agentleFS
michele-orsini-71michele-orsini-71/claude-skills/proofread/SKILL.md

proofread

Skill0 starsChanged 6 months agoMITView on GitHub

Review a written text for grammar errors, syntax errors and non-idiomatic English, and list minimal corrections without rewriting the text. The author's style, tone, word choice and structure are preserved; only real errors and expressions a native speaker would not use are flagged. Built for a non-native English speaker. Use when the user invokes /proofread, or says "check my English", "fix grammar", "is this idiomatic", "proofread this", or pastes a text and asks for language corrections.

28 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use humanize, deploy and 2 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • eherrerosjSkill

    humanize

    Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive 'Signs of AI writing' guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases. Triggers on: 'humanize', 'make this sound human', 'remove AI writing', 'de-AI', 'sound more natural', 'less robotic', 'too AI-sounding', or when reviewing text that reads like AI output.

    Also in 3 projects that use this

  • VercelSkill

    deploy

    Deploy applications to Vercel. Use when the user says "deploy", "deploy to Vercel", "push to production", "deploy my app", or "go live".

    Also in 3 projects that use this

  • Microsoft AzureSkill

    verify

    End-to-end app testing pipeline for browser-based web apps on cloud browsers via Azure Playwright Workspaces: verify the live app, author tests for working flows, heal failing tests, then re-run with video and produce one consolidated report. Three phases (app verification, test authoring, test healing) plus a scoped final sanity run; each phase emits a sub-report. Use when asked to "verify my app", "make sure my app works and has good test coverage", "do a full QA pass", "add tests where I'm missing coverage", "fix failing tests and add new ones", "smoke test before deploy", "QA my deployment", or any combined verify-and-test ask. Requires Azure CLI (`az login`) and a Playwright Workspace resource ID — bootstraps configs on first invocation. Browser-based web apps with Playwright only — not for unit/API tests, native mobile/desktop, load/perf, or full accessibility audits.

    Also in 3 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 9 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 21 edited versions we read keep these.

  • 9

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Spelling and punctuation: only when wrong, not when it is a matter of taste.

    line 17
  2. Distinctive:

    Do not rewrite sentences that are correct, even if you would write them differently.

    line 21
  3. Distinctive:

    Do not change tone, register, sentence length or paragraph structure.

    line 22
  4. Distinctive:

    Do not replace plain words with fancier ones, or the reverse.

    line 23
  5. Distinctive:

    Do not touch code, identifiers, product names or technical terms.

    line 24
  6. Distinctive:

    Do not merge or split sentences unless the original is grammatically broken.

    line 25
  7. Distinctive:

    When unsure whether something is an error or a style choice, leave it.

    line 26
  8. Distinctive:

    Do not output the full corrected text.

    line 39
  9. Distinctive:

    Do not edit files unless the user asks explicitly.

    line 41

“Common” is measured: kept by at least 6 in 10 of the 21 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

The author is a non-native English speaker. They want to fix mistakes, not to get a new text. Their voice is theirs. Your job is to find errors, not to improve the style.

Input

The text is pasted in the message, or given as a file path. If neither is present, ask for it in one sentence and stop.

What to flag

  1. Grammar: agreement, tenses, articles (a/an/the), prepositions, plurals, word order.
  2. Syntax: broken or ambiguous sentence structure, dangling modifiers, missing words.
  3. Idiom: expressions that are correct but that a native speaker would not use. Examples are word-for-word translations, wrong collocations ("make a question" instead of "ask a question") and false friends.
  4. Spelling and punctuation: only when wrong, not when it is a matter of taste.

What NOT to change

  • Do not rewrite sentences that are correct, even if you would write them differently.
  • Do not change tone, register, sentence length or paragraph structure.
  • Do not replace plain words with fancier ones, or the reverse.
  • Do not touch code, identifiers, product names or technical terms.
  • Do not merge or split sentences unless the original is grammatically broken.
  • When unsure whether something is an error or a style choice, leave it. Or flag it as "optional".

The test: a correction must be justified by a rule or by native usage, never by preference.

Output

One entry per issue, in text order:

"original fragment" → "corrected fragment" category — one-line reason.

Quote the smallest fragment that makes the change clear, not the whole sentence. Put "optional" suggestions last, in a separate group. If there are no errors, say so in one sentence.

Do not output the full corrected text. Output it only if the user asks (for example "apply", "give me the full text"). Then apply only the listed corrections and nothing else.

Do not edit files unless the user asks explicitly.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.