agentleFS
legibetlegibet/agent-skills/skills/write/SKILL.md

write

Skill0 starsChanged 26 days agoMITView on GitHub

Write and revise prose in Chinese or English. Use when drafting, revising or reviewing documents, READMEs, notes, papers, articles, code comments, UI copy, issues, PRs or messages.

35 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use read, hunt and 10 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.
  • MicrosoftSkill

    read

    Read pages from a document. Returns MinerU markdown (preferred) or PyPDF text, with optional page screenshots and sub-image fetching. When markdown is available, a figure_images_meta catalog is included — use the figures parameter to fetch specific sub-image pixels. Triggers include "read page 5", "what does page 12 say", "show me the chart on page 3", "extract pages 3-5".

    Also in 6 projects that use this

  • ninehillsSkill

    hunt

    Finds root cause before applying fixes for errors, crashes, regressions, failing tests, broken behavior, and screenshot-reported defects. Use when users report in any language errors, crashes, broken behavior, regressions, failing tests, screenshot evidence, or something that used to work and now fails. Not for code review or new features.

    Also in 4 projects that use this

  • vltingSkill

    think

    Lightweight plan-to-execution pipeline. Explores codebase, runs council deliberation, presents plan for approval, then executes via /run.

    Also in 7 projects that use this

  • genomewalkerSkill

    health

    Soul system health check with remediation

    Also in 5 projects that use this

  • AnthropicSkill

    analyze

    Answer data questions -- from quick lookups to full analyses. Use when looking up a single metric, investigating what's driving a trend or drop, comparing segments over time, or preparing a formal data report for stakeholders.

    Also in 6 projects that use this

  • anombyte93Skill

    discover

    Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a time), or self-brainstorms in Autonomous Mode when no user is present. Intercepts before the brainstorming chain hands off to writing-plans — this skill owns the exit. Extracts constraints, calibrates scale (Solo / Team / Enterprise), and advances the pipeline to GENERATE.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 31 edited versions we read keep these.

  • 2

    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
  1. Distinctive:

    When the text continues an existing document, read that document first and keep its voice, terms and conventions.

    line 19
  2. Distinctive:

    Keep the meaning when you edit.

    line 31

“Common” is measured: kept by at least 6 in 10 of the 31 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

Write

Good text says what its reader needs, in an order the reader can follow, in the language a competent author in the field would use.

Reader and content

Work out who will read the text, what they need to know or be able to do after reading it, and what order makes it easiest to follow. If you can't tell who the reader is or what the text is for, ask the user.

The material at hand (the conversation, the user's remarks, project documents, code, test logs, references, drafts from others) tells you what is true. Decide what to include, in what order and in what words according to what the reader needs. For example:

  • The user's remarks during a discussion are directions for the text. Use their key terms when those are the right terms, and turn their explanations, questions and stated intentions into what the text itself should say.
  • A session records work in the order it happened. Organize the text around what the reader wants to know, and leave out details that only mattered while the work was being done, such as the bug that prompted a setting or the options that were later dropped.
  • Different kinds of text serve different readers. A UI string tells users what they are looking at, a config comment explains the setting, and a README tells a newcomer what the project is and how to use it.
  • When the text continues an existing document, read that document first and keep its voice, terms and conventions.

Language

For Chinese text, read references/zh.md. For English text, read references/en.md. Each file describes problems that often appear in writing in that language, and its examples show typical forms of each problem. Keep text that reads naturally, even when it contains a listed phrase.

Revision

Revise for the same reader and genre as the draft. A fix to a sentence in a set of instructions should still read as a short instruction.

When you edit existing text, change what is wrong and keep what works. Edit in place, and keep each change as small as the problem. If one word is wrong, replace that word. If a sentence is muddled, rewrite that sentence. Regenerating a whole paragraph changes sentences nobody questioned and introduces new problems. Keep sentences the user has accepted, and when you revert a change, restore the original wording.

Keep the meaning when you edit. Conditions, numbers, inequalities and the strength of each claim should stay as they were, and the edit should not add claims that the source doesn't support.

When the user corrects something, the correction points at a specific problem. Work out what the problem is and why it fails the reader, then fix it where it occurs. Fix the same problem elsewhere only where it actually occurs. For example, if the user calls one parenthetical unnecessary, the problem is that parenthetical, and other parentheses can stay. Each fix should bring the sentence closer to what a competent author would write. When you expand a compressed sentence, restore the missing parts without adding padding. When you remove a hedge, keep the sentence complete.

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.