ワンクリックで
writing-clearly
Write concise, faithful prose — comments, docs, commit messages, and updates
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。
メニュー
Write concise, faithful prose — comments, docs, commit messages, and updates
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
Catch bad React in your changes — run react-doctor's deterministic scan and fix what it flags
Run a verifiable security scan (vulns, secrets, misconfig) over code you wrote or deps you added, before calling the work done
Drive a real browser verifiably — navigate, snapshot, act BY INDEX, extract; every step provable
Run multi-agent work as ONE provable causal DAG — parallel subagents, an Orchestrate graph, an immutable spec-seed
Author or connect a Model Context Protocol server so an agent gains new tools
Build automated pipelines that gate merges and ship reliably
| name | writing-clearly |
| description | Write concise, faithful prose — comments, docs, commit messages, and updates |
| version | 1 |
| trust | built-in |
Clear writing is a faithful, compressed model of the truth. Cut anything that doesn't change the reader's understanding.
General
Code comments 4. Comment the WHY, not the WHAT — well-named identifiers already say what. Add a comment only when the reason is non-obvious. Match the file's existing density.
Docs & messages 5. Match length to the reader's need: a commit subject is one line; a function doc is its contract (purpose, params, returns, failure); a status update is a sentence or two — what changed, what's next. 6. Show, don't tell: a short example beats a paragraph of description.
Red flags: marketing adjectives, restating code in English, walls of text where a list or example would do, hedging on things you've verified.