Skip to content

ilandahan/AID / skills/reflection

reflection

Verified

Automatic quality check on significant outputs via isolated sub-agent. Spawns reflection-agent for objective evaluation without conversation context bias.

criteria/phase-5-qa-ship.yaml

View on GitHub
# Phase 5: QA & Ship - Reflection Criteria
# Testing, validation, deployment, release

phase: 5
name: "QA & Ship"
description: "Quality assurance, acceptance testing, deployment, release"

criteria:
  - id: why_alignment
    name: "WHY Alignment"
    weight: 3
    checks:
      - "Tests verify the original requirements are met?"
      - "QA validates user needs, not just technical specs?"
      - "Release delivers promised value?"
    scoring:
      excellent: "QA directly validates business value"
      acceptable: "QA covers technical requirements"
      poor: "QA disconnected from original WHY"

  - id: phase_compliance
    name: "Phase Compliance"
    weight: 2
    checks:
      - "All previous phases completed and approved?"
      - "Not adding new features (scope creep)?"
      - "Following release procedures?"
    scoring:
      excellent: "Clean phase transition, no scope creep"
      acceptable: "Minor adjustments within scope"
      poor: "Adding features or skipping approvals"

  - id: correctness
    name: "Test Quality"
    weight: 3
    checks:
      - "Tests actually test the right things?"
      - "Test assertions are meaningful?"
      - "No false positives or negatives?"
      - "Acceptance criteria properly validated?"
    scoring:
      excellent: "Comprehensive, meaningful tests"
      acceptable: "Good test coverage with minor gaps"
      poor: "Tests don't properly validate requirements"

  - id: security
    name: "Security Validation"
    weight: 3
    checks:
      - "Security tests included?"
      - "Penetration testing done if required?"
      - "No security regressions?"
      - "Deployment is secure?"
    scoring:
      excellent: "Comprehensive security validation"
      acceptable: "Basic security testing done"
      poor: "Security not adequately tested"

  - id: completeness
    name: "Release Readiness"
    weight: 2
    checks:
      - "All acceptance criteria pass?"
      - "Documentation complete?"
      - "Deployment procedure tested?"
      - "Rollback plan ready?"
      - "Monitoring in place?"
    scoring:
      excellent: "Fully release-ready with all checks passed"
      acceptable: "Ready with minor items to address"
      poor: "Not ready for release"

  - id: test_code_quality
    name: "Test Code Quality"
    weight: 3
    checks:
      - "Tests organized in proper directory structure (unit/integration/e2e)?"
      - "No hardcoded credentials in test code or README?"
      - "Tests verified to run in any order (--randomize passed)?"
      - "All existing tests still pass (no regressions)?"
      - "Assertions are meaningful (specific values, not just existence)?"
      - "Tests can actually fail (mutation test passed)?"
    scoring:
      excellent: "Clean, organized, secure, independent tests with strong assertions"
      acceptable: "Minor organization issues, no security problems, tests work"
      poor: "Disorganized, hardcoded secrets, broken tests, or weak assertions"

  - id: test_independence
    name: "Test Independence"
    weight: 2
    checks:
      - "Tests pass when run in isolation?"
      - "Tests pass when run in random order?"
      - "No shared mutable state between tests?"
      - "Setup in beforeEach, not beforeAll for mutable state?"
      - "Proper cleanup in afterEach?"
    scoring:
      excellent: "All tests verified independent, run in any order"
      acceptable: "Tests appear independent, not fully verified"
      poor: "Tests depend on execution order or share state"

threshold: 7
max_iterations: 3

notes:
  borderline: "Review acceptance criteria coverage and rollback plan"
  improvement_focus:
    - "Ensure all acceptance criteria have tests"
    - "Validate security requirements"
    - "Confirm deployment procedure"
    - "Verify monitoring and alerting"
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall