ilandahan/AID / skills/reflection
reflection
VerifiedAutomatic quality check on significant outputs via isolated sub-agent. Spawns reflection-agent for objective evaluation without conversation context bias.
| File | Kind | Size |
|---|---|---|
| SKILL.extended.md | markdown | 13.1 KB |
| SKILL.md | skill md | 4.8 KB |
| criteria/phase-0-discovery.yaml | config | 2.5 KB |
| criteria/phase-1-prd.yaml | config | 2.5 KB |
| criteria/phase-2-tech-spec.yaml | config | 2.6 KB |
| criteria/phase-3-impl-plan.yaml | config | 9.0 KB |
| criteria/phase-4-development.yaml | config | 3.4 KB |
| criteria/phase-4a-code-design.yaml | config | 3.9 KB |
| criteria/phase-4b-code-function.yaml | config | 5.0 KB |
| criteria/phase-5-qa-ship.yaml | config | 3.7 KB |
criteria/phase-2-tech-spec.yaml
View on GitHub# Phase 2: Technical Specification - Reflection Criteria
# System architecture and design phase
phase: 2
name: "Tech Spec"
description: "System architecture, API design, data models, security architecture"
criteria:
- id: why_alignment
name: "WHY Alignment"
weight: 3
checks:
- "Does architecture serve the business requirements from PRD?"
- "Are design decisions justified with clear reasoning?"
- "Trade-offs explained with WHY for chosen approach?"
scoring:
excellent: "Every design decision has clear WHY linked to requirements"
acceptable: "Most decisions justified, some assumptions"
poor: "Architecture without clear connection to requirements"
- id: phase_compliance
name: "Phase Compliance"
weight: 2
checks:
- "Designing system, not implementing it?"
- "Not writing production code?"
- "Staying at architecture level, not task breakdown?"
scoring:
excellent: "Pure architecture and design"
acceptable: "Mostly design with minor implementation hints"
poor: "Contains implementation code or task lists"
- id: correctness
name: "Technical Soundness"
weight: 3
checks:
- "Architecture is technically feasible?"
- "Patterns are appropriate for the problem?"
- "Scalability considered correctly?"
- "No obvious technical flaws?"
scoring:
excellent: "Sound architecture with proven patterns"
acceptable: "Good design with minor concerns"
poor: "Technical flaws or inappropriate patterns"
- id: security
name: "Security Architecture"
weight: 3
checks:
- "Security architecture defined?"
- "Authentication/authorization design complete?"
- "Data protection strategy clear?"
- "Threat model considered?"
scoring:
excellent: "Comprehensive security architecture"
acceptable: "Basic security considerations present"
poor: "Security not adequately addressed"
- id: completeness
name: "Design Coverage"
weight: 2
checks:
- "All components from PRD have design?"
- "Integration points defined?"
- "Error handling strategy clear?"
- "Non-functional requirements addressed?"
scoring:
excellent: "Complete design covering all requirements"
acceptable: "Main components designed, some gaps"
poor: "Major components or integrations missing"
threshold: 7
max_iterations: 3
notes:
borderline: "Review trade-off documentation and integration points"
improvement_focus:
- "Document WHY for each major decision"
- "Add security threat considerations"
- "Clarify component interactions"
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |