Menu
Use when you need to validate cross-references, stage matrix, or debate consistency.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
| name | team-shinchan:verify-consistency |
| description | Use when you need to validate cross-references, stage matrix, or debate consistency. |
| user-invocable | false |
When this skill is invoked, execute immediately. Do not explain.
| Validator | Command | What it checks |
|---|---|---|
| cross-refs | cd "${CLAUDE_PLUGIN_ROOT}" && node tests/validate/cross-refs.js | CLAUDE.md agent/skill references match actual files |
| stage-matrix | cd "${CLAUDE_PLUGIN_ROOT}" && node tests/validate/stage-matrix.js | Workflow stage definitions are consistent |
| debate-consistency | cd "${CLAUDE_PLUGIN_ROOT}" && node tests/validate/debate-consistency.js | Debate panelist and topic configurations are valid |
CLAUDE.mdcd "${CLAUDE_PLUGIN_ROOT}" && node tests/validate/cross-refs.js
Success criteria:
On failure:
cd "${CLAUDE_PLUGIN_ROOT}" && node tests/validate/stage-matrix.js
Success criteria:
On failure:
cd "${CLAUDE_PLUGIN_ROOT}" && node tests/validate/debate-consistency.js
Success criteria:
On failure:
Phase 2 (interview-metrics-researc-002) added the DAG executor on top of the frozen Phase 1
contracts (agents/misae.md 4-step option pipeline, skills/fierce-option-panel/ Workflow,
src/option-metrics.js). Phase 2 only ADDS new exports/modules; it MUST NOT alter Phase 1
function signatures. The DAG schema fields (id, depends_on, touches, verify, estimate,
scope) and the executor module must remain consistent with docs/dag-executor.md.
cd "${CLAUDE_PLUGIN_ROOT}" && node --test tests/option-metrics.test.js && node --test tests/dag-executor.test.js
Success criteria:
tests/option-metrics.test.js still passes (no signature regression, NFR-2)tests/dag-executor.test.js passesdag-executor.js into option-metrics.js (dependency-inversion ban)On failure:
docs/dag-executor.md cross-phase safety)Use when you have a large-scale, multi-phase project requiring orchestrated execution.
Use when you need persistent looping until a task is fully complete.
Deterministic adversarial code review for high-stakes scope — independent per-dimension review, a non-skippable per-finding refutation, completeness + interaction critics, and a deterministic 3-lens rubric judge panel. Opt-in main-loop Workflow tier.
Use when the user wants to review accumulated skill feedback, verdict trends, or improvement candidates collected during Stage 4 retrospectives. Trigger on "show skill feedback", "스킬 피드백 보여줘", or finding which skills need /writing-skills work.
Deterministic competitive code tournament — N builders independently solve one task and return patches, an Action-Kamen judge scores them head-to-head, the winner is picked by score and applied. Opt-in main-loop Workflow tier.
Deterministic adversarial debate for high-stakes or irreversible decisions — mandatory refutation plus a scored judge panel. Opt-in main-loop Workflow tier.