From df713361c40fb8276622e31fb9b29b20546fde1b Mon Sep 17 00:00:00 2001 From: Magnus Hedemark Date: Fri, 14 Aug 2026 16:07:01 -0400 Subject: [PATCH] fix(flatten): point catalog validation and links at flat layout Update validate-skills.rb expected_catalog_paths to the flat */SKILL.md glob (drop the bundles/ term), repoint the 8 README catalog headings to /SKILL.md, and fix the promise-theory and semantic-spacetime workflow-architect links to ../workflow-architect/SKILL.md. Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com> --- README.md | 16 ++++++++-------- promise-theory/SKILL.md | 2 +- scripts/validate-skills.rb | 2 +- semantic-spacetime/SKILL.md | 2 +- 4 files changed, 11 insertions(+), 11 deletions(-) diff --git a/README.md b/README.md index 7dfc54d..6690853 100644 --- a/README.md +++ b/README.md @@ -20,7 +20,7 @@ Multi-agent structured debate system — spawn a panel of expert agents to debat Design and review framework-neutral AI-agent evaluations, trajectory evidence, risk-tiered release gates, and privacy-aware observability. Covers datasets, grader calibration, statistical comparisons, incident-to-case learning, optional OpenTelemetry interoperability, and templates for durable evidence. -### [agent-production-operations](bundles/agent-production-operations/SKILL.md) +### [agent-production-operations](agent-production-operations/SKILL.md) Operate an evaluated agent with tools and authority in production through a runtime control plane covering versioning, staged rollout, fallback, cost and latency budgets, tool health, human escalation, disablement, and trace-to-eval feedback. @@ -172,7 +172,7 @@ Use a small FlareSolverr JSON CLI for browser-backed GET and POST requests, read Safe Forgejo API v1 CLI for issues, pull requests, repositories, file contents, metadata, webhooks, and user settings. Includes a guarded generic `/api/v1/` route for version-specific endpoints such as Actions and admin APIs. -### [forward-deployed-engineering](bundles/forward-deployed-engineering/SKILL.md) +### [forward-deployed-engineering](forward-deployed-engineering/SKILL.md) Carry an embedded technical engagement from an ambiguous need to an adopted, measurable capability and a deliberate generalization decision across discovery, build, deployment, adoption, and field learning. @@ -292,7 +292,7 @@ Machine learning engineering methodology — model training, fine-tuning (LoRA/Q Build, test, sign, and ship mobile apps across iOS, Android, Flutter, and React Native as ONE family skill with per-framework references: project scaffolding, builds and code signing, device and emulator testing, store submission (App Store/TestFlight and Google Play), app lifecycle and backgrounding, offline and sync, and mobile-specific testing. Ships 4 framework references (ios, android, flutter, react-native) and 6 evals. Routes web UI work to frontend-engineering and server-side work to backend-engineering. -### [neckbeard](bundles/neckbeard/SKILL.md) +### [neckbeard](neckbeard/SKILL.md) Evidence-driven software delivery operating model — routes a change through framing, discovery, design, implementation, review, verification, delivery, and learning, choosing the smallest *safe* intervention and proving it at the real delivery boundary. Every non-trivial run leaves an inspectable evidence ledger. Composes the specialist catalog rather than replacing it. Ships a versioned evaluation harness that measures SDLC outcomes, never LOC. Not a "10x developer" persona. @@ -375,7 +375,7 @@ Discover product requirements from human stakeholders — map who to talk to, as Run end-to-end product experiments from assumption to decision — translate assumptions into testable hypotheses, select the right method (qualitative interviews, prototypes, concierge tests, fake doors, feature flags, A/B tests), define guardrails and ethics, and produce readouts that update the roadmap and decision record. Ships 4 references (discovery brief, method selection, guardrails and ethics, experiment readout) and 4 fillable templates (assumption map, experiment brief, guardrail and decision rule record, readout learning entry). Routes statistical design to data-scientist and rollout mechanics to release-engineering. -### [product-lifecycle](bundles/product-lifecycle/SKILL.md) +### [product-lifecycle](product-lifecycle/SKILL.md) Route a