Automated summary
A meta-skill that curates the project's Claude Code skill library: deciding what earns a skill, merging and refining existing ones, retiring stale ones, and auditing them against current architecture rules.
Strengths
- Explicit, testable bar for creating a skill: repeats 3+ times, has non-obvious constraints, isn't already covered, and maps to real code paths.
- Concrete audit procedure: greps cited file paths for drift, checks rules against CLAUDE.md and AGENTS.md, and verifies frontmatter plus least-privilege allowed-tools.
- Clear dedupe and retire policy, with cross-linking between related skills (scaffold → kit → facade-fix) so the chain stays discoverable.
- Enforces SKILL.md conventions, including scoped allowed-tools and disabling model invocation for deploy-class skills.
Limitations
- Tightly coupled to the Inspire Courts repo: the rule list (admin-hub freeze, SWR policy, push cooldown) and cited paths are project-specific.
- No automated validation — auditing relies on reading and judgment, with no health metric or CI enforcement.
- Does not cover authoring the actual content of a new workflow skill, only its governance and upkeep.
Reach for it when adding, merging, or removing a skill, after major architecture changes, or on a periodic sweep to keep the library lean and accurate.
Don't use it to write the body of an operational skill, or for one-off tasks that won't repeat enough to earn a skill.
Security analysis
SafeThe skill uses Read, Edit, Write, Grep, Glob, and Bash scoped specifically to /opt/homebrew/bin/git. It does not instruct destructive system commands, exfiltration, or obfuscated execution. The git usage is for version-controlled curation of project skills, which is a legitimate and low-risk purpose.
No concerns found
How this analysis is madeExamples
Run a skill governance audit: for every .claude/skills/*/SKILL.md, check that each cited file path still exists and that the rules still match CLAUDE.md and AGENTS.md, then list what's drifted and how to fix it.I've now hand-ported three web sections into native screens. Does that clear the bar for a new skill? Check .claude/skills first to see if something already covers it, and tell me whether to create, extend, or skip.native-screen-scaffold and native-screen-generator look like they overlap — compare their SKILL.md bodies and either merge them into one or carve a clear boundary into each description.name: skill-governance description: Curate the Inspire Courts skill library — decide when a workflow earns a skill, refine/dedupe, retire stale skills, and audit skills against current architecture rules. Keeps the toolkit lean and reviewed. Use periodically, after big architecture changes, or when adding/removing a skill. argument-hint: "[audit | new <name> | dedupe | retire <name>]" allowed-tools: Read Edit Write Grep Glob Bash(/opt/homebrew/bin/git *)
Skill governance (the curator)
Project skills live in .claude/skills/<name>/SKILL.md and are the canonical,
git-reviewed copies (CLAUDE.md "Skills" section: project copy wins over user-level).
This meta-skill keeps the library lean + correct + non-redundant so every other
skill stays trustworthy. Skills encode the architecture rules + standing decisions
into tooling — if they drift from the code, they do harm.
When a workflow earns a skill (the bar)
Create a skill only when ALL are true:
- It repeats — you've done (or will do) this 3+ times (e.g. porting a web section, fixing a facade, scaffolding a screen).
- It must follow rules exactly — there are non-obvious constraints that are easy to get wrong (payment gate, no-fabricated-data, nav registration).
- It's not already covered — no existing skill does it (check first; extend instead of forking).
- It's concrete — maps to real code paths + files, not generic advice.
If it's a one-off, or pure judgment with no repeatable steps, it does NOT earn a skill — keep it in DIRECTION/memory instead.
SKILL.md conventions (enforce on every skill)
- Frontmatter:
name(matches dir),description(when-to-use, written so the model can route to it),argument-hint,allowed-tools(least-privilege — scopeBash(...)to the commands actually needed; no blanketBash). Adddisable-model-invocation: truefor deploy-class skills that must be explicit. - Body: grounded in real files (cite exact paths + anchor examples), a
non-negotiables/rules section, and a done = all true checklist. Living
recipe books (like
motion) append entries over time. - Lean: prose earns its place. Cut restating CLAUDE.md verbatim — link the rule, show the code.
Refine / dedupe
- Overlap check: grep skill bodies for the same files/workflows. If two skills
cover the same ground, merge into one and delete the weaker, or carve a clear
boundary in each
description(e.g.native-screen-scaffold= stamp one screen;native-screen-generator= port a web section using it). - Cross-link related skills by name (scaffold → kit → facade-fix) so the chain is discoverable.
