Adonis0123/adonis-skills / .agents/skills/repo-skill-creator
repo-skill-creator
VerifiedCreate 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.
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
- Classify the request as
create,finalize-path,validate, orfinalize-and-stagebefore running a command. - If the user provides a
skills/*path and indicates the skill is already generated/copied, run path-finalize mode directly without additional confirmation. - A request to check, audit, or validate existing skills runs validation only. It must not create a skill or modify the Git index.
- Run auto-discover finalize-and-stage only when the user explicitly asks to prepare newly added skills for commit or to stage them.
- A bare invocation with no path or action defaults to validation. If exactly one new
skills/<slug>/SKILL.mdis 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:
pnpm skills:quick-validate skills/<skill-slug>pnpm skills:validatepnpm 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:
- 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.mditself is inAor??
- include
- Finalize each discovered slug in stable sorted order:
pnpm skills:finalize -- skills/<slug>- stop immediately on first failure
- Stage only related files after all finalize runs succeed:
git add skills/<slug>for each processed sluggit add apps/web/src/generated/skills-index-lite.json apps/web/src/generated/skills-detail-index.jsonfor whichever generated index files changed
- 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-yamlunless 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:
- Commands executed (or planned commands in dry-run).
- Success/failure status.
- Detected/processed skill slugs and staged file paths, with
nonewhen the selected mode does not stage. - Next-step suggestion only when useful (for example, local agent testing via
pnpm skills:test:local).
Skill Rules
- Use lowercase hyphen-case skill names.
- Keep
SKILL.mdfrontmatter valid with non-emptynameanddescription. frontmatter.descriptionmust be English-only (ASCII characters only), and should clearly include when to use the skill.- Add optional directories (
scripts/,references/,assets/) only when needed. - Re-run validation and index generation after updates and before commit.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |