agentleFS
Adonis0123Adonis0123/adonis-skills/.agents/skills/repo-skill-creator/SKILL.md

repo-skill-creator

Skill5 starsChanged 9 days agoMITView on GitHub

Create and maintain repository skills for adonis-skills. Use when users ask to scaffold a new skill under skills/, generate agents/openai.yaml, run skill validation, refresh web index data, or standardize the skill authoring workflow.

The file

Show its rules and text

We split this skill into the rules it gives an agent

19 rules. About 0 are common, 11 are distinctive, and 8 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈11

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 8

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Create and maintain repository skills with intent-specific workflows.

    line 11
  2. Very specific:

    If the user provides a skills/* path and indicates the skill is already generated/copied, run path-finalize mode directly without …

    line 16
  3. Distinctive:

    Run auto-discover finalize-and-stage only when the user explicitly asks to prepare newly added skills for commit or to stage them.

    line 18
  4. Distinctive:

    Use for “check”, “audit”, “validate”, or a bare invocation without a requested creation/finalize action:

    line 64
  5. Distinctive:

    When source changes already exist and generated index freshness is part of the check, also run:

    line 70
  6. Very specific:

    Do not call skills:new, skills:finalize:new, or git add in this mode.

    line 77
  7. Distinctive:

    Run only when the user explicitly asks to finalize and stage newly added skills:

    line 81
  8. Very specific:

    only accept slugs where skills/<slug>/SKILL.md itself is in A or ??

    line 91
  9. Distinctive:

    stop immediately on first failure

    line 94
  10. Distinctive:

    If no new skill is discovered:

    line 98
  11. Distinctive:

    do not create a skill unless the user also requested creation

    line 100
  12. Very specific:

    Do not auto-run pnpm skills:openai-yaml unless explicitly requested.

    line 104
  13. Very specific:

    Do not auto-run local install/sync (skills:install:local, skills:test:local) unless explicitly requested.

    line 105
  14. Very specific:

    Do not stage in create, finalize-path, or validate mode.

    line 106
  15. Distinctive:

    Do not use git add -A; only stage skill-related files from this workflow.

    line 107
  16. Distinctive:

    When executing this skill, always return:

    line 111
  17. Distinctive:

    Use lowercase hyphen-case skill names.

    line 120
  18. Very specific:

    Keep SKILL.md frontmatter valid with non-empty name and description.

    line 121
  19. Very specific:

    Add optional directories (scripts/, references/, assets/) only when needed.

    line 123

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Repo Skill Creator

Create and maintain repository skills with intent-specific workflows. Validation is read-only with respect to Git state; creation, finalization, staging, and runtime installation are separate actions.

Trigger Rules

  1. Classify the request as create, finalize-path, validate, or finalize-and-stage before running a command.
  2. If the user provides a skills/* path and indicates the skill is already generated/copied, run path-finalize mode directly without additional confirmation.
  3. A request to check, audit, or validate existing skills runs validation only. It must not create a skill or modify the Git index.
  4. Run auto-discover finalize-and-stage only when the user explicitly asks to prepare newly added skills for commit or to stage them.
  5. A bare invocation with no path or action defaults to validation. If exactly one new skills/<slug>/SKILL.md is discoverable, report it as the likely finalize target, but do not stage or create anything implicitly.

For normal create or finalize, first read the repository instructions, command definitions, and required arguments. When these establish the applicable entry point and no failure has occurred, use that entry point without routinely pre-reading the initializer, finalizer, validator, indexer, or YAML generator implementation. Read the relevant implementation on demand for an actual failure, command ambiguity, an output that conflicts with the documented contract, or maintenance of that tooling. This does not restrict necessary source or safety checks, target ownership checks, or verification of the real finalize pipeline and generated outputs.

Mode A: Create New Skill

Primary command (recommended):

pnpm skills:new

Manual creation commands:

pnpm skills:init <skill-name> --path skills --resources scripts,references
pnpm skills:finalize -- skills/<skill-name>

Mode B: Finalize Existing Skill by Path

For the selected finalize-path action, run from the current repository root. Relative and absolute targets must resolve to a direct child of this repository's skills/ directory:

pnpm skills:finalize -- <skill-path>

Examples:

pnpm skills:finalize -- skills/code-inspector-init
REPO_ROOT="$(git rev-parse --show-toplevel)"
pnpm skills:finalize -- "$REPO_ROOT/skills/code-inspector-init"

Finalize pipeline is fixed and must run in order:

  1. pnpm skills:quick-validate skills/<skill-slug>
  2. pnpm skills:validate
  3. pnpm skills:index

This mode does not stage files.

Mode C: Validate Existing Skills

Use for “check”, “audit”, “validate”, or a bare invocation without a requested creation/finalize action:

pnpm skills:validate

When source changes already exist and generated index freshness is part of the check, also run:

pnpm skills:index
git diff --check

Do not call skills:new, skills:finalize:new, or git add in this mode.

Mode D: Auto Discover + Finalize + Stage

Run only when the user explicitly asks to finalize and stage newly added skills:

pnpm skills:finalize:new

Behavior contract:

  1. Discover newly added skill candidates from git status --short --untracked-files=all:
    • include A (index-added) and ?? (untracked)
    • only accept slugs where skills/<slug>/SKILL.md itself is in A or ??
  2. Finalize each discovered slug in stable sorted order:
    • pnpm skills:finalize -- skills/<slug>
    • stop immediately on first failure
  3. Stage only related files after all finalize runs succeed:
    • git add skills/<slug> for each processed slug
    • git add apps/web/src/generated/skills-index-lite.json apps/web/src/generated/skills-detail-index.json for whichever generated index files changed
  4. If no new skill is discovered:
    • report that no new skill was found
    • do not create a skill unless the user also requested creation

Scope Boundaries

  • Do not auto-run pnpm skills:openai-yaml unless explicitly requested.
  • Do not auto-run local install/sync (skills:install:local, skills:test:local) unless explicitly requested.
  • Do not stage in create, finalize-path, or validate mode. Staging requires an explicit finalize-and-stage/commit-preparation request.
  • Do not use git add -A; only stage skill-related files from this workflow.

Output Contract

When executing this skill, always return:

  1. Commands executed (or planned commands in dry-run).
  2. Success/failure status.
  3. Detected/processed skill slugs and staged file paths, with none when the selected mode does not stage.
  4. Next-step suggestion only when useful (for example, local agent testing via pnpm skills:test:local).

Skill Rules

  1. Use lowercase hyphen-case skill names.
  2. Keep SKILL.md frontmatter valid with non-empty name and description.
  3. frontmatter.description must be English-only (ASCII characters only), and should clearly include when to use the skill.
  4. Add optional directories (scripts/, references/, assets/) only when needed.
  5. Re-run validation and index generation after updates and before commit.

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.