agentleFS
Sign inStart free
revealui-studiorevealui-studio/revskills/skills/revealui-skills-test/SKILL.md

revealui-skills-test

Skill2 starsChanged 40 days agoMITView on GitHub

Static validator for Studio Agent Skills. Dry-runs skill roots (revskills SoT + equal-adapter command/skill homes), validates referenced scripts exist, flags stale ~/suite/ paths and rule violations. Read-only.

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Never FAIL solely because ~/.claude/commands is missing.

    line 27
  2. Very specific:

    If frontmatter present, confirm valid YAML-ish (--- open/close).

    line 33
  3. Distinctive:

    Do not execute skill bodies — parse statically only.

    line 89
  4. Distinctive:

    Do not modify any file — read-only validator.

    line 90

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Validate skill installs without requiring a Claude-only command dir. Goal: catch broken skills (stale paths, missing scripts, rule-violating commands) before invoke.

Load helpers:

. "$REVEALFLEET_ROOT/revskills/scripts/lib/session-state.sh"

Roots to scan (in order)

  1. SoT (always): $REVEALFLEET_ROOT/revskills/skills/*/SKILL.md
  2. Adapter homes (when present):
    • ~/.claude/commands/*.md (Claude slash / command links)
    • ~/.grok skill pointers if listed in config, or paths under [skills].paths
    • Optional: REVSKILLS_COMMAND_DIRS colon list (same as lint-all-skills)

Never FAIL solely because ~/.claude/commands is missing.

For each skill file

1. Frontmatter

  • If frontmatter present, confirm valid YAML-ish (--- open/close).
  • Confirm description is non-empty when frontmatter exists.

2. Referenced scripts

Extract paths matching:

  • $HOME/.claude/... or ~/.claude/...
  • $HOME/.grok/... or ~/.grok/...
  • $REVEALFLEET_ROOT/revskills/...
  • bash "<path>" / node "<path>" / tsx "<path>"

Assert each target exists. Missing = FAIL.

3. Referenced repos

Extract $REVEALFLEET_ROOT/..., ~/projects/..., ~/suite/....
~/suite/* = FAIL (retired). Missing $REVEALFLEET_ROOT/* = FAIL.

4. Rule compliance (awk linter)

awk -f "$REVEALFLEET_ROOT/revskills/scripts/lib/lint-skill.awk" <skill>

Tags: stale-suite-path, git-C-violates-bash.md, pnpm-dir-violates-bash.md, inline-node-e-violates-hooks.md, tmux-legacy.

5. CLI soundness

For known CLIs (revvault, pnpm, nix, gh, git, …): presence on PATH when invoked in skill code blocks.

6. Status marker

DISABLED in first H1/frontmatter → SKIP.

Batch / CI (no interactive harness required)

bash "$REVEALFLEET_ROOT/revskills/scripts/lint-all-skills.sh"
bash "$REVEALFLEET_ROOT/revskills/scripts/lint-all-skills.sh" --json

Exits 0 on clean, 1 on violation. Preferred pre-push path.

Output

skill              status   issues
revealui-recover   PASS     -
…

JSON sidecar: /tmp/revealui-skills-test-last.json.

Do not

  • Do not execute skill bodies — parse statically only.
  • Do not modify any file — read-only validator.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free