メニュー
Capture repeated mistakes and workflow friction after meaningful work. Use when a task exposed recurring failures, confusing prompts, missing guardrails, or instructions that should be tightened for future Codex sessions.
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 for ADRs, architecture choices, technology selection, boundaries, and updates to `docs/ARCHITECTURE.md`. It keeps research ahead of prose and requires explicit approval before a decision is treated as merged.
Use this skill to discover workflows, map events, commands, read models, automations, and Given/When/Then scenarios before implementation. It keeps discovery separate from architecture and implementation decisions.
Review local changes before a trunk commit or push. Use when the user asks for review, a final preflight pass, or a regression check focused on correctness, risks, and missing tests.
Use this skill whenever the user wants test-first implementation. It runs a Codex-native RED -> DOMAIN -> GREEN -> DOMAIN -> COMMIT loop, with optional subagent delegation when explicitly useful.
Bootstrap a repository for Codex-first, trunk-based development. Use when the user asks to set up AGENTS.md, Codex workflow guidance, or repo-local SDLC defaults without centering Claude-specific conventions.
Keep Codex delegation explicit, sparse, and well-scoped. Use when the user asks for subagents, parallel work, or a multi-agent approach, or when a sidecar task is clearly parallelizable without changing the main workflow default.
| name | session-retrospective |
| description | Capture repeated mistakes and workflow friction after meaningful work. Use when a task exposed recurring failures, confusing prompts, missing guardrails, or instructions that should be tightened for future Codex sessions. |
Use this skill to tighten the workflow without turning every task into process work.
AGENTS.md