メニュー
Use whenever creating, editing, renaming, or deleting any file under .claude/skills/, .claude/agents/, .agents/skills/, or .codex/agents/. Teaches the dual-tool Claude/Codex layout and reminds to run `make sync-agent-config`.
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
Interview the user, inspect this template repo, run the interactive onboarding CLI, and prune unused systems so a new Python project gets running quickly.
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear or thermonuclear code quality review, deep code-quality audit, or especially harsh maintainability review.
Instructions for managing and running git hooks using `prek`. Use this skill for any mention of pre-commit hooks, as `prek` overrides pre-commit hooks.
Pause execution for a requested number of minutes by sleeping one-minute increments to avoid exceeding shell timeouts.
Git branch hygiene - delete merged/closed branch, prune stale refs, sync dependencies
Instructions for running code quality checks and maintaining standards in the Python-Template project.
| name | manage-agent-config |
| description | Use whenever creating, editing, renaming, or deleting any file under .claude/skills/, .claude/agents/, .agents/skills/, or .codex/agents/. Teaches the dual-tool Claude/Codex layout and reminds to run `make sync-agent-config`. |
This repo is dual-tool. Before you create or edit anything under .claude/, .agents/, or .codex/, read this and the detailed rule at .claude/rules/codex-claude-sync.md.
Creating a new skill?
allowed-tools, $ARGUMENTS, !`shell` preprocessing, ${CLAUDE_SKILL_DIR})?
.claude/skills/<name>/SKILL.md (real directory, no symlink). Claude-only..agents/skills/<name>/SKILL.md. Shared; make sync-agent-config creates the .claude/skills/<name> symlink.Creating a new subagent?
.claude/agents/<name>.md (markdown + YAML frontmatter). That is the source of truth..codex/agents/<name>.toml is generated - never hand-edit.make sync-agent-config - the TOML appears.Renaming or deleting?
.agents/skills/ or .claude/agents/).make sync-agent-config - stale symlinks and orphaned TOMLs are pruned automatically..agents/skills/<name>/SKILL.md must only use:
name (required, lowercase-hyphens, ≤64 chars)description (required, ≤250 chars - Codex and Claude use this for implicit matching)Do not use any of these in a shared skill:
allowed-tools, disable-model-invocation, user-invocable, context, agent, model, effort, hooks, paths, shell, argument-hint$ARGUMENTS, $1…$N, ${CLAUDE_SKILL_DIR}, ${CLAUDE_SESSION_ID} substitutions!`cmd` or ```! shell preprocessing blocksAll of those are Claude-only. In Codex they pass through literally and confuse the model. If you need them, make the skill Claude-only (see decision tree above).
Claude .md frontmatter keys that don't exist in Codex (tools, model, color) are preserved as TOML comments in the generated .codex/agents/<name>.toml for human reference. They do not affect Codex behavior. If tool restrictions matter to the agent's job, describe them in the prose body so both tools read them.
Always run make sync-agent-config. The prek pre-commit hook will block the commit otherwise. The script is idempotent and silent when there's nothing to do.