release
Release preparation workflow - security audit → E2E tests → review → changelog → docs
- Installs
- 481
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/parcadei/continuous-claude-v3 --skill release- 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 release 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.
/release - Release Workflow
Structured release preparation to ship with confidence.
When to Use
- "Prepare a release"
- "Ship version X"
- "Release to production"
- "Cut a release"
- "Ready to deploy"
- Before any production deployment
Workflow Overview
┌─────────┐ ┌─────────┐ ┌──────────────┐ ┌──────────┐ ┌─────────┐
│ aegis │───▶│ atlas │───▶│ review-agent │───▶│ herald │───▶│ scribe │
│ │ │ │ │ │ │ │ │ │
└─────────┘ └─────────┘ └──────────────┘ └──────────┘ └─────────┘
Security E2E Final Version Release
audit tests review bump notes
Agent Sequence
| # | Agent | Role | Output |
|---|---|---|---|
| 1 | aegis | Security vulnerability scan | Security report |
| 2 | atlas | Run full E2E test suite | Test report |
| 3 | review-agent | Final release review | Release approval |
| 4 | herald | Version bump, changelog generation | Updated version files |
| 5 | scribe | Release notes, documentation | RELEASE.md, docs |
Why This Order?
- Security first: Catch vulnerabilities before they ship
- E2E tests: Verify full system works end-to-end
- Final review: Human-in-the-loop approval
- Version bump: Only after approval
- Documentation: Ship with proper release notes
Execution
Phase 1: Security Audit
Task(
subagent_type="aegis",
prompt="""
Security audit for release: [VERSION]
Scan for:
- Dependency vulnerabilities (npm audit, pip audit)
- Hardcoded secrets/credentials
- SQL injection, XSS, CSRF risks
- Authentication/authorization issues
- Insecure configurations
Output: Security report with severity levels
"""
)
Phase 2: E2E Tests
Task(
subagent_type="atlas",
prompt="""
Run E2E tests for release: [VERSION]
Execute:
- Full E2E test suite
- Critical path tests
- Integration tests
- Performance benchmarks (if applicable)
Output: Test report with pass/fail counts
"""
)
Phase 3: Final Review
Task(
subagent_type="review-agent",
prompt="""
Final release review: [VERSION]
Review:
- Security audit results
- E2E test results
- Changes since last release (git log)
- Breaking changes
- Migration requirements
Output: RELEASE_APPROVED or RELEASE_BLOCKED with reasons
"""
)
Phase 4: Version Bump & Changelog
Task(
subagent_type="herald",
prompt="""
Prepare release: [VERSION]
Tasks:
- Bump version in package.json/pyproject.toml
- Generate CHANGELOG.md entry
- Update version constants in code
- Tag commit (don't push yet)
Follow semantic versioning.
"""
)
Phase 5: Release Notes
Task(
subagent_type="scribe",
prompt="""
Write release notes: [VERSION]
Include:
- Summary of changes
- New features
- Bug fixes
- Breaking changes
- Migration guide (if needed)
- Contributors
Output: RELEASE.md or update docs
"""
)
Release Types
Major Release (Breaking Changes)
/release --major
→ Full workflow with migration guide
Minor Release (New Features)
/release --minor
→ Full workflow, lighter security review
Patch Release (Bug Fixes)
/release --patch
→ Security + tests + quick review
Hotfix
/release --hotfix
→ Expedited: aegis → atlas → herald
Example
User: /release v2.0.0
Claude: Starting /release workflow for v2.0.0...
Phase 1: Security audit...
[Spawns aegis]
✅ No critical vulnerabilities
⚠️ 2 low-severity issues (documented)
Phase 2: E2E tests...
[Spawns atlas]
✅ 156/156 E2E tests passing
Phase 3: Final review...
[Spawns review-agent]
✅ RELEASE_APPROVED
- 47 commits since v1.9.0
- 3 new features
- 12 bug fixes
- No breaking changes
Phase 4: Version bump...
[Spawns herald]
✅ Version bumped to 2.0.0
✅ CHANGELOG.md updated
✅ Git tag created
Phase 5: Release notes...
[Spawns scribe]
✅ RELEASE-v2.0.0.md created
┌─────────────────────────────────────────┐
│ Release v2.0.0 Ready │
├─────────────────────────────────────────┤
│ Security: ✅ Passed │
│ Tests: ✅ 156/156 │
│ Review: ✅ Approved │
│ │
│ Next steps: │
│ 1. git push origin v2.0.0 │
│ 2. Create GitHub release │
│ 3. Deploy to production │
└─────────────────────────────────────────┘
Blockers
The workflow stops if:
- Critical security vulnerability found
- E2E tests failing
- Review verdict is RELEASE_BLOCKED
Phase 1: Security audit...
❌ CRITICAL: SQL injection in user.py:45
Release blocked. Fix critical issues before proceeding.
Flags
--major/--minor/--patch: Semantic version type--hotfix: Expedited release path--skip-security: Skip security audit (not recommended)--dry-run: Run checks without bumping version
FAQ
What does the release skill do?
Release preparation workflow - security audit → E2E tests → review → changelog → docs
How do I install release?
Run npx skills add https://github.com/parcadei/continuous-claude-v3 --skill release 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/release/ (personal) or .claude/skills/release/ (project).
Which AI agents can use release?
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 release 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 release?
It is published by parcadei in parcadei/continuous-claude-v3. It has 481 recorded installs.
More from parcadei/continuous-claude-v3
discovery-interview
parcadei/continuous-claude-v3
Deep interview process to transform vague ideas into detailed specs. Works for technical and non-technical users.
premortem
parcadei/continuous-claude-v3
Identify failure modes before they occur using structured risk analysis
math
parcadei/continuous-claude-v3
Unified math capabilities - computation, solving, and explanation. I route to the right tool.
github-search
parcadei/continuous-claude-v3
Search GitHub code, repositories, issues, and PRs via MCP
dead-code
parcadei/continuous-claude-v3
Find unused functions and dead code in the codebase
refactor
parcadei/continuous-claude-v3
Code refactoring workflow - analyze → plan → implement → review → validate
Popular testing & qa skills
tdd
mattpocock/skills
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
grilling
mattpocock/skills
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
migrate-to-shoehorn
mattpocock/skills
Migrate test files from as type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace as in tests, or needs partial test data.
run-train
lllllllama/rigorpilot-skills
Rigor Train skill for deep learning research repositories. Use when a documented or selected training command should be run conservatively for startup verification, short-run verification, full kickoff, or resume, with command, config, seed, log, checkpoint, status, and metric evidence written to standardized trainoutputs/. Do not use for environment setup, exploratory sweeps, speculative idea implementation, or end-to-end orchestration.
test-driven-development
obra/superpowers
Use when implementing any feature or bugfix, before writing implementation code
finishing-a-development-branch
obra/superpowers
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work