acedergren/agentic-tools/prod-readiness
Claude Code and agent skill by acedergren/agentic-tools
- community
Checking that the SKILL.md file is still in the repository.
Use when assessing release readiness or running a pre-launch review. Spawns 5 specialist agents in parallel (security, testing, performance, observability, code quality) and synthesizes a prioritized report with ship/don't-ship recommendation. Keywords: production readiness, release review, pre-launch, security audit, test coverage, ship checklist. Triggers on "assess production readiness" or "run launch review".
Install
npx vskill@latest install acedergren/agentic-tools/prod-readinessSKILL.md
Prod-Readiness
When to Use
Load this skill when the user request matches the frontmatter description for Prod-Readiness.
Spawns 5 specialist review agents in parallel, each writing findings to a dedicated report file. Synthesizes into a prioritized production readiness report with executive summary, blockers, and remediation plan.
Do NOT load when
- user wants only one narrow review (use the relevant specialist skill instead)
- codebase is mid-implementation with a knowingly broken baseline
- task is to fix issues rather than assess readiness
NEVER
- Never run on a dirty working tree — uncommitted changes mean agent findings don't map to a stable commit; findings become unreproducible and the report loses traceability
- Never run on a failing baseline — a red test suite makes it impossible to distinguish pre-existing failures from review findings; always confirm baseline is green first
- Never synthesize before all 5 agents finish writing — partial synthesis produces a report that omits entire dimensions; a CRITICAL finding from a slow agent gets buried in LOW backlog
- Never let agents write to the same file — each agent has its own
REVIEW_*.md; shared files produce interleaved, unparseable output - Never commit REVIEW_*.md files from a previous run without clearing them — stale findings from a prior session mixed with new ones produce a misleading severity distribution
- Never rate an issue CRITICAL without a file:line reference — untraceable CRITICALs create review fatigue and get deprioritized the same as vague LOWs
Pre-flight (always run before spawning agents)
If tests are failing: warn the user, do not proceed until baseline is green.
Agent specializations
Team name: prod-review-<YYYYMMDD>
Spawn all 5 in parallel via TeamCreate + Task.
| Agent | Report file | Domain | |
|---|---|---|---|
| security-auditor | REVIEW_SECURITY.md | OWASP Top 10, RBAC gaps, input validation, secrets, auth flows, webhook security | |
| test-coverage-analyst | REVIEW_TESTING.md | Uncovered critical paths, always-passing tests, missing error path tests, flaky patterns | |
| performance-infra | REVIEW_PERFORMANCE.md | N+1 queries, unbounded queries, missing indexes, memory leaks, graceful shutdown, rate limiting | |
| observability-analyst | REVIEW_OBSERVABILITY.md | Unhandled rejections, PII in logs, error response consistency, structured logging, health endpoint | |
| code-quality | REVIEW_QUALITY.md | Dead code, circular deps, TODO/FIXME density, package boundary violations, type safety gaps |
security-auditor prompt
test-coverage-analyst prompt
performance-infra prompt
observability-analyst prompt
code-quality prompt
Monitor agents
If no file update from an agent in 2 minutes, send a check-in message.
Synthesize
Run after all 5 REVIEW_*.md exist. Use node scripts/summarize-review-reports.js or manually synthesize into PRODUCTION_READINESS_REPORT.md:
Each item: **[CATEGORY] Title** with File:Line, Risk, Effort (S/M/L), Fix.
Final quality gate
Append results to report.
Commit and shutdown
Shut down all agents, clean up team.
Arguments
- (empty) — full review
--quick— skip performance and code-quality agents, focus on security and test coverage--security-only— spawn only security-auditor--no-commit— generate reports but don't commit
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/prod-readiness/SKILL.md
Popularity
- Repository stars
- 8
- Repository forks
- 1
- 7-day trend score
- 11
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 1 Apr 2026, 7 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/acedergren/agentic-tools/prod-readiness)