Agent Automation
Mandatory workflow that AI agents MUST execute after EVERY implementation.
11 stars
byhivellm
Best use case
Agent Automation is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Mandatory workflow that AI agents MUST execute after EVERY implementation.
Teams using Agent Automation should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
$curl -o ~/.claude/skills/agent-automation/SKILL.md --create-dirs "https://raw.githubusercontent.com/hivellm/rulebook/main/templates/skills/core/agent-automation/SKILL.md"
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/agent-automation/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How Agent Automation Compares
| Feature / Agent | Agent Automation | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Mandatory workflow that AI agents MUST execute after EVERY implementation.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
<!-- AGENT_AUTOMATION:START --> # Agent Automation Rules **CRITICAL**: Mandatory workflow that AI agents MUST execute after EVERY implementation. ## Workflow Overview After completing ANY feature, bug fix, or code change, execute this workflow in order: ### Step 1: Quality Checks (MANDATORY) Run these checks in order - ALL must pass: ```bash 1. Type check (if applicable) 2. Lint (MUST pass with ZERO warnings) 3. Format code 4. Run ALL tests (MUST pass 100%) 5. Verify coverage meets threshold (default 95%) ``` **Language-specific commands**: See your language template (TYPESCRIPT, RUST, PYTHON, etc.) for exact commands. **IF ANY CHECK FAILS:** - ❌ STOP immediately - ❌ DO NOT proceed - ❌ DO NOT commit - ✅ Fix the issue first - ✅ Re-run ALL checks ### Step 2: Security & Dependency Audits ```bash # Check for vulnerabilities (language-specific) # Check for outdated dependencies (informational) # Find unused dependencies (optional) ``` **Language-specific commands**: See your language template for audit commands. **IF VULNERABILITIES FOUND:** - ✅ Attempt automatic fix - ✅ Document if auto-fix fails - ✅ Include in Step 5 report - ❌ Never ignore critical/high vulnerabilities without user approval ### Step 3: Update OpenSpec Tasks If `openspec/` directory exists: ```bash # Mark completed tasks as [DONE] # Update in-progress tasks # Add new tasks if discovered # Update progress percentages # Document deviations or blockers ``` ### Step 4: Update Documentation ```bash # Update ROADMAP.md (if feature is milestone) # Update CHANGELOG.md (conventional commits format) # Update feature specs (if implementation differs) # Update README.md (if public API changed) ``` ### Step 5: Git Commit **ONLY after ALL above steps pass:** **⚠️ CRITICAL: All commit messages MUST be in English** ```bash git add . git commit -m "<type>(<scope>): <description> - Detailed change 1 - Detailed change 2 - Tests: [describe coverage] - Coverage: X% (threshold: 95%) Closes #<issue> (if applicable)" ``` **Commit Types**: `feat`, `fix`, `docs`, `refactor`, `perf`, `test`, `build`, `ci`, `chore` **Language Requirement**: Commit messages must be written in English. Never use Portuguese, Spanish, or any other language. ### Step 6: Report to User ``` ✅ Implementation Complete 📝 Changes: - [List main changes] 🧪 Quality Checks: - ✅ Type check: Passed - ✅ Linting: Passed (0 warnings) - ✅ Formatting: Applied - ✅ Tests: X/X passed (100%) - ✅ Coverage: X% (threshold: 95%) 🔒 Security: - ✅ No vulnerabilities 📊 OpenSpec: - ✅ Tasks updated - ✅ Progress: X% → Y% 📚 Documentation: - ✅ CHANGELOG.md updated - ✅ [other docs updated] 💾 Git: - ✅ Committed: <commit message> - ✅ Hash: <commit hash> 📋 Next Steps: - [ ] Review changes - [ ] Push to remote (if ready) ``` ## Automation Exceptions Skip steps ONLY when: 1. **Exploratory Code**: User says "experimental", "draft", "try" - Still run quality checks - Don't commit 2. **User Explicitly Requests**: User says "skip tests", "no commit" - Only skip requested step - Warn about skipped steps 3. **Emergency Hotfix**: Critical production bug - Run minimal checks - Document technical debt **In ALL other cases: Execute complete workflow** ## Error Recovery If workflow fails 3+ times: ```bash 1. Create backup branch 2. Reset to last stable commit 3. Report to user with error details 4. Request guidance or try alternative approach ``` ## Best Practices ### DO's ✅ - ALWAYS run complete workflow - ALWAYS update OpenSpec and documentation - ALWAYS use conventional commits - ALWAYS report summary to user - ASK before skipping steps ### DON'Ts ❌ - NEVER skip quality checks without permission - NEVER commit failing tests - NEVER commit linting errors - NEVER skip documentation updates - NEVER assume user wants to skip automation - NEVER commit debug code or secrets ## Summary **Complete workflow after EVERY implementation:** 1. ✅ Quality checks (type, lint, format, test, coverage) 2. ✅ Security audit 3. ✅ Update OpenSpec tasks 4. ✅ Update documentation 5. ✅ Git commit (conventional format) 6. ✅ Report summary to user **Only skip with explicit user permission and document why.** <!-- AGENT_AUTOMATION:END -->
Related Skills
We are still matching the closest adjacent skills for this page. In the meantime, continue through the full directory.