silently, then on trigger phrase scans session
  context to infer workflow patterns from what actually happened

The output is a skills bundle: sub-skills per workflow phase with trigger
conditions, a manifest, a Mermaid decision map, and optionally a kanban
board if the workflow is deterministic/linear.

Ships 3 sub-skills (interviewer, observer, bundle-builder), 3 reference
documents (workflow archetypes, trigger condition patterns, kanban
decision criteria), 4 templates, and a worked example output bundle.

Also fixes broken table formatting in AGENTS.md (extra pipe characters
in trigger table rows).
 2026-05-29 21:29:56 -04:00
Magnus Hedemark c5c4d2434a feat: add opensource-contributions skill 
Comprehensive open source contribution guidance with progressive disclosure.
Restructured from a single ~23K-token monolithic SKILL.md into a concise
~1.2K-token orchestrator with 10 focused reference files.

Changes:
- SKILL.md: 1,720 lines → 100 lines (AgentSkills.io compliant frontmatter)
- 10 new reference files covering phases 0a-4, pitfalls, default posture
- Portable PR template compliance checker script (stdlib-only)
- All personal context scrubbed for public export
- AGENTS.md + README.md updated with trigger table entry

Signed-off-by: Magnus Hedemark <magnus919@pm.me>
 2026-05-28 21:43:30 -04:00
Magnus Hedemark b864a312c7 feat: add lastfm skill — Last.fm music data API with discovery pipeline 
A skill wrapping the lastfm-cli tool for the Last.fm music data API:
user listening history, artist/album/track metadata, collaborative
filtering-based similar music discovery, global/per-country charts,
search, tags, and scrobble/love/now-playing write operations.

Includes a Music Discovery Pipeline section for turning liked tracks
into recommendations via Last.fm's collaborative filtering graph.
 2026-05-28 13:31:09 -04:00
Magnus Hedemark 74b8370fa7 feat: add brand-designer skill — brand identity documentation toolkit 
Create comprehensive brand identity documentation for any brand:
- 7 markdown templates: brand-card, strategy, visual-id, voice,
  application, governance, asset-inventory
- brand-book CLI: init, compile (--artifact selector), validate,
  preview — all with --json and --dry-run support
- generate script: brand-card, mockup, swatch, moodboard,
  logo-bg image prompts (reference-image-aware)
- 6 reference files: canonical components, gold-standard analysis,
  artifact hierarchy, format comparison, template schemas,
  image generation patterns
- 12/12 tests passing

PR co-authored by: Jasper (AI agent on behalf of Magnus Hedemark)

Signed-off-by: Magnus Hedemark
 2026-05-24 19:06:36 -04:00
Magnus Hedemark dc2981b129 feat: add nous-branding skill — brand identity guide with reference-image generation 
- Complete Nous Research brand identity documentation
- Official Nous Girl mascot specs from the brand booklet
- Color palette (Electric Blue #3847FF + 5 more), typography system,
  texture system, design principles
- 7 reference images in assets/ (3 official from brand booklet, 4 generated)
- scripts/generate-with-ref.py — hits OpenAI /v1/images/edits directly with
  reference image upload, bypassing text-only image_generate tool
- 4 prompt templates: text-only, mascot portrait, system sheet, reference-image
- Brand compliance checklist
- AGENTS.md trigger table and README.md index updated
 2026-05-24 13:34:00 -04:00
Magnus Hedemark 88e92f4472 feat: add epub skill v2 — 11 scripts, 9 references, 46 tests 
Complete EPUB creation, editing, validation, and knowledge extraction
skill for the Agent Skills open format. Built from spec research, real
EPUB testing on 2.1MB commercial Apress title, and Apple Books
compatibility verification on macOS 26.

Scripts (11):
  epub-scaffold    — Create valid EPUB3 with cover XHTML, Apple Books CSS
  epub-edit        — Surgical editing (8 subcommands, epublib)
  epub-info        — Structure/metadata dump as JSON
  epub-text        — Clean text extraction, per-chapter or single-file
  epub-extract-knowledge — Heuristic + LLM extraction (env var auto-detect)
  epub-validate    — EPUBCheck or Python fallback validation
  epub-images      — List/extract all images with cover detection
  epub-batch       — Multi-file processing (extract-text, validate, metadata)
  epub-convert     — EPUB2→EPUB3 conversion with validation
  epub-repair      — Diagnose & auto-fix common structural issues
  epub-cover       — Add cover XHTML wrapper for Apple Books compatibility

References (9):
  epub-format-internals.md, python-libraries.md, spec-and-validation.md,
  tutorials-and-guides.md, agent-capability-discovery.md,
  fixed-layout-epub.md, accessibility.md, media-overlays.md,
  apple-books-compatibility.md (NEW — verified on macOS 26)

Test: 46/46 passing (test_epub_skill.sh)
 2026-05-23 18:08:48 -04:00
Magnus Hedemark 5ed56721c6 chore: resolve merge conflict after pulling origin main (data-scientist merged, epub added locally) 2026-05-23 16:48:10 -04:00
Magnus Hedemark 487f8923dc feat: add data-scientist skill 
PhD-level data science expertise with decision framework, five reference
documents (statistical methodology, experimental design, causal inference,
regression modeling, Bayesian workflow), five automation scripts (power
analysis, assumption diagnostics, model comparison, effect size calculator,
experimental design generator), and two report templates.

Python default with --engine r flag for R output. Dual language support.
 2026-05-22 16:35:31 -04:00
Magnus Hedemark 555cf087d9 feat: add kanban-guru skill 
A virtual Kanban expert skill with rich reference material covering all
seven cadences, classes of service, Little's Law, flow metrics,
multi-portfolio operating models, and Scrum-to-Kanban transitions.

- SKILL.md: diagnosis, design, and transition modes with QuickScan
- references/cadences.md: all seven cadences with agendas and formats
- references/classes-of-service.md: four canonical + custom classes
- references/flow-metrics.md: SLEs, CFDs, forecasting, right-sizing
- references/multi-portfolio.md: capacity allocations, board design
- references/transition-guide.md: Scrum-to-Kanban playbook
- references/wip-limits.md: Little's Law, calibration, breach signals
- references/glossary.md: A-Z kanban terminology

Sanitized for public use — no private context or references.
 2026-05-22 01:16:37 -04:00
Magnus Hedemark c1d13b95c6 docs: add AGENTS.md, LICENSE.md, curated README with installation sections 
README.md: curated skill index with descriptions for all 6 skills,
installation sections for Claude Code, OpenCode, Hermes Agent, Codex
CLI, GitHub Copilot, and generic frameworks.

LICENSE.md: standard MIT boilerplate.

AGENTS.md: agent loading guide with trigger table, progressive
disclosure rules, troubleshooting, and format compliance references.

Signed-off-by: Jasper <magnus@groktop.us>
 2026-05-21 22:53:03 -04:00