release skill
Release preparation workflow - security audit → E2E tests → review → changelog → docs
A100/100content scan
Is the release skill safe?
Clean: nothing in its files matched our rules. We read 1 file in the folder on 2026-09-28.
No findings.
Install the release skill
A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description.
git clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3.git /tmp/Continuous-Claude-v3 mkdir -p ~/.claude/skills cp -r /tmp/Continuous-Claude-v3/.claude/skills/release ~/.claude/skills/release
available in every project
In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub
The instructions your agent would load
SKILL.md as published, without the frontmatter. Read it on GitHub
/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 notesAgent Sequence
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 guideMinor Release (New Features)
/release --minor
→ Full workflow, lighter security reviewPatch Release (Bug Fixes)
/release --patch
→ Security + tests + quick reviewHotfix
/release --hotfix
→ Expedited: aegis → atlas → heraldExample
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
More skills from parcadei/Continuous-Claude-v3
- Aagent-context-isolationAgent Context Isolation
- Aagent-orchestrationAgent Orchestration Rules
- Aagentic-workflowAgentic Workflow Pattern
- Aagentica-claude-proxyGuide for integrating Agentica SDK with Claude Code CLI proxy
- Aagentica-infrastructureReference guide for Agentica multi-agent infrastructure APIs
- Aagentica-promptsWrite reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity
- Aagentica-sdkBuild Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration
- Aagentica-serverAgentica server + Claude proxy setup - architecture, startup sequence, debugging
- Aagentica-spawnSpawn Agentica multi-agent patterns
- Aanalytic-functionsProblem-solving strategies for analytic functions in complex analysis
- Aast-grep-findAST-based code search and refactoring via ast-grep MCP
- Aasync-repl-protocolAsync REPL Protocol