changelog-generator
Generate changelogs from git commits. Use when user says "generate changelog", "update changelog", "what changed since last release", or before preparing a new release.
- Installs
- 229
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/decebals/claude-code-java --skill changelog-generator- 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-generator 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 Generator Skill
Generate changelogs from conventional commits for Java projects.
When to Use
- Before a release
- User says "generate changelog" / "update changelog" / "what changed since last release"
- After completing a milestone
Versioning Convention Detection
Detect versioning style using this priority order:
1. Check CLAUDE.md (if exists)
grep -A5 "## Versioning" CLAUDE.md 2>/dev/null
Look for explicit convention:
## Versioning
This project uses Semantic Versioning (x.y.z).
Tag format: `release-x.y.z`
2. Fallback: Detect from git tags
git tag --sort=-version:refname | head -10
| Pattern detected | Versioning style |
|---|---|
v3.15.0, 3.15.0 | SemVer (x.y.z) |
release-3.15.0 | SemVer with prefix |
v2.1, 2.1 | Two-component (x.y) |
2026.01, 26.1 | CalVer |
| No pattern | Ask user |
3. Fallback: Detect from CHANGELOG.md
grep -E "^\#+ \[.*\]" CHANGELOG.md | head -5
Extract version format from existing entries.
4. Last resort: Ask user
No versioning convention detected. Which format does this project use?
- Semantic Versioning (x.y.z) - e.g., 3.15.0
- Two-component (x.y) - e.g., 2.1
- Calendar Versioning - e.g., 2026.01
Supported Versioning Styles
| Style | Format | Tag examples | Version bump |
|---|---|---|---|
| SemVer | x.y.z | v3.15.0, release-3.15.0 | major.minor.patch |
| Two-component | x.y | v2.1, 2.1 | major.minor |
| CalVer | YYYY.MM[.patch] | 2026.01, 2026.01.1 | year.month[.patch] |
Legacy Projects (CLAUDE.md without versioning section)
If CLAUDE.md exists but has no versioning info:
- Don't assume - detect from tags/changelog
- If detected, optionally suggest adding to CLAUDE.md:
Detected versioning: SemVer (x.y.z) with tag prefix 'release-' Want me to add this to CLAUDE.md for future reference?
Output Format
Supports two formats - detect from existing CHANGELOG.md or ask user preference.
Format A: Keep a Changelog (h2 versions)
# Changelog
## [Unreleased]
## [1.2.0] - 2026-01-29
### Added
- [#123]: New feature for plugin dependencies
### Changed
- [#456]: Improved performance of plugin loading
### Fixed
- [#234]: Resolved NPE when directory missing
Format B: pf4j style (h3 versions)
## Change Log
### [Unreleased][unreleased]
### [3.15.0] - 2026-01-29
#### Added
- [#123]: New feature for plugin dependencies
#### Changed
- [#456]: Improved performance of plugin loading
#### Fixed
- [#234]: Resolved NPE when directory missing
Reference-Style Links (Recommended)
Use reference-style links for cleaner, more readable entries:
#### Fixed
- [#648]: Restore missing `module-info.class` in multi-release JAR
- [#625]: Fix exception handling inconsistency in `startPlugin()`
#### Added
- [#629]: Validate dependency state on plugin start
- [#633]: Allow customization of `PluginClassLoader` parent delegation
<!-- At the bottom of the file -->
[#648]: https://github.com/user/repo/issues/648
[#633]: https://github.com/user/repo/pull/633
[#629]: https://github.com/user/repo/pull/629
[#625]: https://github.com/user/repo/pull/625
Benefits:
- Cleaner to read (no long URLs inline)
- Links defined once, reusable
- Easier to write and maintain
Version Comparison Links
Add comparison links at the bottom for easy diff viewing:
[unreleased]: https://github.com/user/repo/compare/release-3.15.0...HEAD
[3.15.0]: https://github.com/user/repo/compare/release-3.14.1...release-3.15.0
[3.14.1]: https://github.com/user/repo/compare/release-3.14.0...release-3.14.1
Pattern: [version]: https://github.com/{owner}/{repo}/compare/{previous-tag}...{current-tag}
Section Order
Adapt to existing file, or use this default order:
| Section | When to use |
|---|---|
| Fixed | Bug fixes |
| Changed | Changes to existing functionality |
| Added | New features |
| Deprecated | Soon-to-be removed features |
| Removed | Removed features |
| Security | Vulnerability fixes (CVEs) |
Note: pf4j uses Fixed → Changed → Added → Removed. Keep a Changelog uses Added → Changed → Deprecated → Removed → Fixed → Security.
