メニュー
One-paragraph description of when to use this skill, what triggers it, and what it should NOT be used for.
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 this skill to validate repo health before starting work. It checks that required files, tools, and services are present and functional. Run at session start or after major structural changes.
Use this skill when debugging live runtime behavior in a multi-process or distributed system, especially IPC framing, socket registration, supervised process startup, routing/materialization, liveness, or request/response mismatches. Trigger when the user asks to watch a live stack, debug runtime integration issues, inspect process/socket state, or compare test behavior against real execution. This skill is general and should not assume a Rust-only stack.
HIGH PRIORITY. Use this skill when changing architecture or workflow docs so domain, frontmatter, status truth, proposal links, and task links stay aligned automatically. Trigger for edits in docs/architecture/, docs/README.md, or docs/task.md when the work changes current truth, near-future seams, proposal status, or documentation structure.
HIGH PRIORITY. Use this skill to keep architecture and process proposals concise, current, and linked to active tasks. A proposal is not a static doc; it is an active plan. Trigger for disposition updates, task alignment, or removing stale certainty. Pair this with architecture-docs-maintainer when metadata, domains, or source-of-truth linkage also need upkeep.
HIGH PRIORITY. Use this skill at the START of EVERY session to retrieve project context and during the session to store decisions. It is the mandatory bootstrap mechanism for continuity and the engine for project optimization. Retrieve before meaningful work, write back important decisions, and use revealed gaps to improve repo-local protocols.
Use this skill when deciding how deeply to validate a change or when explaining confidence in a code change. Trigger for test planning, selecting the right validation rung, or classifying confidence as test-green, smoke-green, or watched-live-green. Do not use this skill for runtime root-cause investigation or slice close-out unless validation choice is the main task.
| name | your-skill-name |
| description | One-paragraph description of when to use this skill, what triggers it, and what it should NOT be used for. |
Scope: General | Project-specific.
Use this skill when the main question is: [describe the decision or task this skill addresses].
Use [other-skill](../other-skill/SKILL.md) when [describe handoff condition].
[Describe when to escalate, when to skip steps, or how to choose between paths.]
Report:
