skill-self-improvement-verificator

# Skill: Self-Improvement Verificator > [!IMPORTANT] > **TIER 3 (Meta-Skill)**: Use ONLY when creating or modifying `System/Agents`, `System/Docs`, or `GEMINI.md`. ## 1. Purpose This skill acts as a **Guardian** for the Framework itself. Before any changes are applied to the "Brain" of the IDE (Prompts, Skills, Docs), this skill verifies that the proposed changes are safe, consistent, and do not break the "Constitutional" rules (Tier 0 skills). ## 2. Modes This skill operates in two distinct modes depending on the current Stage. ### Mode A: SPECIFICATION AUDIT (Analysis Phase) **Trigger**: When `docs/TASK.md` proposes a Framework Upgrade. **Action**: Verify the Specification. **Checklist**: 1. [ ] **Root Integrity**: Does the update respect `skill-core-principles` (Stub-First, Atomicity)? 2. [ ] **Skill Compatibility**: Do new Agents/Prompts explicitly load `TIER 0` skills? 3. [ ] **Documentation**: Does the task include updating `System/Docs/` to reflect changes? 4. [ ] **Migration**: Does the task describe how to migrate existing sessions (if applicable)? ### Mode B: PLAN AUDIT (Planning Phase) **Trigger**: When `docs/PLAN.md` details the implementation steps. **Action**: Verify the Execution Plan. **Checklist**: 1. [ ] **Verification Step**: Is there an explicit step to run `pytest` or `validation_scripts`? 2. [ ] **Rollback**: Is there a backup step (e.g., `cp GEMINI.md GEMINI.bak`)? 3. [ ] **Atomic Updates**: Are changes broken down into safe, verifiable chunks? 4...