Rule: Follow existing file's order if present.
Mapping Conventional Commits to Changelog
| Commit Type | Changelog Section |
|---|---|
| feat | Added |
| fix | Fixed |
| perf | Changed |
| refactor | Changed |
| build(deps) | Changed or Security (if CVE) |
| BREAKING CHANGE | Changed (with bold note) |
| deprecate | Deprecated |
Workflow
-
Check for existing CHANGELOG.md
cat CHANGELOG.md | head -20Detect format (h2 vs h3 versions, section order, link style).
-
Determine version range
# Find last tag git describe --tags --abbrev=0 # List recent tags git tag --sort=-version:refname | head -5 -
Get commits since last release
git log v3.14.1..HEAD --oneline -
Extract issue/PR references Look for patterns:
#123,fixes #123,closes #123,(#123) -
Generate changelog entry
- Group by section
- Use reference-style links
- Add version comparison link
-
Suggest version bump (based on detected versioning style)
SemVer (x.y.z):
- BREAKING CHANGE → Major (3.0.0 → 4.0.0)
- feat → Minor (3.14.0 → 3.15.0)
- fix only → Patch (3.14.0 → 3.14.1)
Two-component (x.y):
- BREAKING CHANGE → Major (2.0 → 3.0)
- feat/fix → Minor (2.1 → 2.2)
CalVer (YYYY.MM):
- New month → 2026.01 → 2026.02
- Same month, new release → 2026.01 → 2026.01.1
Token Optimization
- Use
git log --onelinefor initial scan - Only fetch full body if BREAKING CHANGE suspected
- Reuse existing link definitions from file
- Don't re-read entire changelog - just prepend new section
Example: Full Workflow
Input: User says "generate changelog for next release"
Step 1: Check existing format
head -30 CHANGELOG.md
→ Detects pf4j style (h3 versions, Fixed first)
Step 2: Find version range
git describe --tags --abbrev=0
→ release-3.15.0
Step 3: Get commits
git log release-3.15.0..HEAD --oneline
→ 5 commits found
Step 4: Generate entry
### [Unreleased][unreleased]
#### Fixed
- [#650]: Fix memory leak in extension factory
#### Changed
- [#651]: Rename `LegacyExtension*` to `IndexedExtension*`
#### Added
- [#652]: Add support for plugin priority ordering
Step 5: Generate link definitions
[#652]: https://github.com/pf4j/pf4j/pull/652
[#651]: https://github.com/pf4j/pf4j/pull/651
[#650]: https://github.com/pf4j/pf4j/issues/650
Step 6: Update version comparison links
[unreleased]: https://github.com/pf4j/pf4j/compare/release-3.15.0...HEAD
Step 7: Suggest version
Suggested: 3.16.0 (minor - has new feature)
Handling Edge Cases
No conventional commits
List under "Changed" with original message:
#### Changed
- Updated plugin loading mechanism
- Refactored test utilities
Security fix
#### Security
- [#618], [#623]: Fix path traversal vulnerabilities in ZIP extraction
Breaking change
#### Changed
- **BREAKING**: [#645] Renamed `LegacyExtension*` classes to `IndexedExtension*`
Multiple issues for same fix
- [#630], [#631]: Set `failedException` when plugin validation fails
Integration with Existing CHANGELOG.md
-
Read existing file to detect:
- Heading level (## or ### for versions)
- Section order
- Link style (reference or inline)
- Existing link definitions
-
Insert new version after
[Unreleased]section -
Merge link definitions - add new ones, keep existing
-
Update
[unreleased]comparison link to point to new version
Quick Reference
| User says | Action |
|---|---|
| "generate changelog" | Full changelog since last tag |
| "changelog since v3.14" | From specific version |
| "what's unreleased" | Preview unreleased changes |
| "update changelog for 3.16" | Generate and insert for version |
| "add changelog entry for #123" | Single issue entry |
FAQ
What does the changelog-generator skill do?
Generate changelogs from git commits. Use when user says "generate changelog", "update changelog", "what changed since last release", or before preparing a new release.
How do I install changelog-generator?
Run npx skills add https://github.com/decebals/claude-code-java --skill changelog-generator 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-generator/ (personal) or .claude/skills/changelog-generator/ (project).
Which AI agents can use changelog-generator?
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-generator 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-generator?
It is published by decebals in decebals/claude-code-java. It has 229 recorded installs.
More from decebals/claude-code-java
java-code-review
decebals/claude-code-java
Systematic code review for Java with null safety, exception handling, concurrency, and performance checks. Use when user says "review code", "check this PR", "code review", or before merging changes.
clean-code
decebals/claude-code-java
Clean Code principles (DRY, KISS, YAGNI), naming, function design and readability. Use when code is hard to read, with long methods, unclear names, duplication or deep nesting. For how responsibilities are split across classes and which way dependencies point, use solid-principles instead.
concurrency-review
decebals/claude-code-java
Review Java concurrency code for thread safety, race conditions, deadlocks, and modern patterns (Virtual Threads, CompletableFuture, @Async). Use when user asks "check thread safety", "concurrency review", "async code review", or when reviewing multi-threaded code.
solid-principles
decebals/claude-code-java
SOLID principles checklist with Java examples. Use when a class has too many responsibilities, an abstraction leaks, or a dependency points the wrong way, and when the user asks about Single Responsibility, Open/Closed, Liskov, Interface Segregation or Dependency Inversion. For naming, duplication and method length, use clean-code instead.
architecture-review
decebals/claude-code-java
Analyze Java project architecture at macro level - package structure, module boundaries, dependency direction, and layering. Use when user asks "review architecture", "check structure", "package organization", or when evaluating if a codebase follows clean architecture principles.
design-patterns
decebals/claude-code-java
Common design patterns with Java examples (Factory, Builder, Strategy, Observer, Decorator, etc.). Use when user asks "implement pattern", "use factory", "strategy pattern", or when designing extensible components.
Popular backend & apis skills
find-skills
vercel-labs/skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
entra-app-registration
microsoft/azure-skills
Guides Microsoft Entra ID app registration, OAuth 2.0 authentication, and MSAL integration. USE FOR: create app registration, register Azure AD app, configure OAuth, set up authentication, add API permissions, generate service principal, MSAL example, console app auth, Entra ID setup, Azure AD authentication. DO NOT USE FOR: Key Vault secrets (use azure-keyvault-expiration-audit), general Azure resource security guidance.
google-agents-cli-adk-code
google/agents-cli
This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management" — in a project that needs ADK (Agent Development Kit) API patterns and code examples. It provides a quick reference for agent types, tool definitions, orchestration patterns, callbacks, state management, the graph Workflow API, and reference recipes to study. Do NOT use for scaffolding (use google-agents-cli-scaffold) or deployment (use google-agents-cli-deploy).
embedded-captions
heygen-com/hyperframes
Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet anchor rail is the default; embed every word only when the user explicitly wants a fully cinematic treatment. The workflow runs locally end to end, including transcription and subject matting; split multi-shot footage before applying it.
entra-agent-id
microsoft/azure-skills
Provision Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph, and configure OAuth 2.0 token exchange (fmipath, OBO, cross-tenant) including the Microsoft Entra SDK for AgentID sidecar. USE FOR: Agent Identity Blueprint, BlueprintPrincipal, agent OAuth, fmipath token exchange, agent OBO, Workload Identity Federation for agents, polyglot agent auth, Microsoft.Identity.Web.AgentIdentities. DO NOT USE FOR: standard Entra app registration (use entra-app-registration), Microsoft Foundry agent authoring (use microsoft-foundry).
neon
neondatabase/agent-skills
Overview of Neon, a complete set of cloud backend primitives around Lakebase Postgres: Auth, Object Storage, Functions, the AI Gateway, and Realtime. Start here to choose Neon for undecided login, files, APIs, and LLM calls, set up the CLI or MCP server, and follow the branch-first workflow. Use when building an app or backend on Neon, or when "Neon" or "Lakebase Postgres" is mentioned. Child skill neon-postgres wins for an existing DATABASEURL, SQL, schema, inspect, or search. Child skill neon-auth wins for login, users, sessions, identity routing, and Managed Better Auth setup. Child skill neon-realtime wins for live queries in reactive apps and agents. Also use for object storage, S3, buckets, serverless functions, function triggers, cron, AI gateway, LLM calls, realtime, logs, Loki, Grafana, observability, postgres, database, backend, Claimable Neon, neon.new, or a no-signup database.