
changelog
Keep a Changelog format. Covers structure, change types, versioning. Use when creating or updating CHANGELOG.md files following the Keep a Changelog specification, or applying semver-compatible changelog conventions. Keywords: CHANGELOG.md, semver, Keep a Changelog.
- Installs
- 189
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/itechmeat/llm-code --skill 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 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.
Changelog
Format specification for CHANGELOG.md based on Keep a Changelog 1.1.0.
Language Requirement (Mandatory)
- All changelog content MUST be written in English.
- If source information is provided in another language, translate it to English.
- Do not mix languages within the same changelog.
Quick Reference
File 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).
Section Structure
## [Unreleased]
### Added
- New feature description
## [1.0.0] - 2024-01-15
### Added
- Feature A
- Feature B
### Changed
- Modified behavior X
### Fixed
- Bug fix Y
Types of Changes
| Type | Purpose |
|---|---|
Added | New features |
Changed | Changes in existing functionality |
Deprecated | Soon-to-be removed features |
Removed | Now removed features |
Fixed | Bug fixes |
Security | Vulnerabilities |
Format Rules
Version Header
## [X.Y.Z] - YYYY-MM-DD
- Version in brackets, linked to comparison
- Date in ISO 8601 format (YYYY-MM-DD)
Date-Based Versioning (Alternative)
For projects using date-based versioning instead of semver:
## [YYYY-MM-DD]
Use current date instead of [Unreleased]. This project uses date-based versioning.
Yanked Releases
## [0.0.5] - 2014-12-13 [YANKED]
Use when version was pulled due to serious bug or security issue.
Comparison Links (at file end)
[unreleased]: https://github.com/user/repo/compare/v1.0.0...HEAD
[1.0.0]: https://github.com/user/repo/compare/v0.9.0...v1.0.0
[0.9.0]: https://github.com/user/repo/releases/tag/v0.9.0
Guiding Principles
- For humans, not machines — Write clear, readable entries
- Entry for every version — Document all releases
- Group same types — Keep Added/Changed/Fixed together
- Linkable versions — Use comparison links
- Latest first — Reverse chronological order
- Show release dates — Use ISO 8601 format
- State versioning scheme — Mention Semantic Versioning if used
Complete Example
# 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).
## [Unreleased]
### Added
- New authentication method
## [1.2.0] - 2024-01-20
### Added
- User profile page
- Export to CSV functionality
### Changed
- Improved loading performance by 40%
### Deprecated
- Legacy API endpoint `/api/v1/users` (use `/api/v2/users`)
### Fixed
- Login timeout issue on slow connections
## [1.1.0] - 2024-01-10
### Added
- Dark mode support
### Security
- Fixed XSS vulnerability in comment field
## [1.0.0] - 2024-01-01
### Added
- Initial release with core features
- User registration and login
- Dashboard with analytics
[unreleased]: https://github.com/user/project/compare/v1.2.0...HEAD
[1.2.0]: https://github.com/user/project/compare/v1.1.0...v1.2.0
[1.1.0]: https://github.com/user/project/compare/v1.0.0...v1.1.0
[1.0.0]: https://github.com/user/project/releases/tag/v1.0.0
Bad Practices
Commit log diffs
Don't dump git log into changelog:
- Full of noise (merge commits, obscure titles)
- Not human-readable
- Mixes important and trivial changes
Ignoring deprecations
Don't skip deprecation notices:
- Users need to know what will break
- Document deprecations before removals
- List breaking changes clearly
Confusing dates
Don't use regional date formats:
- Use ISO 8601:
YYYY-MM-DD - Avoids ambiguity (is 01/02/2024 Jan 2 or Feb 1?)
Inconsistent changes
Don't document only some changes:
- Changelog should be single source of truth
- Important changes must be mentioned
- Consistently updated
Writing Tips
Good Entry Examples
### Added
- OAuth2 authentication with Google and GitHub providers
- Rate limiting for API endpoints (100 req/min)
### Changed
- Database queries now use prepared statements for better security
- Upgraded dependency `lodash` from 4.17.20 to 4.17.21
### Fixed
- Memory leak in WebSocket connection handler
- Race condition in concurrent file uploads
Entry Guidelines
- Review current git changes (diff or changed files list) before drafting; ensure all material changes are covered.
