release-skills

WHAT: Universal release workflow with auto-detection, multi-language changelogs, semantic versioning, and git tagging. WHEN: User wants to create a release, bump version, update changelog, push a new version, or prepare for deployment. KEYWORDS: "release", "发布", "new version", "新版本", "bump version", "update version", "更新版本", "push", "推送", "create release", "prepare release", "tag version"

7 stars

Best use case

release-skills is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

WHAT: Universal release workflow with auto-detection, multi-language changelogs, semantic versioning, and git tagging. WHEN: User wants to create a release, bump version, update changelog, push a new version, or prepare for deployment. KEYWORDS: "release", "发布", "new version", "新版本", "bump version", "update version", "更新版本", "push", "推送", "create release", "prepare release", "tag version"

Teams using release-skills should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/release-skills/SKILL.md --create-dirs "https://raw.githubusercontent.com/wpank/ai/main/skills/tools/release-skills/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/release-skills/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How release-skills Compares

Feature / Agentrelease-skillsStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

WHAT: Universal release workflow with auto-detection, multi-language changelogs, semantic versioning, and git tagging. WHEN: User wants to create a release, bump version, update changelog, push a new version, or prepare for deployment. KEYWORDS: "release", "发布", "new version", "新版本", "bump version", "update version", "更新版本", "push", "推送", "create release", "prepare release", "tag version"

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Release Skills

Universal release workflow supporting any project type with multi-language changelog generation.

## Supported Projects

| Type | Version File | Auto-Detected |
|------|--------------|---------------|
| Node.js | package.json | ✓ |
| Python | pyproject.toml | ✓ |
| Rust | Cargo.toml | ✓ |
| Claude Plugin | marketplace.json | ✓ |
| Generic | VERSION / version.txt | ✓ |

## Options

| Flag | Description |
|------|-------------|
| `--dry-run` | Preview changes without executing |
| `--major` | Force major version bump |
| `--minor` | Force minor version bump |
| `--patch` | Force patch version bump |


## Installation

### OpenClaw / Moltbot / Clawbot

```bash
npx clawhub@latest install release-skills
```


---

## Workflow

### Step 1: Detect Configuration

1. Check for `.releaserc.yml` (optional config)
2. Auto-detect version file (priority: package.json → pyproject.toml → Cargo.toml → marketplace.json → VERSION)
3. Scan for changelog files: `CHANGELOG*.md`, `HISTORY*.md`, `CHANGES*.md`
4. Identify language of each changelog by suffix

**Language Detection**:
| Pattern | Language |
|---------|----------|
| `CHANGELOG.md` (no suffix) | en |
| `CHANGELOG.zh.md` / `CHANGELOG_CN.md` | zh |
| `CHANGELOG.ja.md` / `CHANGELOG_JP.md` | ja |
| `CHANGELOG.{lang}.md` | Corresponding language |

Output:
```
Project detected:
  Version file: package.json (1.2.3)
  Changelogs: CHANGELOG.md (en), CHANGELOG.zh.md (zh)
```

### Step 2: Analyze Changes

```bash
LAST_TAG=$(git tag --sort=-v:refname | head -1)
git log ${LAST_TAG}..HEAD --oneline
```

Categorize by conventional commit:
- `feat:` → Features
- `fix:` → Fixes  
- `docs:` → Documentation
- `refactor:` → Refactor
- `perf:` → Performance
- `chore:` → Skip in changelog

**Breaking Change Detection**:
- `BREAKING CHANGE` in message or body
- Removed public APIs, renamed exports

Warn if breaking changes: "Consider major version bump (--major)."

### Step 3: Determine Version

Priority:
1. User flag (`--major/--minor/--patch`)
2. BREAKING CHANGE → Major (1.x.x → 2.0.0)
3. `feat:` present → Minor (1.2.x → 1.3.0)
4. Otherwise → Patch (1.2.3 → 1.2.4)

Display: `1.2.3 → 1.3.0`

### Step 4: Generate Changelogs

For each changelog file:

1. Identify language from filename
2. Detect third-party contributors via merged PRs
3. Generate content in that language:
   - Section titles in target language
   - Date format: YYYY-MM-DD
   - Attribution: `(by @username)` for non-owner contributors
4. Insert at file head, preserve existing content

**Section Titles**:
| Type | en | zh | ja |
|------|----|----|-----|
| feat | Features | 新功能 | 新機能 |
| fix | Fixes | 修复 | 修正 |
| docs | Documentation | 文档 | ドキュメント |
| breaking | Breaking Changes | 破坏性变更 | 破壊的変更 |

**Format**:
```markdown
## 1.3.0 - 2026-01-22

### Features
- Add user authentication (by @contributor1)
- Support OAuth2 login

### Fixes
- Fix memory leak in connection pool
```

### Step 5: Group by Module (Optional)

For monorepos, group commits by affected skill/module:

```
baoyu-cover-image:
  - feat: add new style options
  → README updates: options table

baoyu-comic:
  - refactor: improve panel layout
  → No README updates
```

