Skip to content

mgiovani/ai-arsenal / skills/create-skill

create-skill

Verified

Create a new agent skill (or Claude Code slash command) from a plain-language description, using live spec fetching, pattern research, and an approval-gated blueprint before any files are written. Use whenever the user wants to build, scaffold, or author a new skill, subagent capability, or slash command, including phrasings like 'make a command for X', 'create a slash command', 'turn this into a reusable skill', or 'package this workflow as a skill'. Not for editing CLAUDE.md/AGENTS.md memory rules (use create-rule) or discovering/installing existing third-party skills (use find-skills).

references/frontmatter-fields.md

View on GitHub
# Frontmatter field reference

Full reference for SKILL.md YAML frontmatter fields beyond the basics covered in Phase 3. Consult this when a skill needs argument substitution or an isolated execution context.

## All fields

```yaml
---
name: my-skill                     # kebab-case, becomes /slash-command
description: "What it does..."     # when Claude should use it — the trigger mechanism
disable-model-invocation: true     # user-invoked only; skip for skills with side effects
argument-hint: "[args]"            # shown in autocomplete
license: MIT                       # optional
compatibility: ...                 # optional, rarely used
metadata:                          # optional: author, version, source
  author: name
  version: 1.0.0
context: fork                      # run in an isolated subagent (see below)
agent: Explore                     # subagent type when context: fork is set
hooks:                             # lifecycle hooks scoped to this skill
  PreToolUse:
    - matcher: Bash(git commit*)
      hooks: [...]
---
```

Validate against `scripts/quick_validate.py`: it enforces this exact key set and rejects anything else, since unknown keys silently break skill loading. `allowed-tools` is also valid but left out on purpose: in Claude Code it only pre-approves the listed tools for the invoking turn and never restricts the others.

## `context: fork` (Isolated subagent pattern)

Used by `docs-adr`, `review-security`, and others in this repo for skills that should run without the calling conversation's history: the SKILL.md content becomes the *entire* prompt for the subagent, not an addition to context.

```yaml
---
name: pr-summary
description: Summarize changes in a pull request
context: fork
agent: general-purpose
---

## Pull request context
- PR diff: !`gh pr diff`
- PR comments: !`gh pr view --comments`

## Task
Summarize this pull request...
```

Use this when the skill's job is self-contained (e.g., "analyze this PR and report back") rather than conversational. Don't use it for skills that need to reference what the user already said earlier in the session: that context won't be there.

## Argument substitution

| Variable | Description |
|----------|-------------|
| `$ARGUMENTS` | All arguments passed when invoking the skill |
| `$0`, `$1`, `$2`... | Specific argument by 0-based index |

If the skill body never references `$ARGUMENTS`, any arguments passed are appended automatically as `ARGUMENTS: <value>` at the end.

## Dynamic context injection

The `` !`command` `` syntax runs a shell command before the skill content reaches Claude; the command's output replaces the placeholder inline. Used in `docs-init`, `docs-update`, `git-commit`, `git-release` for injecting live repo state (diffs, current file contents) without a separate tool call.

```markdown
## Current state
- Changed files: !`git diff --name-only`
```
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: 471kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall