agentleFS
quochuydevquochuydev/kit/skills/fix-english/SKILL.md

fix-english

Skill0 starsChanged 8 months agoMITView on GitHub

Rewrite a sentence into correct, natural English and offer a few tone variations. Use when the user asks to fix grammar, correct a sentence, or invokes /fix-english.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    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
  1. Distinctive:

    Read the sentence the user provided.

    line 13
  2. Distinctive:

    If NO sentence was provided (empty argument), offer two options:

    line 14
  3. Distinctive:

    If there is no prior user message in the conversation, only show option 1.

    line 22
  4. Distinctive:

    If the intent is ambiguous, ASK one short clarifying question before rewriting.

    line 23
  5. Distinctive:

    Do NOT explain every grammar rule.

    line 25
  6. Distinctive:

    Keep rewrites roughly the same length unless the user asks for shorter/longer.

    line 41
  7. Distinctive:

    Use natural, native-sounding English, not overly formal textbook phrasing.

    line 42
  8. Distinctive:

    If the input is already correct, say so and offer 1–2 stylistic alternatives.

    line 43
  9. Distinctive:

    Never lecture on grammar unless the user asks why.

    line 44

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Fix English

Rewrite the user's sentence into clear, grammatically correct English and offer a small set of alternatives so they can pick the tone that fits.

Process

  1. Read the sentence the user provided.
  2. If NO sentence was provided (empty argument), offer two options:

    Which sentence should I fix?

    1. Paste the sentence you want me to fix.
    2. Fix the previous prompt: "{preview of the user's most recent prior message}"

    For the preview, if the prior message is longer than ~60 characters, show the first ~20 chars + ... + the last ~20 chars (e.g. "i see Server Requi... heading for it"). Otherwise show it in full.

    If there is no prior user message in the conversation, only show option 1. Then stop and wait for the user's reply. Do NOT invent an example sentence or guess.

  3. If the intent is ambiguous, ASK one short clarifying question before rewriting. Otherwise skip straight to the output.
  4. Produce one primary correction plus 2–3 short alternatives covering different tones (neutral, concise, formal/casual).
  5. Do NOT explain every grammar rule. Only call out a fix if it changes the meaning or the user seems to be learning.

Output Format

**Corrected:** {primary rewrite}

**Alternatives:**
- {alt 1 — different phrasing or tone}
- {alt 2 — shorter or more formal}
- {alt 3 — optional}

Rules

  • Preserve the user's original meaning — do not add new information.
  • Keep rewrites roughly the same length unless the user asks for shorter/longer.
  • Use natural, native-sounding English, not overly formal textbook phrasing.
  • If the input is already correct, say so and offer 1–2 stylistic alternatives.
  • Never lecture on grammar unless the user asks why.

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.