agentleFS
mikejhillmikejhill/agent-skills/skills/technical-writing/SKILL.md

technical-writing

Skill0 starsChanged 8 months agoMITView on GitHub

Write or review clear technical documentation, procedures, specifications, reports, and explanations in any format or location. Use beyond docs folders; project-documentation separately governs repository organization and metadata.

151 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

6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 143 edited versions we read keep these.

  • 6

    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:

    Put the key result, required action, or decisive constraint first.

    line 8
  2. Distinctive:

    Prefer numbered steps for procedures, bullets for parallel points, tables for comparisons or mappings, and diagrams for relationships, …

    line 12
  3. Distinctive:

    Use diagrams to answer a concrete question.

    line 15
  4. Distinctive:

    Use familiar words. Define necessary domain terms and abbreviations once.

    line 22
  5. Distinctive:

    Place a warning before the hazardous action.

    line 31
  6. Distinctive:

    Check commands and claims against available evidence.

    line 34

“Common” is measured: kept by at least 6 in 10 of the 143 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

Put the key result, required action, or decisive constraint first. Let a reader find what matters without reading every sentence.

Choose a useful form

  • Prefer numbered steps for procedures, bullets for parallel points, tables for comparisons or mappings, and diagrams for relationships, flows, or states.
  • Nest numbered steps when a parent operation has meaningful substeps. Avoid deep nesting that hides sequence or responsibility.
  • Minimize long prose paragraphs. Keep a short paragraph when it explains cause, rationale, or an exception better than fragmented bullets.
  • Use diagrams to answer a concrete question. Label entities and connections consistently; provide a concise text equivalent. Decorative imagery does not replace technical evidence.
  • Split documents into review-sized units with one coherent purpose. Start sections with their key point; avoid repeated summaries and boilerplate.

Write precise sentences

  • Apply ASD-STE100 principles: short sentences, simple grammar, active voice, imperative instructions, consistent technical names, and one intended meaning per term.
  • Give one action per procedural sentence unless actions must occur together. Put the condition before the action when it determines applicability.
  • Use familiar words. Define necessary domain terms and abbreviations once. Avoid idioms, metaphor, promotional claims, vague pronouns, and unnecessary noun chains.
  • Preserve needed articles, subjects, and qualifiers. Do not shorten text until its meaning changes or its uncertainty disappears.
  • Separate requirements, recommendations, observations, and examples. Identify who must act and what constitutes completion. State uncertainty and unsupported claims honestly.

These are selected STE principles, not a complete implementation of ASD-STE100. Its controlled vocabulary and writing rules require the applicable specification and validation for a formal compliance claim. Do not reproduce its dictionary/manual or label ordinary simplified writing as certified/compliant.

Make procedures executable

  1. State purpose, prerequisites, required permissions, and inputs before the first affected step.
  2. Place a warning before the hazardous action. State the hazard, consequence, and avoidance action; use notes for information rather than hidden commands.
  3. Give ordered actions with explicit conditions and concrete values or clearly named placeholders. Preserve exact commands, UI labels, units, and identifiers.
  4. State expected results at checkpoints. Include failure/stop conditions and recovery or escalation when needed.
  5. Check commands and claims against available evidence. Report validation limits; never invent successful execution or review.

For Markdown, use a single document title and logical heading levels, descriptive relative links within the repository, backtick code fences with language labels, and longer outer fences for nested examples. Follow existing lint configuration and verify rendering, links, and diagrams where relevant. A tooling exception belongs in the applicable profile, not a silent rewrite of shared guidance.

Authoritative STE sources

Consult the ASD Simplified Technical English Maintenance Group and its official FAQ when the task needs exact standard rules. The official site may restrict automated retrieval; disclose that limitation rather than substituting an unofficial copy as authoritative. ASD's public introductory extract, hosted by the University of Macerata explains controlled terminology; it is historical Issue 7 material, not proof of current compliance.

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.