mizchi-blog-style
mizchi Blog Style
mizchi 個人ブログ向けの文体評価 skill。記事を書いた後、subagent に「mizchi 文体度」と「AI 臭度」を判定させて反復改善する。
詳細な文体プロファイル (5 種類の特徴的フレーズ集 + 過去記事 23 本の構成分析) は ~/ghq/github.com/mizchi/zenn/CLAUDE.md (644 行) を参照。本 skill はその要点抜粋 + AI 臭判定基準 + 評価ワークフローに集中する。
いつ使うか
- zenn / dev.to / 個人 blog の記事ドラフトを書いた直後
- AI に下書きさせた記事を mizchi 文体に寄せたいとき
- 「AI 臭い」と感じるが具体的にどこかが言語化できないとき
使わない場面:
- 業務文書 / OSS の README (公的に英語、技術リファレンス調)
- ペアプロのチャット応答 (リアルタイム会話)
mizchi 文体の核 (5 軸)
詳細は zenn/CLAUDE.md にあるが、レビュー時のチェック観点はこの 5 軸に集約できる:
More from mizchi/skills
empirical-prompt-tuning
Methodology for iteratively improving agent-facing instructions (skills / slash commands / CLAUDE.md / code-gen prompts) via bias-free executor + two-sided evaluation (self-report + instruction-side metrics). Meta-skill, invoke ONLY when the user explicitly asks for an "empirical" eval of a prompt or skill, or for the Iter-0 description / body consistency check. Do NOT auto-invoke after every skill edit; this loop is operator-triggered by name.
62retrospective-codify
Pair "what failed first" with "what finally worked" and codify the should-have-known-it insight as an ast-grep rule, a skill, or a CLAUDE.md rule. Meta-skill: invoke ONLY when the user explicitly says "codify today''s lessons," "make it a skill," "drop it into lint," or asks to extract a reusable rule from a trial-and-error fix. Do NOT auto-invoke at every task completion. Spares future-you (or another agent) the same trap.
17gh-fix-ci
Debug or fix failing GitHub PR checks running in GitHub Actions. Inspects checks/logs via `gh`, drafts a fix plan, and implements only after explicit approval. Out of scope: external CI (e.g. Buildkite) — report only the details URL.
17tech-article-reproducibility
Evaluate the reproducibility of technical articles. Dispatch a subagent to simulate a first-time reader reproducing the work locally and list missing information. Use as the final check on a draft before publication.
15playwright-cli
Use when running Playwright via terminal CLI — `npx playwright test` (test runner), `codegen` (interactive recording), `screenshot` / `pdf` (one-off captures), and CI sharding. NOT for agent-driven real-time browser control (use `claude-in-chrome` MCP tools for that).
14conventional-changelog
Reference for Conventional Commits and automatic CHANGELOG generation. Compares release-please / changesets / git-cliff / towncrier and covers commit format, Keep a Changelog, and semver tag practices. Use when setting up or unifying a release flow.
13