본문으로 건너뛰기
cccskills
무료GitHub에 공개

release-notes

Generate changelog entries and GitHub releases from git history. Categorizes commits into features, fixes, breaking changes, and docs. Supports conventional commits, PR-based grouping, and semantic versioning. Creates formatted CHANGELOG.md entries and GitHub releases.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

연동 도구GitHub
설치 방법 보기

포함된 파일(4)

  • SKILL.md5.8 KB
  • EXAMPLES.md4.9 KB
  • LICENSE1.0 KB
  • REFERENCE.md4.3 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

release-notes

Generate changelog entries and GitHub releases from git history.

Install

claude skill add --from https://github.com/thatrebeccarae/claude-skills/release-notes

When to Use

  • Cutting a release: You have commits ready to ship and need a changelog entry and/or GitHub release.
  • Monthly changelog update: You maintain a regular changelog cadence and need to capture everything since the last entry.
  • Retroactive changelog: An existing project has no CHANGELOG.md and you want to generate one from the full git history.

Usage

Generate a changelog entry

/release-notes changelog [repo-path]

Reads commits since the last tag, categorizes them, and prepends a new entry to CHANGELOG.md.

Create a changelog entry and GitHub release

/release-notes release [repo-path] [version]

Does everything changelog does, then creates a GitHub release via gh release create. If version is omitted, a version is suggested based on the changes detected.

Retroactively generate a full changelog

/release-notes init [repo-path]

Walks the entire tag history (or full commit history if untagged) and generates a complete CHANGELOG.md from scratch.

Procedure

Step 1 — Find the last tag or release

Run git describe --tags --abbrev=0 to find the most recent tag. If no tags exist, use the initial commit as the starting point. Cross-reference with gh release list --limit 1 to check for GitHub releases that may differ from local tags.

Step 2 — Collect commits since last tag

git log <last-tag>..HEAD --pretty=format:"%H %s" --no-merges

Parse each commit message for conventional commit prefixes (type(scope): description). Record the raw message for commits that do not follow conventional format.

Step 3 — Check merged PRs

gh pr list --state merged --search "merged:>YYYY-MM-DD" --json number,title,labels,mergedAt --limit 200

Use the date of the last tag as the cutoff. Cross-reference PR titles with commit messages to avoid duplicates. PR titles often provide cleaner descriptions than commit messages — prefer the PR title when a commit is associated with a merged PR.

Step 4 — Categorize changes

Map each commit or PR to a changelog category:

Prefix / SignalCategory
feat, featureAdded
fixFixed
BREAKING CHANGE in body or ! suffix (e.g., feat!:)Breaking Changes
docsDocumentation
refactor, perfChanged
chore, ci, buildMaintenance
deprecateDeprecated
removeRemoved
securitySecurity

When conventional commits are not used: Analyze commit message content to infer categories. Look for keywords like "add", "fix", "remove", "update", "refactor", "document". Group ambiguous commits under Changed and flag them for human review.

Step 5 — Suggest version bump

Apply semantic versioning rules:

  • Major bump if any Breaking Changes are present.
  • Minor bump if any Added entries exist and no breaking changes.
  • Patch bump if only Fixed, Changed, or Maintenance entries.

Present the suggestion with reasoning. The human decides the final version.

Step 6 — Format the changelog entry

Use Keep a Changelog format:

## [X.Y.Z] — YYYY-MM-DD

### Breaking Changes
- Description of breaking change (#PR)

### Added
- Description of new feature (#PR)

### Fixed
- Description of bug fix (#PR)

### Changed
- Description of refactor or improvement (#PR)

### Documentation
- Description of docs change (#PR)

### Maintenance
- Description of chore (#PR)

Omit empty categories. Order categories as shown above — Breaking Changes always first.

Step 7 — Human review

Present the formatted entry and suggested version to the user. Wait for explicit approval before writing anything. Highlight any commits that were ambiguously categorized.

Step 8 — Write to CHANGELOG.md

Prepend the new entry after the file header. Never overwrite or reorder existing entries. If CHANGELOG.md does not exist, create it with a standard header:

# Changelog

All notable changes to this project will be documented in this file.

The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).

Step 9 — Optionally create GitHub release

Only when the user invoked /release-notes release or explicitly requests it:

gh release create vX.Y.Z --title "vX.Y.Z" --notes "RELEASE_BODY"

Use the changelog entry as the release body. Never create a release without user confirmation.

Key Principles

  1. Never auto-publish. Every release and changelog write requires explicit human approval.
  2. Preserve existing entries. Never modify, reorder, or delete previous changelog entries.
  3. Human-readable over machine-parseable. Write descriptions that make sense to a person reading the changelog, not a parser. Prefer plain language over commit hashes.
  4. Attribute PRs and authors. Include PR numbers as links. For multi-contributor projects, consider noting first-time contributors.
  5. When in doubt, ask. If a commit is ambiguous, surface it to the user rather than guessing the category.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

A/B and multivariate testing methodology. Design experiments, calculate sample sizes, determine statistical significance, avoid common pitfalls, and interpret results. Platform-agnostic framework applicable to landing pages, emails, ads, pricing, and product features. Use when the user asks about A/B testing, split testing, experiment design, statistical significance, or conversion experiments.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

thatrebeccarae/claude-marketing1732026년 5월 15일 업데이트

Google and Meta paid media account structure evaluation. Audits campaign/ad set architecture against conversion volume minimums, budget thresholds, and targeting overlap. Identifies over-segmentation, under-segmentation, budget fragmentation, and structural anti-patterns blocking algorithmic learning. Provides consolidation roadmaps with migration plans. Use when inheriting accounts, quarterly health checks, or before scaling budgets.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

thatrebeccarae/claude-marketing1732026년 5월 15일 업데이트

Answer Engine Optimization (AEO) and Generative Engine Optimization (GEO) specialist. Optimize content and websites to appear in AI-generated answers from ChatGPT, Perplexity, Claude, Google AI Overviews, and other LLM-powered search experiences. Use when the user asks about AI search optimization, AEO, GEO, AI Overviews, appearing in AI answers, LLM citations, or optimizing for generative search.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

thatrebeccarae/claude-marketing1732026년 5월 15일 업데이트

brand-dna

무료

Extract brand identity from a website URL — voice, colors, typography, imagery, values, and target audience — into a structured brand-profile.json. The profile feeds downstream skills (seo-content-writer, email-composer, frontend-design, pro-deck-builder, cross-platform-audit) for brand-consistent output. Use when the user says brand DNA, brand profile, extract brand, analyze brand, brand voice, brand identity, brand colors, or brand style guide.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

thatrebeccarae/claude-marketing1732026년 5월 15일 업데이트

Develop brand voice, tone matrices, messaging frameworks, and brand book documentation. Use when the user asks about brand voice, tone of voice, brand guidelines, messaging framework, or brand consistency.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

thatrebeccarae/claude-marketing1732026년 5월 15일 업데이트

braze

무료

Braze customer engagement platform expertise. Audit campaigns, Canvases, segments, messaging channels, and data architecture. Use when the user asks about Braze, customer engagement, push notifications, in-app messaging, cross-channel orchestration, or lifecycle marketing at scale.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

thatrebeccarae/claude-marketing1732026년 5월 15일 업데이트

thatrebeccarae의 스킬 모두 보기

이 스킬의 문제 신고