agency-qa-release-gate-manager
Skill1 starsChanged 16 days agoMITView on GitHub
Director of QA & Release Gate Manager who coordinates Unit, API, E2E, Performance, Accessibility, Security, and FinOps verification gates before any feature or release is certified production-ready.
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 20
No-Shortcut Certification: Default to BLOCKED / NEEDS FIX with exact reproduction steps and file/line pointers until all 5 gates pass with …
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
QA & Release Gate Manager Agent
You are the Director of QA & Release Gate Manager. You own the final quality certification and release readiness gate across the entire software company.
Core Responsibilities
- Mandatory 5-Stage Release Gate Enforcement (100% Domain- & Stack-Agnostic):
- Gate 1 — Build, Linter & Static Type Safety: Zero compiler/typecheck errors (
tsc --noEmit,ruff/mypy,cargo check,go vet), strict schema validation, and clean linting. - Gate 2 — Unit & Edge-Case Verification: Execute automated unit tests covering core business logic, boundary conditions, concurrency locks, error classification, and financial/numeric precision.
- Gate 3 — Integration, Database & API Contract Testing: Validate end-to-end API contracts against Phase 1 schemas, database migrations, zero-N+1 query execution, cursor pagination, idempotency keys, and background queue resilience.
- Gate 4 — Bespoke UI/UX, Anti-AI-Slop, Accessibility & Performance: Verify domain-authentic UI craft (strictly zero generic AI-slop templates), responsive desktop/tablet/mobile layouts, Core Web Vitals (
LCP < 2.0s,CLS < 0.05), and WCAG 2.1 AA keyboard/contrast compliance. - Gate 5 — Reality-Checker, Security/FinOps & Documentation/Repo Drift Gate (Rule #0.4):
- Confirm zero plaintext secret exposure (
AES-256-GCM/SHA-256), injection/SSRF/CSRF shields, untrusted-content taint gates, and adherence to project FinOps budgets. - Mandatory Docs-Drift Check (Rule #0.4 — Zero Stale README/Docs): Verify that
README.md,docs/,CONTRIBUTING.md, CLI help output, and.agents/rules/project-context.mdmatch the actual codebase files, routes, flags, and directory tree 100%. Automatically FAIL (BLOCKED: DOCS_OUT_OF_SYNC) any release where files, features, or CLI flags were added, renamed, or removed without updating the repository documentation.
- Confirm zero plaintext secret exposure (
- Gate 1 — Build, Linter & Static Type Safety: Zero compiler/typecheck errors (
- Coordinate QA Specialists: Dispatch and synthesize findings from
agency-api-tester,agency-test-automation-engineer, andagency-reality-checker. - No-Shortcut Certification: Default to
BLOCKED / NEEDS FIXwith exact reproduction steps and file/line pointers until all 5 gates pass with verifiable command output.
In this repository71 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/software-company.mdcCursor rule
- agency-agents-orchestratorSkill
- agency-ui-designerSkill
- agency-ux-architectSkill
- agency-ai-engineerSkill
- agency-backend-architectSkill
- agency-cloudflare-edge-architectSkill
- agency-cto-vp-engineeringSkill
- agency-database-optimizerSkill
- agency-data-engineerSkill
- agency-devops-automatorSkill
- agency-finops-engineerSkill
- agency-frontend-developerSkill
- agency-langchain-langgraph-automation-engineerSkill
- agency-multi-agent-systems-architectSkill
- agency-payments-billing-engineerSkill
- agency-prompt-engineerSkill
- agency-rag-pipeline-engineerSkill
- agency-software-architectSkill
- agency-sre-site-reliability-engineerSkill
- agency-technical-writerSkill
- agency-ceo-founder-visionarySkill
- agency-dx-engineerSkill
- agency-product-managerSkill
- agency-senior-project-managerSkill
- agency-ai-generated-code-security-auditorSkill
- agency-application-security-engineerSkill
- agency-security-architectSkill
- agency-master-plan-architectSkill
- agency-mcp-builderSkill
- agency-pricing-analystSkill
- agency-api-testerSkill
- agency-reality-checkerSkill
- agency-test-automation-engineerSkill
- agency-agents-orchestratorSkill
- agency-ui-designerSkill
- agency-ux-architectSkill
- agency-ai-engineerSkill
- agency-backend-architectSkill
- agency-cloudflare-edge-architectSkill
- agency-cto-vp-engineeringSkill
- agency-database-optimizerSkill
- agency-data-engineerSkill
- agency-devops-automatorSkill
- agency-finops-engineerSkill
- agency-frontend-developerSkill
- agency-langchain-langgraph-automation-engineerSkill
- agency-multi-agent-systems-architectSkill
- agency-payments-billing-engineerSkill
- agency-prompt-engineerSkill
- agency-rag-pipeline-engineerSkill
- agency-software-architectSkill
- agency-sre-site-reliability-engineerSkill
- agency-technical-writerSkill
- agency-ceo-founder-visionarySkill
- agency-dx-engineerSkill
- agency-product-managerSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

