docs-changelog
Write changelog entries for open source documentation sites using Keep a Changelog format. Use when asked to "write a changelog", "update the changelog", "add changelog entry", "document recent changes", or after a release/set of changes that should be recorded. Reviews git commits since the last changelog entry and produces a categorized, human-readable entry.
- Installs
- 39
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/petekp/agent-skills --skill docs-changelog- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads docs-changelog automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Docs Changelog
Write a new changelog entry by reviewing commits since the last documented entry, categorizing changes, and appending a well-written entry in Keep a Changelog format.
Workflow
1. Find the changelog file
Search for the changelog in common locations:
CHANGELOG.md
changelog.md
docs/changelog.md
docs/CHANGELOG.md
src/pages/changelog.md
src/content/changelog.mdx
content/changelog.md
Use glob with patterns like **/changelog.{md,mdx} and **/CHANGELOG.{md,mdx} if not found in standard locations. If multiple candidates exist, ask the user which one to use.
2. Parse the last entry
Read the changelog file and extract the most recent version header. The header format is:
## [X.Y.Z] - YYYY-MM-DD
Extract:
- Version number (e.g.,
1.2.0) — for determining the next version - Date (e.g.,
2025-01-15) — for scoping the git log
If the changelog is empty or has only an [Unreleased] header, use the repo's earliest tag or first commit as the boundary.
3. Gather commits
Run:
git log --oneline --no-merges --after="YYYY-MM-DD" HEAD
Where YYYY-MM-DD is the date from the last changelog entry. Also check tags:
git tag -l --sort=-creatordate | head -5
If there's a tag newer than the last changelog entry, use that as the new version number. Otherwise, ask the user what version this entry should be.
4. Categorize changes
Review each commit and assign it to one Keep a Changelog category:
| Category | What belongs here |
|---|---|
| Added | New features, new pages, new API endpoints |
| Changed | Updates to existing functionality, behavior changes, dependency updates |
| Deprecated | Features marked for future removal |
| Removed | Deleted features, removed pages, dropped support |
| Fixed | Bug fixes, typo corrections, broken link repairs |
| Security | Vulnerability patches, security improvements |
Categorization rules:
- Read the diff when a commit message is ambiguous — the code tells the truth
- Group related commits into a single bullet (e.g., three typo-fix commits become one "Fixed typos across documentation" entry)
- Skip commits that are purely internal (CI config, linting, formatting-only) unless they affect user-visible behavior
- Skip merge commits and version bump commits
5. Write the entry
Insert the new entry directly below the # Changelog header (or below ## [Unreleased] if present). Use this exact structure — omit any category section that has no items:
## [X.Y.Z] - YYYY-MM-DD
### Added
- Brief, human-readable description of what was added
### Changed
- Brief description of what changed
### Fixed
- Brief description of what was fixed
Writing rules:
- Each bullet is one sentence, starting with a past-tense verb (Added, Updated, Fixed, Removed)
- Write for the end user of the documentation site, not for developers
- Link to relevant pages or PRs where helpful:
Fixed broken link on [Getting Started](/docs/getting-started) page - Keep entries scannable — no paragraphs, no sub-bullets
- Use the project's existing tone (scan prior entries to match)
- Today's date for the entry date unless the user specifies otherwise
6. Verify
After writing the entry:
- Confirm the entry is in reverse chronological order (newest first)
- Check that version link references at the bottom of the file are updated if the project uses them (e.g.,
[1.3.0]: https://github.com/org/repo/compare/v1.2.0...v1.3.0) - Read the final file to ensure formatting is clean
Present the new entry to the user for review before considering the task complete.
FAQ
What does the docs-changelog skill do?
Write changelog entries for open source documentation sites using Keep a Changelog format. Use when asked to "write a changelog", "update the changelog", "add changelog entry", "document recent changes", or after a release/set of changes that should be recorded. Reviews git commits since the last changelog entry and produces a categorized, human-readable entry.
How do I install docs-changelog?
Run npx skills add https://github.com/petekp/agent-skills --skill docs-changelog in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/docs-changelog/ (personal) or .claude/skills/docs-changelog/ (project).
Which AI agents can use docs-changelog?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is docs-changelog safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains docs-changelog?
It is published by petekp in petekp/agent-skills. It has 39 recorded installs.
More from petekp/agent-skills
typography
petekp/agent-skills
Apply professional typography principles to create readable, hierarchical, and aesthetically refined interfaces. Use when setting type scales, choosing fonts, adjusting spacing, designing text-heavy layouts, implementing dark mode typography, or when asked about readability, font pairing, line height, measure, typographic hierarchy, variable fonts, font loading, or OpenType features.
macos-app-design
petekp/agent-skills
Use when designing or building native macOS applications with SwiftUI or AppKit. Triggers on menu bar structure, keyboard shortcuts, multi-window behavior, Liquid Glass design system, macOS Tahoe/Sequoia, sidebar navigation, toolbar design, app icons, SF Symbols, or making an app feel like a "good Mac citizen."
optimize-agent-docs
petekp/agent-skills
Build a retrieval-optimized knowledge layer over agent documentation in dotfiles (.claude, .codex, .cursor, .aider). Use when asked to "optimize docs", "improve agent knowledge", "make docs more efficient", or when documentation has accumulated and retrieval feels inefficient. Generates a manifest mapping task-contexts to knowledge chunks, optimizes information density, and creates compiled artifacts for efficient agent consumption.
codebase-study-guide
petekp/agent-skills
Generate a pedagogically-grounded study guide for learning an unfamiliar codebase. Use when the user wants to onboard onto a codebase, understand a project's architecture, create learning materials for a team, or asks things like "help me learn this codebase", "create an onboarding guide", "I'm new to this project", "how does this system work", "study guide for this repo", or "explain this codebase to me". Produces a structured document that builds understanding from purpose to systems to patterns, using evidence-based learning techniques (elaborative interrogation, concept mapping, threshold concepts, worked examples, progressive disclosure).
unix-macos-engineer
petekp/agent-skills
Expert Unix and macOS systems engineer for shell scripting, system administration, command-line tools, launchd, Homebrew, networking, and low-level system tasks. Use when the user asks about Unix commands, shell scripts, macOS system configuration, process management, or troubleshooting system issues.
explainer-visuals
petekp/agent-skills
Create high-quality animated explainer visuals for essays and blog posts. Use when the user wants to visualize concepts, processes, data, or ideas with interactive web animations. Triggers on requests like "create a visual for", "animate this concept", "make an explainer", "visualize this idea", "diagram this process", "show this data", or when essay content would benefit from visual explanation. Handles abstract concepts (mental models, frameworks), technical processes (algorithms, systems), and data visualization (trends, comparisons). Outputs self-contained HTML/CSS/JS that embeds directly in web content.
Popular docs & writing skills
grill-with-docs
mattpocock/skills
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
lark-markdown
open.feishu.cn
飞书 Markdown：查看、创建、上传、编辑和比较飞书中的原生 Markdown 文件。当用户要操作飞书 Markdown 文件，或比较其远端版本及本地草稿时使用。纯本地 Markdown 文件操作不触发本 skill。不负责将 Markdown 导入为飞书在线文档，也不负责文件搜索、权限、评论、移动、删除等云空间管理操作。
writing-beats
mattpocock/skills
Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.
writing-shape
mattpocock/skills
Writing, exploit: shape raw material into an article, paragraph by paragraph.
writing-fragments
mattpocock/skills
Writing, explore: mine raw fragments, no structure yet.
writing-for-agents
mattpocock/skills
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.