release-prep
The release-prep skill automates production release preparation by sequentially executing a full audit across 11 parallel agents, creating a prioritized fix plan, implementing critical P1 issues only, running verification tests, validating deployment readiness, and generating a release PR with documented changes. Use this when preparing a codebase for production deployment to ensure all critical issues are addressed and deployment blockers are eliminated.
git clone --depth 1 https://github.com/undeadlist/claude-code-agents /tmp/release-prep && cp -r /tmp/release-prep/skills/release-prep ~/.claude/skills/release-prepSKILL.md
# Release Prep Workflow Prepare for a production release. Runs full audit, fixes critical issues, validates deployment readiness, and generates the release PR. ## Execution (Sequential Phases) ### Phase 1: Full Audit (Parallel) Spawn all 11 audit agents in parallel (same as `/full-audit`): - All auditors save reports to `.claude/audits/AUDIT_*.md` ### Phase 2: Fix Planning Spawn `fix-planner`: - Read all audit reports - Create `.claude/audits/FIXES.md` with prioritized action items ### Phase 3: Critical Fixes Spawn `code-fixer`: - Implement **P1 (critical) fixes only** - P2/P3 can wait for next release ### Phase 4: Verification Spawn `test-runner`: - All tests pass (including after fixes) - No regressions introduced ### Phase 5: Deploy Validation Spawn `deploy-checker`: - Build succeeds - Environment valid - Dependencies clean ### Phase 6: PR Generation Spawn `pr-writer`: - Generate release PR with summary of all changes - Include audit findings and fixes applied ## Release Criteria ### Must Pass (Blockers) - Zero P1 issues remaining - All tests pass - Build succeeds - Deploy checker passes ### Should Pass (Document if not) - P2 issues addressed or documented - Performance within acceptable range - Documentation updated ## Usage ``` /release-prep Version: 2.1.0 Release date: 2024-03-15 ```
API endpoint testing. Discovery, validation, auth flows, error handling.
Supervisor agent. Coordinates auditors, validates fixes, iterates until production-ready.
Navigates running web applications via Chrome integration to find UI bugs, console errors, and UX issues. Uses /chrome tools to interact with localhost or deployed apps.
Runtime bug scanner. Finds error handling gaps, race conditions, memory leaks, null refs.
Fix bugs with regression prevention using test-first approach
Code quality auditor. Reviews patterns, maintainability, complexity, consistency.
Implements fixes from FIXES.md. Production-quality code following project patterns.
Real-time console monitoring during browser sessions. Watches for errors, warnings, and logs as you test.