agentleFS
agentstationagentstation/skills/technical-writing/SKILL.md

technical-writing

Skill1 starsChanged 2 months agoMITView on GitHub

Use this skill before you write or edit developer-facing prose. Artifacts include a response, README, docstring, comment, error message, PR, issue, release notes, runbook, API text, prompt, tool description, technical web page, and agent message. Use it when a request asks to write, rewrite, tighten, shorten, or proofread technical text. Use it when a draft reads like generated filler or AI slop. Do not use it for marketing, fiction, or other voice-led prose.

142 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ketchup-video, principle-explain-the-number 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.
  • tristanphvnSkill

    ketchup-video

    Catch the user up like /keel:ketchup, with a short silent video of slides for what happened and the waiting calls as text under it. Use for /keel:ketchup-video.

    Also in 14 projects that use this

  • ianclearySkill

    principle-explain-the-number

    Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.

    Also in 29 projects that use this

  • eryzerzSkill

    make-bot-ui

    Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale.

    Also in 20 projects that use this

  • jaydubya818Skill

    principle-attack-the-premise

    Apply when repeated fixes fail and a shared assumption may be wrong.

    Also in 35 projects that use this

  • jaydubya818Skill

    principle-test-behavior-not-implementation

    Apply when tests mirror internals instead of asserting observable outcomes.

    Also in 36 projects that use this

  • ianclearySkill

    poteto-help

    Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.

    Also in 14 projects that use this

  • +5 more from jaydubya818

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 134 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use a controlled writing system instead of a vague request to "write clearly." The linter verifies mechanical rules.

    line 8
  2. Distinctive:

    Start with the answer. Use direct claims instead of assistant scaffolds, stock phrases, restricted vocabulary, invented contrasts, or …

    line 17
  3. Distinctive:

    Write dead prose. Dead prose carries the facts and no voice.

    line 21
  4. Very specific:

    Read CONFIG.md before a configuration change.

    line 30
  5. Very specific:

    Read references/asd-ste100.md before changing this skill's rules or making an ASD-STE100 conformance claim.

    line 40

“Common” is measured: kept by at least 6 in 10 of the 134 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

Technical writing

Use a controlled writing system instead of a vague request to "write clearly." The linter verifies mechanical rules. A human or agent must still verify facts, meaning, terminology, and audience fit.

Protect source content. Reproduce text exactly. During an edit, preserve every fact, unknown, value, identifier, and behavior. Keep conforming text unchanged unless the user requests another change. Support new claims with evidence and mark each inference or unknown.

Start with the answer. Use direct claims instead of assistant scaffolds, stock phrases, restricted vocabulary, invented contrasts, or decorative conclusions. Report each configured occurrence.

Write dead prose. Dead prose carries the facts and no voice. It has no rhythm, emphasis, or persuasion. Each sentence states a fact, an instruction, or a condition. Measure a draft by what the reader can verify, not by how the text sounds.

Workflow

  1. Identify the audience, artifact, and mode.
  2. Load the nearest .agents/technical-writing.toml and its GLOSSARY.md. Read CONFIG.md before a configuration change.
  3. For long-lived text without a glossary, read references/glossary.md.
  4. For a rewrite or edit, read references/rewrite.md before changing the source.
  5. Draft with references/rules.md. Read references/technical-artifacts.md when the artifact needs specific structure.
  6. Read references/formulaic-style.md when revising stock prose or changing a formulaic-style rule.
  7. Read references/asd-ste100.md before changing this skill's rules or making an ASD-STE100 conformance claim.
  8. Set the helper path:

    export TECHNICAL_WRITING="${AGENTS_HOME:-$HOME/.agents}/skills/technical-writing/scripts/technical-writing"
  9. For a file or substantive draft, run:

    "$TECHNICAL_WRITING" lint <path> --format text
  10. Revise until the linter exits with status 0.
  11. Complete the human checks in references/conformance.md.

For short technical conversation, apply the rules and final check without a tool call. For durable prose, run the linter until it passes.

Modes

  • developer: technical collaboration and developer-facing artifacts.
  • strict: procedures, runbooks, safety text, and tightly controlled error messages. Apply every configured limit and treat warnings as failures.

Project configuration can change a mechanical rule. Record the technical or terminology reason. Do not weaken factual or terminology checks.

Acceptance

A durable artifact or conformance claim passes only when:

  • The linter exits with status 0.
  • The text preserves protected content and approved terms.
  • A rewrite preserves precision or states why a rule cannot apply.
  • A reviewer completes the conformance checks.

The linter is not an ASD-STE100 certification tool. It checks the deterministic subset that this skill defines.

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.