- Tighten
allowed-toolsto the minimum; widen only with cause.
Retire stale skills
Retire (delete the dir, note it in the commit) when:
- The workflow no longer exists (the feature/area was removed).
- It's superseded by a better skill (dedupe outcome).
- Its instructions contradict current architecture and can't be salvaged.
Never leave a skill that points at moved/renamed files — fix or retire it.
Audit skills vs current rules (run periodically)
For each SKILL.md:
- File-path drift: every cited path still exists.
grep -oE '[a-zA-Z0-9_./-]+\.(swift|ts|tsx|mjs)' .claude/skills/*/SKILL.mdthen confirm each resolves. (Heads-up:DesignKit.swiftlives atios-native/Sources/Features/AdminDesign/, while the base layer isios-native/Sources/DesignSystem/DesignSystem.swift— don't conflate them.) - Rule drift: the skill's rules still match CLAUDE.md (admin-hub freeze, kit-only
UI, design tokens, no
dark:, SWR policy, API guard + manifest, push cooldown) and AGENTS.md (readnode_modules/next/dist/docs/before Next.js code). - Convention drift: frontmatter complete,
allowed-toolsleast-privilege, checklist present. - Coverage gaps: is there a repeated workflow with no skill? Flag it for creation (the standing rule: build skills anywhere a workflow repeats).
Produce a short report: OK / fix-needed / retire, with the one-line reason each.
Library map (keep current)
| Skill | One-line role |
|---|---|
| native-screen-scaffold | stamp one native screen correctly first time |
| native-kit | use/extend the native component kit (reuse-first) |
| native-screen-generator | port a web admin section → native (parity workhorse) |
| skill-governance | this meta-skill — curate the library |
| facade-fix | wire a "renders but doesn't work" screen end-to-end |
| data-surfacing | surface desktop-only/hidden data natively (real data) |
| ui-wiring | clickable rows→profile, actionable alerts, nav+search (no orphans) |
| test-factory | tests-as-you-build + reusable fixtures/factories |
| ai-feature | scaffold an AI feature on the shared prompt/voice lib + safety rails |
| payment-flow | build a money flow correctly (Square gate, audit, refund→credit) |
| observability-auto-fix | Sentry error → diagnose → fix → ship through the gates |
| audit/cycle/improve/fix-sweep/deploy/motion | baseline website skills |
Update this table whenever a skill is added/retired.
Checklist
- [ ] New skill cleared the 4-point bar (repeats, rule-bound, non-redundant, concrete).
- [ ] Frontmatter complete +
allowed-toolsleast-privilege. - [ ] Body grounded in real paths with a checklist.
- [ ] No overlap left unmerged; related skills cross-linked.
- [ ] Stale skills retired (not left pointing at dead paths).
- [ ] Library map table updated; committed with a clear message.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/skill-governance-mrx3xxxm/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/skill-governance-mrx3xxxm' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/skill-governance-mrx3xxxm/download' --output '.skill-downloads/skill-governance-mrx3xxxm/SKILL.md.part' && mv '.skill-downloads/skill-governance-mrx3xxxm/SKILL.md.part' '.skill-downloads/skill-governance-mrx3xxxm/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Tools declared by the author (check availability in your agent): Read Edit Write Grep Glob Bash(/opt/homebrew/bin/git *)
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/skill-governance-mrx3xxxm/SKILL.md' && test -s '.skill-downloads/skill-governance-mrx3xxxm/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/skill-governance' && cp -R '.skill-downloads/skill-governance-mrx3xxxm' '.claude/skills/skill-governance'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/skill-governance-mrx3xxxm'openskills read 'skill-governance-mrx3xxxm'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/skill-governance-mrx3xxxm/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Supabase Docs Authoring
Documentation
Write, edit, and review Supabase documentation content including guides, tutorials, reference docs, and partials. Follow style guides and MDX/TOML validation rules.
Create Architecture Decision Record
Documentation
Create a new Architecture Decision Record with sequential numbering, register it in the AgentDB graph, and link related ADRs.
Plan update with deep research
Documentation
Updates a plan document by launching parallel subagents to analyze a topic across all compiler passes, then consolidates findings into the plan doc.