本文へ移動
cccskills
無料GitHub で公開

changelog-generator

Transform git commit history into polished user-facing changelogs and release notes. Use when the user wants a CHANGELOG.md from a version tag or date range, weekly product updates, app store release notes, or Keep a Changelog formatted output with internal noise filtered out.

インストール方法を見る

含まれるファイル(1)

  • SKILL.md2.4 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Changelog Generator

Scans commits across a date range or version tag, categorizes changes, strips internal noise, and rewrites technical language into plain prose.

Source Repository


/changelog

Point at a commit range, version tag, or time window.

Workflow:

  1. Gather commits via git log for the requested range.
  2. Filter out internal noise — refactors, test-only, CI/chore commits unless user wants them.
  3. Group by type: New Features, Improvements, Bug Fixes, Security.
  4. Rewrite each entry in user-facing language (benefits, not implementation details).
  5. Format per Keep a Changelog or the user's style guide if provided.
  6. Output ready-to-commit CHANGELOG.md or alternate format (Notion post, app store notes).

Grouping rules:

Commit signalCategory
feat:, new capabilityNew Features
fix:, regressionBug Fixes
perf:, refactor: (user-visible)Improvements
security:, CVE, auth fixSecurity
chore:, ci:, test:Filter out (default)

Example Prompts

  • Generate a changelog for commits between v1.4.0 and v1.5.0. Group by features, improvements, bug fixes, security. User-facing language.
  • Create release notes from commits in the past 7 days. Filter chore/ci/test. Output as a Notion-ready product update post.
  • Write app store release notes for iOS v3.2 since the last tag. Max 200 words. Friendly and benefit-focused.

Style Guide Support

If the user provides a style guide file, enforce:

  • Terminology (feature names, product voice)
  • Tone (formal vs casual)
  • Formatting (bullet vs paragraph, emoji policy)

Guardrails

  • Run git log in the correct repo root — confirm with user if ambiguous.
  • Do not invent features not present in commits.
  • Flag breaking changes explicitly in a dedicated section.
  • For app store notes, respect platform character limits.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Design, analyze, and document A/B tests for conversion, onboarding, pricing, lifecycle, and product experiments. Use when the user asks for `/ab-test-setup`, experiment design, sample size, statistical significance, A/B test analysis, ICE-scored test backlogs, or avoiding common testing mistakes.

日本語の概要は準備中です。原文の説明を表示しています。

eigent-ai/agent-skills242026年5月27日 更新

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

日本語の概要は準備中です。原文の説明を表示しています。

eigent-ai/agent-skills242026年5月27日 更新

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

日本語の概要は準備中です。原文の説明を表示しています。

eigent-ai/agent-skills242026年5月27日 更新

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

日本語の概要は準備中です。原文の説明を表示しています。

eigent-ai/agent-skills242026年5月27日 更新

Full legal plugin suite for commercial contract review, privacy/DPA analysis, and AI governance vendor reviews. Use when the user invokes /commercial-legal:review, /privacy-legal:dpa-review, /ai-governance-legal:vendor-ai-review, renewal tracking, DSAR responses, or EU AI Act triage.

日本語の概要は準備中です。原文の説明を表示しています。

eigent-ai/agent-skills242026年5月27日 更新

Review contracts with clause-by-clause risk scoring, market benchmarks, negotiability ratings, and redline suggestions. Use when the user pastes an NDA, SaaS/MSA, M&A LOI, or payment agreement and wants a Contract Safety Score, CUAD-based risk breakdown, or /review as [position] analysis.

日本語の概要は準備中です。原文の説明を表示しています。

eigent-ai/agent-skills242026年5月27日 更新

eigent-ai のスキルをすべて見る

このスキルの問題を報告する