メニュー
Chezmoi dotfiles conventions and patterns. Use when modifying dotfiles, adding new managed files, working with chezmoi templates, or syncing agent skills and subagents through agentspec.
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
Write or rewrite text in ASD-STE100 Simplified Technical English (STE): the approved-word dictionary discipline, controlled verb forms, sentence and paragraph limits, procedural vs descriptive rules, and safety-instruction structure. Use when the user asks for Simplified Technical English, STE, ASD-STE100, controlled language, or aerospace-style technical writing, or when authoring procedures, maintenance instructions, or safety warnings that must be unambiguous. Do NOT use for general documentation cleanup (use clean-docs), README structure (use write-readme), or ordinary prose style.
House doctrine for designing LLM agent systems: safety enforced by the harness and tools rather than model goodwill, tools that execute and return results, minimal loop code, interface-first component seams, typed config, deterministic evals over LLM judges, and POC scope discipline. Use when designing or reviewing any agent, tool-use loop, eval harness, or agent-backed CLI, in any framework. Do NOT use for Pydantic AI framework mechanics (use building-pydantic-ai-agents), generic design principles (use review-design), or Go agent-loop implementation details (use agent).
Operate the detect-secrets pre-commit hook correctly: update the baseline with the right flags, break the "baseline file was updated, please git add" commit loop, allowlist false positives, and audit real findings. Use when a commit fails on detect-secrets, the .secrets.baseline keeps changing, or a false positive blocks a push. Do NOT use for storing or injecting secrets via 1Password (use manage-secrets) or repo-wide leak scanning with gitleaks and trufflehog (use audit-security).
Run a project's own eval suite end to end without babysitting: locate the harness, launch it in the background, monitor to completion, parse the report into a normalized summary (pass rate, latency percentiles, tokens, cost), and diff against the previous run with per-case regressions explained. Use when asked to "run the evals", re-run after a change, or score a new dataset in any repo with an eval harness. Do NOT use for the GAP benchmark suite (use run-evals), SAIGE provider-boundary checks (use verify), or designing new eval sets (that is authoring work, not a run).
Playbook of known failure modes in this dotfiles stack: pipx "bad interpreter" after Python rebuilds, gpg commit-signing failures, direnv/nix shellHook running bash instead of zsh, Powerlevel10k instant-prompt warnings, and Neovim plugin errors from removed Lua APIs. Use when a shell startup error, git signing failure, broken CLI shim, or nvim stack trace appears on this machine. Do NOT use for generic runtime debugging in projects (use diagnose-runtime), chezmoi naming and templating conventions (use dotfiles), or authoring pinned installers (use setup-devenv-with-chezmoi).
Clean and modernize documentation in place. Enforce no em dashes, readable structure, proper Markdown formatting, accurate commands, current examples, resolved internal links, and user-focused guidance. Use when the user invokes /clean-docs, asks to clean docs, make docs up to date, improve README/AGENTS prose, remove AI-looking punctuation, or make docs easier for users to act on.
| name | dotfiles |
| description | Chezmoi dotfiles conventions and patterns. Use when modifying dotfiles, adding new managed files, working with chezmoi templates, or syncing agent skills and subagents through agentspec. |
| allowed-tools | Read, Grep, Glob, Bash(chezmoi *), Bash(agentspec *) |
Chezmoi is a general-purpose dotfile manager. This skill documents naming, templating, and agent-resource patterns that apply to any chezmoi-managed dotfiles repo. Substitute paths to your own chezmoi source directory wherever examples reference ~/.local/share/chezmoi.
dot_ prefix maps to .. Example: dot_zshrc becomes ~/.zshrc.private_ prefix sets restrictive permissions. Example: private_dot_ssh/..tmpl suffix indicates a chezmoi template using Go text/template.run_once_before_ and run_once_after_ scripts run once during chezmoi apply.run_onchange_ scripts re-run when their content changes.Templates use Go text/template with chezmoi data from ~/.config/chezmoi/chezmoi.toml:
{{ .chezmoi.os }}
{{ .chezmoi.hostname }}
{{ if eq .chezmoi.os "darwin" }}macOS-specific{{ end }}
Use {{ .chezmoi.os }} guards for platform-specific blocks.
Typical source paths inside a chezmoi repo:
| Source path | Target path | Purpose |
|---|---|---|
dot_config/ | ~/.config/ | App configs such as Neovim, Ghostty, Tmux, and direnv |
dot_zsh/ | ~/.zsh/ | Zsh functions and shell customizations |
dot_agents/ | ~/.agents/ | Cross-tool agent skills and subagents |
dot_agents/skills/ | ~/.agents/skills/ | Portable agent skills |
dot_agents/agents/ | ~/.agents/agents/ | Agent personas and subagents |
dot_codex/ | ~/.codex/ | Codex config, profiles, and agents |
dot_claude/ | ~/.claude/ | Claude Code config and project-scoped skills |
Brewfile.tmpl | generated Brewfile | Homebrew package source of truth |
run_onchange_after_install-*.sh.tmpl | chezmoi script | Pinned upstream installers |
chezmoi source-path to find it.chezmoi diff.chezmoi apply.chezmoi add <file>.dot_agents/agents/*.md and define how to think.dot_agents/skills/*/SKILL.md and define what to do.~/.agents/ and are linked into tools with agentspec.~/.agents/.Use agentspec for skills and agents:
agentspec manage add "$(chezmoi source-path)/dot_agents" --all-tools
agentspec manage validate dot_agents/skills/<name>/SKILL.md
agentspec manage validate dot_agents/agents/<name>.md
agentspec manage verify --accept --name <name>
agentspec sync --fast
agentspec status
After editing a local skill or agent:
chezmoi apply ~/.agents.agentspec manage add "$(chezmoi source-path)/dot_agents" --all-tools.agentspec manage verify --accept --name <name> for each changed local resource.agentspec sync --fast.~/.agents/skills/ or ~/.agents/agents/; chezmoi overwrites them.chezmoi source-path.dot_agents/skills/ but appears unmanaged, adopt it with agentspec manage add <name> --all-tools.private_ for sensitive configs. Do not manage SSH keys, API keys, or tokens in chezmoi.