- Start with verb or noun describing the change
- Be specific (mention affected component/endpoint)
- Reference issue/PR numbers when relevant:
(#123) - Keep entries concise but informative
- Omit empty sections (do not include a section header if there are no entries for it)
File Naming
Required: CHANGELOG.md (uppercase). Do not use lowercase or alternative names.
Do not use alternative filenames.
GitHub Releases vs CHANGELOG.md
| Aspect | GitHub Releases | CHANGELOG.md |
|---|---|---|
| Portability | GitHub-only | Universal |
| Discoverability | Less visible | Standard location |
| Version control | Separate UI | In repository |
| Diff links | Manual setup | Easy to add |
GitHub Releases can complement but shouldn't replace CHANGELOG.md.
Conventional Commits Integration
Changelogs work best with Conventional Commits format:
| Commit Type | Changelog Section |
|---|---|
feat: | Added |
fix: | Fixed |
perf: | Changed |
refactor: | Changed |
docs: | (often omitted) |
BREAKING CHANGE | Highlight in Changed |
| Security fix | Security |
revert: | Removed or Fixed |
Automated Generation
Tools that parse Conventional Commits and generate changelogs:
See commits skill for commit message format.
Workflow Integration
Unreleased Section Pattern
- Add changes to
## [Unreleased]during development - At release time, rename to
## [X.Y.Z] - YYYY-MM-DD - Create new empty
## [Unreleased]section - Add comparison link for new version
Pre-commit Checklist
Before release:
- All notable changes documented
- Unreleased section moved to version
- Date added in ISO 8601 format
- Comparison link added
- Breaking changes highlighted
- Deprecations documented
Critical Prohibitions
- Do not use git log as changelog
- Do not omit breaking changes or deprecations
- Do not use ambiguous date formats
- Do not leave changelog inconsistently updated
- Do not forget to update Unreleased → version at release
- Do not write changelog entries in any language other than English
README Synchronization
After writing changelog, review the project's main README.md:
- Check for outdated information — features, skills, tools lists
- Add new entries — if changelog introduces new skills, features, or components
- Remove deprecated items — if changelog removes functionality
- Update descriptions — if changelog changes existing functionality
What to sync:
- Skills/features tables
- Compatibility lists
- Installation instructions
- Links and references
What NOT to sync:
- Changelog content itself (no duplication)
- Version history
- Detailed change descriptions
Do NOT mention README.md updates in CHANGELOG — README synchronization is implied and should not be logged as a separate change.
Links
- Official specification: https://keepachangelog.com/en/1.1.0/
- Semantic Versioning: https://semver.org/spec/v2.0.0.html
- Related: commits skill — Conventional Commits format
Templates
- CHANGELOG.template.md — Empty template to start
- CHANGELOG.example.md — Complete working example
FAQ
What does the changelog skill do?
Keep a Changelog format. Covers structure, change types, versioning. Use when creating or updating CHANGELOG.md files following the Keep a Changelog specification, or applying semver-compatible changelog conventions. Keywords: CHANGELOG.md, semver, Keep a Changelog.
How do I install changelog?
Run npx skills add https://github.com/itechmeat/llm-code --skill 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/changelog/ (personal) or .claude/skills/changelog/ (project).
Which AI agents can use 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 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 changelog?
It is published by itechmeat in itechmeat/llm-code. It has 189 recorded installs.
More from itechmeat/llm-code
react-testing-library
itechmeat/llm-code
React Testing Library: user-centric component testing with queries, user-event simulation, async utilities, and accessibility-first API. Use when writing React component tests, selecting elements by role/label/text, simulating user events, or testing async UI behavior. Keywords: React Testing Library, @testing-library/react, user-event, queries, render.
openspec
itechmeat/llm-code
OpenSpec artifact-driven workflow. Covers OPSX commands, schemas, project config. Use when applying the artifact-driven workflow (OPSX), planning or reviewing changes based on artifact dependencies, or working with OPSX commands and schema/template resolution. Keywords: OPSX, artifact graph, /opsx:.
mantine-dev
itechmeat/llm-code
Open the skill to read its SKILL.md instructions.
social-writer
itechmeat/llm-code
Open the skill to read its SKILL.md instructions.
base-ui
itechmeat/llm-code
Base UI unstyled React components. Covers forms, menus, overlays, composition. Use when building accessible, unstyled React UI components with @base-ui/react, composing with render props, or implementing custom-styled form controls, menus, and overlays. Keywords: @base-ui/react, render props, unstyled components.
refine-dev
itechmeat/llm-code
Open the skill to read its SKILL.md instructions.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available