product through its full lifecycle — discovery, strategy and portfolio choice, roadmap, UX and requirements, experimentation, delivery handoff, adoption, success, and lifecycle review — by composing existing specialist product skills with phase-entry evidence, handoff artifacts, and stop/escalation rules. A thin orchestration bundle that provides cross-skill routing and a lifecycle evidence ledger; never duplicates a specialist's methodology. Ships 2 references (phases with per-phase contracts and ledger spec, capability map), a discovery brief, an AGENTS.md loading guide, and 6 evals covering complete lifecycle trajectories, stopped/escalated paths, and evidence handoffs. Does not assume B2B SaaS; customer-success routing is conditional on product type. @@ -400,7 +400,7 @@ Build and maintain outcome-based product roadmaps and portfolio views that seque CPO methodology — product vision and strategy (North Star, product principles), competitive analysis and positioning, roadmap prioritization (RICE, Kano, OST), product-market fit frameworks (Sean Ellis test, retention curves), market sizing (TAM/SAM/SOM), platform strategy, product lifecycle management. -### [production-excellence](bundles/production-excellence/SKILL.md) +### [production-excellence](production-excellence/SKILL.md) Cross-domain production gate model — assembles readiness, migration, recovery, capacity/cost, and incident-learning evidence into a launch or operational decision (go/no-go/defer/exception/escalation) with an accountable owner and a post-launch learning path. Composes 12 specialist skills (production-readiness, migration-engineering, resilience-and-recovery, capacity-and-cost-engineering, incident-learning, SRE, release, platform, security, data, QA, verification) without copying their runbooks. Ships 4 references (discovery brief, evidence packet, gate model, handoff record) and 5 integrated evals covering normal release, blocked launch, data migration, dependency outage, and cost/SLO conflict. ### [production-readiness](production-readiness/SKILL.md) @@ -435,7 +435,7 @@ Senior-to-principal release engineering methodology — release process models a Administer and troubleshoot remote Linux, FreeBSD, NetBSD, OpenBSD, and macOS hosts safely, one system or a controlled fleet at a time. Covers SSH, Ansible, Paramiko, portable diagnostics, platform-specific services, packages, configuration, firewalls, rollback, and evidence-led verification. -### [research-and-vault](bundles/research-and-vault/SKILL.md) +### [research-and-vault](research-and-vault/SKILL.md) Run a repeatable research-to-notes sequence: gather sources, record URLs and dates, extract independent atomic claims, then create a durable note with explicit coverage gaps. @@ -499,7 +499,7 @@ Develop, self-host, and administer Supabase across the CLI local stack, managed 4-phase root cause debugging protocol: understand bugs before fixing. Covers schema/environment divergence, exception type specificity in fallback chains, progressive characterization grids for API/retrieval failures, dependency source detection (editable dev forks), macOS sandboxed application debugging, and the Rule of Three for recognizing architectural problems. Adapted from [obra/superpowers](https://github.com/obra/superpowers) (MIT) with significant expansion from real-world use. -### [tailscale](bundles/tailscale/SKILL.md) +### [tailscale](tailscale/SKILL.md) Self-hosted Tailscale/Headscale VPN ecosystem. Seven sub-skills covering Headscale server deployment, ACL/tailnet policy authoring, Tailscale client configuration, node lifecycle (auth keys, registration, tagging, decommissioning), subnet routing and exit nodes, DERP relay infrastructure, and backup/migration. Ships 23 scripts with `--json` and `--dry-run` support, 8 reference documents, and 6 templates. @@ -566,7 +566,7 @@ Design, build, and review accessible web interfaces through native semantics, ke ### [woodpecker-ci](woodpecker-ci/SKILL.md) Operate self-hosted Woodpecker CI from installation through production troubleshooting. Covers Forgejo/Gitea integration, server and agent setup, Docker and Kubernetes backends, workflow syntax, secrets, plugins, matrices, CLI/local execution, upgrades, security, and incident response. -### [workflow-architect](bundles/workflow-architect/SKILL.md) +### [workflow-architect](workflow-architect/SKILL.md) Discover