Refine Prose
Refine prose so it says what the writer means to a specific reader: cut the text that should not exist, put the point first, state things literally, remove the patterns that mark machine writing, and match the voice. Use when drafting, revising, tightening, editing, proofreading, or reviewing prose: essays, posts, emails, PR descriptions, docs, plans, reports, comments, commit messages, UI strings. Also use for requests like "clean this up", "make it read better", "tighten this", "does this sound like AI", "de-slop", or "humanize". Not for code.
Install
npx skills add petekp/claude-code-setup --skill refine-prosegit clone --depth 1 https://github.com/petekp/claude-code-setup.git /tmp/claude-code-setup
mkdir -p ~/.claude/skills
cp -r /tmp/claude-code-setup/skills/refine-prose ~/.claude/skills/refine-prosePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Refine prose Work from the reader's side. Ask what this reader needs in order to understand or decide, then remove everything that does not serve that. Most weak prose fails above the word level. It says things the reader did not need, in an order that hides the point, in phrasing chosen to sound like writing rather than to say something. Fix those in that order. Word-level tells come last and matter least. One move covers most fixes: describe what is present, in literal words, with the person who did it named. ## Before editing Settle three things from the request or the text itself: - **The reader and what they will do with the text.** A busy engineer deciding whether to merge reads differently from a friend receiving a reply. - **Whose voice it is in.** Pete's own message or post: read `~/.claude/skills/write-as-pete/VOICE.md` and apply it after the passes below. Interface strings: read `~/.claude/skills/clean-copy/SKILL.md` for what survives on a screen and how to report a batch. Anything else: the default register under Voice. - **The mode.** Rewrite returns revised text. Review reports findings and changes nothing. Draft writes new text, then applies the passes to it. Ask only when the answer would change the edit materially. Otherwise choose the reading a careful editor would choose and say so in one line. ## Pass 1: Cut what should not exist Walk each section, paragraph, and sentence down these questions. Delete at
Details
- Skill name
refine-prose- Repository
- petekp/claude-code-setup
- Path
skills/refine-prose/SKILL.md- License
- MIT
- Repo updated
- 26 October 2026
FAQ
What does the Refine Prose skill do?
Refine prose so it says what the writer means to a specific reader: cut the text that should not exist, put the point first, state things literally, remove the patterns that mark machine writing, and match the voice. Use when drafting, revising, tightening, editing, proofreading, or reviewing prose: essays, posts, emails, PR descriptions, docs, plans, reports, comments, commit messages, UI strings. Also use for requests like "clean this up", "make it read better", "tighten this", "does this sound like AI", "de-slop", or "humanize". Not for code.
How do I install the Refine Prose skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add petekp/claude-code-setup --skill refine-prose. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Refine Prose popular?
It lives in petekp/claude-code-setup, which has 49 GitHub stars and 10 forks.
Related skills
Catch Up
49petekp/claude-code-setup
Give the human a fast, plain-English catch-up on what changed in the project: what the agents did, why, and what decisions need their input. Use when the user asks to "catch me up", "what changed", "where are we", "recap", "brief me", "give me the rundown", "what did you do", "summarize the session", or "fill me in", or otherwise wants to get back up to speed after being away.
Clean Copy
49petekp/claude-code-setup
Cut interface copy that should not exist. Captions that restate a label, hints that pre-empt a worry the user never had, warnings that are scar tissue from a fixed bug. Use when writing or reviewing any user-facing string (labels, hints, empty states, toasts, confirmations, button text), or when asked to clean up or tighten copy.
Code Comments
49petekp/claude-code-setup
Write, review, or remove code comments. Use when adding comments or doc comments, reviewing the comments in a diff, or cleaning up or removing comments.
Neovim Rpc
49sodiumjoe/dotfiles
Interact with a running neovim instance over RPC — open files, show diffs, execute Lua. Use when you need to open a file in the user's editor, show a vimdiff, or run arbitrary Lua in neovim. Requires $NVIM or $NVIM_SOCKET_PATH to be set.
Postready
43analystacademy/claude-skills
Run the full publish-ready pipeline on source content — generate LinkedIn posts, fact-check them, tighten them, and HR-screen them — all in one shot, end-to-end. Trigger this skill whenever the user types /postready, says "make this publish-ready", "run the full pipeline", "give me final posts from this", or shares source material (PDF, email, newsletter, URL, pasted text) and signals they want finished, ready-to-publish posts rather than rough drafts.
Uw Unity Editor Tools
47devdavv/unity-ai-workflow
Generate custom editor tooling including Custom Inspectors, PropertyDrawers, EditorWindows, Gizmos, and Handles. Use when building designer-facing tools, spatial visualization, batch operations, or custom component UIs. Triggers on requests like "create a custom inspector", "add gizmos", "build an editor window", "make this component designer-friendly", "add a debug visualization", "create a level editor tool", "add a property drawer", "make a batch rename tool", or any editor tooling work. Always uses SerializedProperty and Undo for safety.
Browse the most popular Claude skills, all writing & content skills, or write your own with the skills generator.