Menu
AIエージェント履歴を安全に集計し、再利用できる skills / agents / rules / scripts 候補だけを抽出する。履歴本文を公開せず、秘密情報を先に検出して抽象化したいときに使用。
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/nwiizo/dotfiles --skill home-history-distillThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Add config to this macOS dotfiles repo. Use for env vars, fish abbreviations/functions/plugins, direct symlinked config files, tool integrations, shared agent config, and app config such as Neovim, Ghostty, Warp, Git, Bat, Atuin, tealdeer, and gh.
Add a package to this macOS dotfiles repo. Use when the user asks to install, add, or migrate a CLI package or GUI app, for example "add jq", "ripgrep を入れて", "lazygit 入れたい", "brew install foo を repo 管理に", "kubectl 追加して". Homebrew owns binaries here; update Brewfile, validate with brew bundle, apply with brew bundle, and verify the executable.
実装前の計画・設計・意思決定を、1問ずつの徹底インタビューで叩いて固める。共有理解に達するまで実装しない。Invoke manually before non-trivial implementation when a plan or design already exists and needs stress-testing.
Based on SOC occupation classification
Showing SKILL.md
| name | home-history-distill |
| description | AIエージェント履歴を安全に集計し、再利用できる skills / agents / rules / scripts 候補だけを抽出する。履歴本文を公開せず、秘密情報を先に検出して抽象化したいときに使用。 |
Past prompts are useful raw material, but they are not publishable artifacts. Use this skill to turn local AI history into reusable dotfiles assets without leaking conversation content.
/tmp, not the repository:python3 .agents/skills/prompt-review/scripts/collect.py --days 0 > /tmp/dotfiles-prompt-review-data.json
secret_warningspython3 scripts/summarize-ai-history.py /tmp/dotfiles-prompt-review-data.json
If secret_warnings is non-empty:
Extract reusable patterns:
AGENTS.md or .agents/rules/Write only abstracted instructions. Do not include raw logs, credentials, private endpoints, account IDs, customer names, or personal paths.
Validate:
git secrets --scan
./scripts/audit-agent-config.sh
Report the data scope, high-frequency categories, created assets, skipped candidates, and any secret-warning remediation needed.