メニュー
Verify all 5 LLM providers when modifying provider or LLM runtime logic
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use when bringing the harness method to a NEW or non-sentropic repo — maps the repo's conventions into a harness profile so the same scope/branch/verify kernel applies anywhere.
Use before any creative/design work (a feature, a package, an evolution) — explores intent and design via the spec-ladder with multi-peer adversarial review BEFORE implementation.
Use on any bug, test failure, or unexpected behaviour BEFORE proposing a fix — runs the generic evidence-first root-cause loop.
Use when you have a spec/decisions and need an executable plan — writes a lot-based BRANCH.md from the template and completes with track for realization state.
Use when completing a feature, a design step, or before merging — runs a ≥2-peer consensus review and reconciles the findings, instead of a single rubber-stamp pass.
Use when adding or evolving tests for a feature/bugfix — applies the sentropic test-pyramid, scoped-test loop, environment isolation, and AI-flaky policy.
| name | provider-cascade |
| description | Verify all 5 LLM providers when modifying provider or LLM runtime logic |
| paths | api/src/services/llm-runtime/**,api/src/services/providers/** |
| allowed-tools | Read Bash Grep Glob |
api/src/services/providers/openai-provider.tsapi/src/services/providers/gemini-provider.tsapi/src/services/providers/claude-provider.tsapi/src/services/providers/mistral-provider.tsapi/src/services/providers/cohere-provider.tsllm-runtime/index.ts for dispatch changesmake test-api-ai ENV=test-$BRANCH