### Step 6: User Confirmation

Present:
- Changelog preview
- Proposed version bump
- Changes summary

Ask:
1. Confirm version bump (show recommended)
2. Push to remote? (Yes/No)

### Step 7: Create Release

```bash
# Stage files
git add <version-file> CHANGELOG*.md

# Commit
git commit -m "chore: release v{VERSION}"

# Tag
git tag v{VERSION}

# Push (if confirmed)
git push origin main
git push origin v{VERSION}
```

**Output**:
```
Release v1.3.0 created.
Tag: v1.3.0
Status: Pushed to origin
```

---

## Scripts

| Script | Purpose |
|--------|---------|
| `scripts/prepare_release.py` | Prepare release with version bump |
| `scripts/release_notes.py` | Generate release notes from commits |
| `scripts/roadmap_changelog.py` | Generate changelog from roadmap |

---

## Configuration (.releaserc.yml)

Optional overrides:

```yaml
version:
  file: package.json
  path: $.version

changelog:
  files:
    - path: CHANGELOG.md
      lang: en
    - path: CHANGELOG.zh.md
      lang: zh

commit:
  message: "chore: release v{version}"

tag:
  prefix: v
```

---

## Dry-Run Mode

With `--dry-run`:
- Show all proposed changes
- Preview changelog entries
- List commits to create
- No actual changes made

---

## Version Paths

| File | Path |
|------|------|
| package.json | `$.version` |
| pyproject.toml | `project.version` |
| Cargo.toml | `package.version` |
| marketplace.json | `$.metadata.version` |
| VERSION | Direct content |

---

## Quality Criteria

Good releases:
- Clear changelog entries describing user-facing changes
- Proper contributor attribution
- Consistent multi-language content
- No orphaned tags (always with commit)
- Version bump matches change significance

---

## NEVER

- Force push to main/master
- Skip user confirmation before push
- Create tags without commits
- Include internal/chore changes in user-facing changelog
- Push without explicit user consent
- Add Co-Authored-By to release commits (they're automated)

Related Skills

find-skills

7
from wpank/ai

Discover and install agent skills from the open skills ecosystem. Use when user asks "how do I do X", "find a skill for", "is there a skill that can", wants to extend capabilities, or mentions needing help with a specific domain. Triggers on find skill, search skill, install skill, npx skills, skills.sh.

schema-markup

7
from wpank/ai

Add, fix, or optimize schema markup and structured data. Use when the user mentions schema markup, structured data, JSON-LD, rich snippets, schema.org, FAQ schema, product schema, review schema, or breadcrumb schema.

prompt-engineering

7
from wpank/ai

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, designing production prompt templates, or building AI-powered features.

professional-communication

7
from wpank/ai

Write effective professional messages for software teams. Use when drafting emails, Slack/Teams messages, meeting agendas, status updates, or translating technical concepts for non-technical audiences. Triggers on email, slack, teams, message, meeting agenda, status update, stakeholder communication, escalation, jargon translation.

persona-docs

7
from wpank/ai

Create persona documentation for a product or codebase. Use when asked to create persona docs, document target users, define user journeys, document onboarding flows, or when starting a new product and needing to define its audience. Persona docs should be the first documentation created for any product.

mermaid-diagrams

7
from wpank/ai

Create software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams including class diagrams, sequence diagrams, flowcharts, ERDs, C4 architecture diagrams, state diagrams, git graphs, and other diagram types. Triggers include requests to diagram, visualize, model, map out, or show the flow of a system.

game-changing-features

7
from wpank/ai

Find 10x product opportunities and high-leverage improvements. Use when the user wants strategic product thinking, mentions 10x, wants to find high-impact features, or asks what would make a product dramatically more valuable.

clear-writing

7
from wpank/ai

Write clear, concise prose for humans — documentation, READMEs, API docs, commit messages, error messages, UI text, reports, and explanations. Combines Strunk's rules for clearer prose with technical documentation patterns, structure templates, and review checklists.

brainstorming

7
from wpank/ai

Explore ideas before implementation through collaborative dialogue. Use before any creative work — creating features, building components, adding functionality, or modifying behavior. Turns ideas into fully formed designs and specs through structured conversation.

Article Illustrator

7
from wpank/ai

When the user wants to add illustrations to an article or blog post. Triggers on: "illustrate article", "add images to article", "generate illustrations", "article images", or requests to visually enhance written content. Analyzes article structure, identifies positions for visual aids, and generates illustrations using a Type x Style two-dimension approach.

subagent-driven-development

7
from wpank/ai

Execute implementation plans by dispatching a fresh subagent per task with two-stage review (spec compliance then code quality). Use when you have an implementation plan with mostly independent tasks and want high-quality, fast iteration within a single session.

skill-judge

7
from wpank/ai

Evaluate Agent Skill quality against official specifications. Use when reviewing SKILL.md files, auditing skill packages, improving skill design, or checking if a skill follows best practices. Provides 8-dimension scoring (120 points) with actionable improvements. Triggers on review skill, evaluate skill, audit skill, improve skill, skill quality, SKILL.md review.