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-0-discovery.yaml

View on GitHub
# Phase 0: Discovery - Reflection Criteria
# Research & validation phase

phase: 0
name: "Discovery"
description: "Research, stakeholder identification, competitive analysis"

criteria:
  - id: why_alignment
    name: "WHY Alignment"
    weight: 3
    checks:
      - "Is the research answering the fundamental WHY question?"
      - "Are we validating the right problem, not jumping to solutions?"
      - "Does this help decide if we should proceed?"
    scoring:
      excellent: "Research directly addresses core business/user need"
      acceptable: "Research is relevant but slightly tangential"
      poor: "Research doesn't connect to the stated problem"

  - id: phase_compliance
    name: "Phase Compliance"
    weight: 2
    checks:
      - "Staying in research mode, not proposing solutions?"
      - "Not writing PRD content yet?"
      - "Not making architecture decisions?"
    scoring:
      excellent: "Pure research and validation"
      acceptable: "Mostly research with minor solution hints"
      poor: "Already proposing features or technical solutions"

  - id: correctness
    name: "Research Quality"
    weight: 3
    checks:
      - "Are facts verified from reliable sources?"
      - "Is competitive analysis accurate and current?"
      - "Are stakeholder needs correctly captured?"
    scoring:
      excellent: "Well-sourced, verified, comprehensive research"
      acceptable: "Good research with minor gaps"
      poor: "Unverified claims, outdated info, missing key data"

  - id: security
    name: "Confidentiality"
    weight: 2
    checks:
      - "No sensitive business data exposed inappropriately?"
      - "Competitive intel handled appropriately?"
      - "Stakeholder information protected?"
    scoring:
      excellent: "All sensitive information properly handled"
      acceptable: "Minor confidentiality considerations needed"
      poor: "Sensitive data exposed or mishandled"

  - id: completeness
    name: "Coverage"
    weight: 2
    checks:
      - "All relevant stakeholders identified?"
      - "Key competitors analyzed?"
      - "Market context understood?"
      - "Success metrics proposed?"
    scoring:
      excellent: "Comprehensive coverage of all discovery areas"
      acceptable: "Main areas covered, some gaps"
      poor: "Major stakeholders or competitors missing"

threshold: 7
max_iterations: 3

notes:
  borderline: "Consider deeper stakeholder interviews or market research"
  improvement_focus:
    - "Validate assumptions with data"
    - "Ensure all stakeholder perspectives captured"
    - "Check for cognitive biases in analysis"
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