メニュー
Use when writing prose humans will read—documentation, commit messages, error messages, reports, UI text—or when the user wants existing text to sound human rather than AI-written ("humanize this", "reads like ChatGPT").
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。
Build, launch, and drive the mindwalk web UI end-to-end for verification.
Set up or troubleshoot Yassimba's curated agent skills, Pi packages, Herdr, and Herdr plugins through the ai-setup CLI. Use when the user asks to install this collection, configure Herdr, add one of its capabilities, update the setup, or diagnose installation problems.
Backlog management: use when the user mentions a backlog, asks what's next, wants work recorded before implementation, or wants queued ideas or specs prioritized, transitioned, completed, or removed; also use when another skill needs to record lifecycle changes.
Use when the user wants to brainstorm or explore an idea — a feature, product direction, or "what if" — before deciding whether it deserves a plan. Ideation only — ends in an idea brief, not a design.
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (this repo's documented coding standards) and Spec (what the originating issue/PRD asked for). Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
Use when creating a git commit — the user asks to commit, or a unit of work is complete and ready to commit.
SOC 職業分類に基づく
| name | writing-clearly-and-concisely |
| description | Use when writing prose humans will read—documentation, commit messages, error messages, reports, UI text—or when the user wants existing text to sound human rather than AI-written ("humanize this", "reads like ChatGPT"). |
Write vigorous prose. Vigorous writing is concise: every word tells, sentences are active and concrete, needless words are gone. This skill pairs Strunk's The Elements of Style with a field guide to AI writing patterns.
Strunk's Elementary Principles of Composition — apply these to everything you write:
Pick the row that matches the task and load exactly one file — the full pass below is the only exception:
| Task | Load |
|---|---|
| Writing or editing paragraphs, docs, explanations | references/elements-of-style/03-elementary-principles-of-composition.md |
| Fixing grammar, commas, punctuation in existing text | references/elements-of-style/02-elementary-rules-of-usage.md |
| Choosing the right word, fixing common misuses | references/elements-of-style/05-words-and-expressions-commonly-misused.md |
| Headings, quotations, formatting | references/elements-of-style/04-a-few-matters-of-form.md |
| Making text sound human ("humanize", "reads like ChatGPT") | references/humanizer.md |
| Auditing whether text is AI-written (deep pattern catalogue) | references/signs-of-ai-writing.md |
Load the bundle — 02, 03, 04, 05, references/humanizer.md, and references/ai-patterns.md — when, and only when, the user explicitly signals a comprehensive job:
"Fix this paragraph" or "tighten this sentence" stays with the single-file default.
LLMs regress to statistical means, producing generic, puffy prose. Say what the thing actually does, in the words a knowledgeable human would pick. Guardrails:
When these bullets aren't enough, load references/ai-patterns.md — the distilled field guide with words-to-watch per pattern. Reserve references/signs-of-ai-writing.md (the full Wikipedia catalogue with examples) for explicit "is this AI-written?" audits.
A writing or editing pass is finished when a re-read of the full output finds:
If the re-read finds a violation, fix it and re-read again.
