agentleFS
enunoenuno/unifi-mcp-server/.agents/skills/source-command-unifi-mcp-release-prep/SKILL.md

source-command-unifi-mcp-release-prep

Skill294 starsChanged 18 days agoApache-2.0View on GitHub

Prepare a new release with version bump, changelog, and quality checks

We split this skill into the rules it gives an agent

22 rules. About 0 are common, 20 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈20

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill when the user asks to run the migrated source command unifi-mcp-release-prep.

    line 8
  2. Distinctive:

    Ask user for release details:

    line 18
  3. Distinctive:

    Check git status (must be clean or on release branch)

    line 24
  4. Distinctive:

    Verify on main branch or create release branch

    line 25
  5. Distinctive:

    Check for uncommitted changes

    line 26
  6. Distinctive:

    Ensure all tests pass

    line 27
  7. Distinctive:

    Run comprehensive quality checks:

    line 29
  8. Distinctive:

    Run full test suite with coverage:

    line 37
  9. Distinctive:

    Verify coverage meets 80% minimum threshold

    line 39
  10. Distinctive:

    Check that all tests pass

    line 40
  11. Distinctive:

    If coverage < 80%, warn user and ask to proceed

    line 41
  12. Very specific:

    Update pyproject.toml version field

    line 44
  13. Distinctive:

    Update version in README.md badges

    line 46
  14. Distinctive:

    Update Docker image tags in documentation

    line 47
  15. Distinctive:

    Update CHANGELOG.md with new version section

    line 58
  16. Distinctive:

    Run /unifi-mcp-update-docs to sync API.md

    line 61
  17. Distinctive:

    Verify README.md is current

    line 62
  18. Distinctive:

    Check that examples still work

    line 63
  19. Distinctive:

    Update compatibility matrix if needed

    line 64
  20. Distinctive:

    Never release with failing tests

    line 133
  21. Distinctive:

    Verify no uncommitted changes

    line 135
  22. Distinctive:

    Check for security vulnerabilities

    line 136

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

source-command-unifi-mcp-release-prep

Use this skill when the user asks to run the migrated source command unifi-mcp-release-prep.

Command Template

Prepare a new release for the UniFi MCP Server with comprehensive quality checks.

This command orchestrates the complete release preparation process including version bumping, changelog generation, testing, and validation.

Steps to execute:

  1. Ask user for release details:
    • Version number (e.g., "0.2.0") or type (major/minor/patch)
    • Release type: major, minor, patch, or custom
    • Brief release description
  2. Verify current state:
    • Check git status (must be clean or on release branch)
    • Verify on main branch or create release branch
    • Check for uncommitted changes
    • Ensure all tests pass
  3. Run comprehensive quality checks:
    • Code formatting: black --check src/ tests/
    • Import sorting: isort --check-only src/ tests/
    • Linting: ruff check src/ tests/
    • Type checking: mypy src/
    • Security scan: bandit -r src/ -ll
    • Dependency check: safety check
  4. Run full test suite with coverage:
    • Execute: pytest --cov=src --cov-report=term-missing -v
    • Verify coverage meets 80% minimum threshold
    • Check that all tests pass
    • If coverage < 80%, warn user and ask to proceed
  5. Update version numbers:
    • Update pyproject.toml version field
    • Update src/__init__.py version
    • Update version in README.md badges
    • Update Docker image tags in documentation
  6. Generate changelog:
    • Get commits since last tag: git log $(git describe --tags --abbrev=0)..HEAD --oneline
    • Categorize commits:
      • Features (feat:)
      • Bug fixes (fix:)
      • Documentation (docs:)
      • Refactoring (refactor:)
      • Tests (test:)
      • Other changes
    • Update CHANGELOG.md with new version section
  7. Update documentation:
    • Run /unifi-mcp-update-docs to sync API.md
    • Verify README.md is current
    • Check that examples still work
    • Update compatibility matrix if needed
  8. Create release summary:
    • Version number
    • Release date
    • Highlights (top 3-5 features/fixes)
    • Breaking changes (if any)
    • Contributors
    • Full changelog
  9. Prepare release artifacts:
    • Tag format: v{version} (e.g., v0.2.0)
    • Release branch: release/v{version} (if not on main)
    • Draft GitHub release notes

Report back with:

  • Pre-release checklist status:
    • All tests passing
    • Coverage >= 80%
    • No linting errors
    • No type errors
    • No security vulnerabilities
    • Documentation updated
    • Changelog generated
    • Version bumped
  • Release summary
  • Next steps:
    • Review changes
    • Create release tag
    • Push to GitHub
    • Create GitHub release
    • Publish to PyPI (optional)
    • Build and push Docker images

Example workflow:

User: "Prepare release 0.2.0"

Assistant checks:
✓ Git status clean
✓ On main branch
✓ All tests pass (179/179)
✗ Coverage: 34.10% (below 80% target)
✓ No linting errors
✓ No type errors
✓ No security issues

Release Summary:
Version: 0.2.0
Date: 2025-01-15
Type: Minor release

Highlights:
- Zone-Based Firewall implementation (60% complete)
- Traffic Flows integration (100% complete)
- 22 new tool modules
- Comprehensive CI/CD pipeline

Breaking Changes: None

Warning: Test coverage (34.10%) is below 80% target.
Proceed with release? (y/n)

Safety checks:

  • Never release with failing tests
  • Warn if coverage < 80%
  • Verify no uncommitted changes
  • Check for security vulnerabilities
  • Confirm version number doesn't already exist

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.