Skill Create

name: skill-create description: Analyze local git history to extract coding patterns and generate SKILL.md files. Local version of the Skill Creator GitHub App. allowed_tools: ["Bash", "Read", "Write", "Grep", "Glob"]

$skill-create - Local Skill Generation

Native Subagent Protocol (Codex)

Codex supports native subagents. Delegate with spawn_agent, coordinate with send_input, collect via wait_agent, and clean up with close_agent.

Execution preference:

1. Use native subagents first for independent workstreams (parallel when possible).
2. Merge results in main thread and run final verification.
3. Fallback only when delegation is blocked: use the [ANALYST]/[ARCHITECT]/[EXECUTOR]/[REVIEWER] structure in a single response.

Minimal orchestration pattern:

spawn_agent -> send_input (optional) -> wait_agent -> close_agent

Analyze your repository's git history to extract coding patterns and generate SKILL.md files that teach Codex your team's practices.

Usage

$skill-create                    # Analyze current repo
$skill-create --commits 100      # Analyze last 100 commits
$skill-create --output ./skills  # Custom output directory
$skill-create --instincts        # Also generate instincts for continuous-learning-v2

What It Does

1. Parses Git History - Analyzes commits, file changes, and patterns
2. Detects Patterns - Identifies recurring workflows and conventions
3. Generates SKILL.md Drafts - Creates first-pass Codex skill files
4. Prepares Handoff - Produces input for $skill-development refinement
5. Optionally Creates Instincts - For the continuous-learning-v2 system

Recommended Combined Workflow

Treat $skill-create as draft generation, then run quality refinement and validation:

1. $skill-create - Generate skill drafts from repo history
2. $skill-development - Refine structure, trigger quality, and progressive disclosure
3. $skill-quality-analyzer - Score and identify documentation defects
4. $skill-tester - Verify functional behavior with concrete test prompts

Definition of done:

• Trigger phrases are unambiguous
• Guidance is executable in current Codex CLI
• Governance checks pass in the repository

Analysis Steps

Step 1: Gather Git Data

# Get recent commits with file changes
git log --oneline -n ${COMMITS:-200} --name-only --pretty=format:"%H|%s|%ad" --date=short

# Get commit frequency by file
git log --oneline -n 200 --name-only | grep -v "^$" | grep -v "^[a-f0-9]" | sort | uniq -c | sort -rn | head -20

# Get commit message patterns
git log --oneline -n 200 | cut -d' ' -f2- | head -50

Step 2: Detect Patterns

Look for these pattern types:

Step 3: Generate SKILL.md

Output format:

---
name: {repo-name}-patterns
description: Coding patterns extracted from {repo-name}
version: 1.0.0
source: local-git-analysis
analyzed_commits: {count}
---

# {Repo Name} Patterns

## Commit Conventions
{detected commit message patterns}

## Code Architecture
{detected folder structure and organization}

## Workflows
{detected repeating file change patterns}

## Testing Patterns
{detected test conventions}

Step 4: Generate Instincts (if --instincts)

For continuous-learning-v2 integration:

---
id: {repo}-commit-convention
trigger: "when writing a commit message"
confidence: 0.8
domain: git
source: local-repo-analysis
---

# Use Conventional Commits

## Action
Prefix commits with: feat:, fix:, chore:, docs:, test:, refactor:

## Evidence
- Analyzed {n} commits
- {percentage}% follow conventional commit format

Example Output

Running $skill-create on a TypeScript project might produce:

---
name: my-app-patterns
description: Coding patterns from my-app repository
version: 1.0.0
source: local-git-analysis
analyzed_commits: 150
---

# My App Patterns

## Commit Conventions

This project uses **conventional commits**:
- `feat:` - New features
- `fix:` - Bug fixes
- `chore:` - Maintenance tasks
- `docs:` - Documentation updates

## Code Architecture

src/ ├── components/ # React components (PascalCase.tsx) ├── hooks/ # Custom hooks (use*.ts) ├── utils/ # Utility functions ├── types/ # TypeScript type definitions └── services/ # API and external services

## Workflows

### Adding a New Component
1. Create `src/components/ComponentName.tsx`
2. Add tests in `src/components/__tests__/ComponentName.test.tsx`
3. Export from `src/components/index.ts`

### Database Migration
1. Modify `src/db/schema.ts`
2. Run `pnpm db:generate`
3. Run `pnpm db:migrate`

## Testing Patterns

- Test files: `__tests__/` directories or `.test.ts` suffix
- Coverage target: 80%+
- Framework: Vitest

GitHub App Integration

For advanced features (10k+ commits, team sharing, auto-PRs), use the Skill Creator GitHub App:

• Install: github.com/apps/skill-creator
• Comment $skill-creator analyze on any issue
• Receives PR with generated skills

Related Commands

• $instinct-import - Import generated instincts
• $instinct-status - View learned instincts
• $evolve - Cluster instincts into skills/agents

Part of Everything Codex