agent-launcher-orchest…
Use when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account — "build me an agent", "launch this as a…
Produce consistent, auditable release notes from Conventional Commits. Separates commit parsing, semantic-bump logic, and changelog rendering for automated releases with editorial control. Use when cutting a release, generating CHANGELOG.md from git history, computing the next
$ npx -y skills add alirezarezvani/claude-skills --skill changelog-generator --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/changelog-generatorContext preview
The summary Claude sees to decide when to auto-load this skill.
Produce consistent, auditable release notes from Conventional Commits. Separates commit parsing, semantic-bump logic, and changelog rendering for automated releases with editorial control. Use when cutting a release, generating CHANGELOG.md from git history, computing the next
name: "changelog-generator" description: "Produce consistent, auditable release notes from Conventional Commits. Separates commit parsing, semantic-bump logic, and changelog rendering for automated releases with editorial control. Use when cutting a release, generating CHANGELOG.md from git history, computing the next semantic version from commits, automating release notes in CI, or planning a hotfix/rollback. Examples: 'generate the changelog for v1.4.0', 'what version bump do these commits require', 'we need an emergency hotfix process'."
**Tier:** POWERFUL **Category:** Engineering **Domain:** Release Management / Documentation
Use this skill to produce consistent, auditable release notes from Conventional Commits. It separates commit parsing, semantic bump logic, and changelog rendering so teams can automate releases without losing editorial control.
python3 scripts/generate_changelog.py \ --from-tag v1.3.0 \ --to-tag v1.4.0 \ --next-version v1.4.0 \ --format markdown
git log v1.3.0..v1.4.0 --pretty=format:'%s' | \ python3 scripts/generate_changelog.py --next-version v1.4.0 --format markdown python3 scripts/generate_changelog.py --input commits.txt --next-version v1.4.0 --format json
python3 scripts/generate_changelog.py \ --from-tag v1.3.0 \ --to-tag HEAD \ --next-version v1.4.0 \ --write CHANGELOG.md
When the user has not decided the next version, derive it instead of guessing:
git log v1.3.0..HEAD --oneline | \ python3 scripts/version_bumper.py --current-version 1.3.0 --output-format json
Output JSON contains `recommended_version`, `bump_type` (`major`/`minor`/`patch`/`none`), and with `--include-commands` the exact `git tag` commands. Feed `recommended_version` into `generate_changelog.py --next-version`. Pre-releases: add `--prerelease alpha|beta|rc`. Input must be real `git log --oneline` output (hex hashes); a sample lives at `assets/sample_git_log.txt`.
python3 scripts/commit_linter.py --from-ref origin/main --to-ref HEAD --strict --format text
Or file/stdin:
python3 scripts/commit_linter.py --input commits.txt --strict cat commits.txt | python3 scripts/commit_linter.py --format json
Supported types:
Breaking changes:
SemVer mapping:
1. Mixing merge commit messages with release commit parsing 2. Using vague commit summaries that cannot become release notes 3. Failing to include migration guidance for breaking changes 4. Treating docs/chore changes as user-facing features 5. Overwriting historical changelog sections instead of prepending
1. Keep commits small and intent-driven. 2. Scope commit messages (`feat(api): ...`) in multi-package repos. 3. Enforce linter checks in PR pipelines. 4. Review generated markdown before publishing. 5. Tag releases only after changelog generation succeeds. 6. Keep an `[Unreleased]` section for manual curation when needed.
When a release goes wrong, classify before acting (full procedures in [references/hotfix-procedures.md](references/hotfix-procedures.md)):
| Severity | Definition | SLA | Approval | |---|---|---|---| | P0 — Critical | Outage, data loss, exploited vulnerability | Fix deployed ≤ 2h; emergency deploy bypasses normal gates | Engineering Lead + On-call Manager | | P1 — High | Major feature broken, significant user impact | Fix deployed ≤ 24h; expedited review | Engineering Lead + Product Manager | | P2 — Medium | Minor issues, limited impact | Next release cycle | Standard PR review |
Hotfix branch comes from the last stable tag, contains the minimal fix only, and gets its own patch-bump changelog entry via the workflow above.
Pre-commit to these thresholds before tagging; roll back when any fires:
| Trigger | Threshold | |---|---| | Error rate spike | > 2x baseline within 30 min | | Performance degradation | > 50% latency increase | | Feature failure | Core functionality broken | | Security incident | Vulnerability being exploited | | Data corruption | Database integrity compromised |
Prefer feature-flag disable over code rollback; database rollbacks only for non-destructive migrations (forward-only migrations preferred). See [references/hotfix-procedures.md](references/hotfix-procedures.md).
388 production-ready Claude Code skills, plugins, and agent skills for 13 AI coding tools. The most comprehensive open-source library of Claude Code skills and agent plugins — also works with OpenAI Codex, Gemini CLI, Cursor, and 9 more coding agents.
Repo: alirezarezvani/claude-skills
Use when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account — "build me an agent", "launch this as a…
Phase 3 of building a Claude Managed Agent — the bounded grade→iterate loop. Define a CMA outcome (a required markdown rubric graded by an isolated grader),…
Phase 1 of building a Claude Managed Agent — interview the founder about the one job the agent should do, then produce a build sheet (CMA primitives table +…
Phase 4 of building a Claude Managed Agent — make it run without you. Turn a graded agent into a recurring scheduled deployment (POSIX-cron), an event-driven…
Phase 2 of building a Claude Managed Agent — turn a validated build sheet into exact API payloads and a resumable BYOK curl launch script, then launch…
Close out a launched Claude Managed Agent — recap every primitive the founder now owns, regenerate the single-file overview page, and suggest the next 1-2…