your actual workflow through conversation or passive observation, then generate a tailored skills bundle that encodes it as loadable agent skills with trigger conditions. Dual mode: active interrogation (guided 8-15 question interview) or passive observation (analyzes session context from what you actually did). Output includes sub-skills per workflow phase, a manifest with trigger conditions, a Mermaid decision map, and optionally a kanban board if the workflow is linear. Ships 3 sub-skills, 3 reference documents, 4 templates, and a worked example output bundle. diff --git a/promise-theory/SKILL.md b/promise-theory/SKILL.md index 7de216c..0f53640 100644 --- a/promise-theory/SKILL.md +++ b/promise-theory/SKILL.md @@ -79,7 +79,7 @@ Run these commands from the skill directory (`promise-theory/`); `python3 script |-------|---------------| | [agent-evals-and-observability](../agent-evals-and-observability/SKILL.md) | You need the assessment layer: evals, guardrails, and observability that verify promises are kept (also routed from `references/trust-and-verification.md`) | | [agent-council](../agent-council/SKILL.md) | You need multi-agent debate as structured promise exchange and convergence (also routed from `references/agent-coordination.md`) | -| [workflow-architect](../bundles/workflow-architect/SKILL.md) | You need to design a workflow as a chain of promises (also routed from `references/patterns.md`) | +| [workflow-architect](../workflow-architect/SKILL.md) | You need to design a workflow as a chain of promises (also routed from `references/patterns.md`) | | [artifact-pyramids](../artifact-pyramids/SKILL.md) | You need to structure promise-keeping evidence as summaries → analysis → evidence dossiers (also routed from `references/trust-and-verification.md`) | | [agent-skills](../agent-skills/SKILL.md) | You are authoring or editing an Agent Skills-format skill — the format this skill follows | | [cli-builder](../cli-builder/SKILL.md) | You are building or refactoring the bundled CLI — `scripts/promise-contract.py` follows cli-builder conventions (non-interactive, `--json`, `--dry-run`) | diff --git a/scripts/validate-skills.rb b/scripts/validate-skills.rb index 4e9268d..3fdecef 100755 --- a/scripts/validate-skills.rb +++ b/scripts/validate-skills.rb @@ -33,7 +33,7 @@ unless catalog_names == expected_catalog_names end catalog_paths = catalog_entries.map(&:last).sort -expected_catalog_paths = (Dir.glob("#{ROOT}/*/SKILL.md") + Dir.glob("#{ROOT}/bundles/*/SKILL.md")) +expected_catalog_paths = Dir.glob("#{ROOT}/*/SKILL.md") .map { |path| path.delete_prefix("#{ROOT}/") } .sort missing_catalog_paths = expected_catalog_paths - catalog_paths diff --git a/semantic-spacetime/SKILL.md b/semantic-spacetime/SKILL.md index 500835a..986a4d0 100644 --- a/semantic-spacetime/SKILL.md +++ b/semantic-spacetime/SKILL.md @@ -137,7 +137,7 @@ with absolute paths. | [promise-theory](../promise-theory/SKILL.md) | You need the substrate vocabulary SST builds on: promises, offers and acceptances, convergence, the Downstream Principle, and coordination diagnosis (also routed from `references/foundations.md`) | | [agent-evals-and-observability](../agent-evals-and-observability/SKILL.md) | You need to turn measurement and verification of semantic claims into evals, traces, and release gates (also routed from `references/foundations.md`) | | [agent-council](../agent-council/SKILL.md) | You want structured multi-agent debate as a mechanism for negotiating shared meaning between agents | -| [workflow-architect](../bundles/workflow-architect/SKILL.md) | You want to encode a semantic-spacetime-informed workflow as a reusable skill bundle | +| [workflow-architect](../workflow-architect/SKILL.md) | You want to encode a semantic-spacetime-informed workflow as a reusable skill bundle | | [artifact-pyramids](../artifact-pyramids/SKILL.md) | You need to structure SST evidence — models, maps, observations — as summaries → analysis → evidence dossiers | | [agent-skills](../agent-skills/SKILL.md) | You are authoring or editing an Agent Skills-format skill — the format this skill follows | | [cli-builder](../cli-builder/SKILL.md) | You are building or refactoring the bundled CLI for SST models (it will follow cli-builder conventions: non-interactive, `--json`, `--dry-run`) |