agentleFS
TianMingKanaeTianMingKanae/engineering-multi-ai-skills/skills/technical-writing/SKILL.md

technical-writing

Skill6 starsChanged 19 days agoMITView on GitHub

Plan, draft and revise evidence-backed technical English, including paper sections, abstracts, captions, theses, reports and reviewer responses. Use for manuscript structure, clarity or a style pass; not for generating unverified results or changing publication criteria.

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

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

  • 0

    Common

    Most of the 134 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:

    Write for the actual reader and purpose.

    line 8
  2. Distinctive:

    Keep result, inference and recommendation distinct.

    line 42

“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

Write for the actual reader and purpose. Plan the argument, draft it, then revise evidence, structure and language in separate passes. Preserve technical meaning while making the prose easier to follow. Prefer honest, accurate, complete, accessible, concise and diplomatic writing over impressive wording.

These notes adapt the planning and revision approach of Mike Markel, Writing in the Technical Fields: A Step-by-Step Guide for Engineers, Scientists, and Technicians, IEEE Press / Wiley, 1994. The guides are condensed, rewritten guidance with synthetic examples, not book excerpts or a substitute for the book. No book PDF or private project context is bundled or required. Manuscript-specific practices below are toolkit adaptations; the target publication's current author instructions and the user's authorized scope take precedence.

Workflow

  1. Identify the audience, document type, requested action and publication/house style. State the purpose in one sentence. Use an existing approved outline when available; do not introduce an approval pause for routine assigned drafting. Resolve a genuinely consequential scope ambiguity before investing in a long draft.
  2. Map each proposed claim to its evidence and conditions. Use the project's accepted evidence register when available, or explicit source/results references. Keep missing evidence as an unresolved item in working notes; do not invent a citation, number, significance test or completed experiment.
  3. Outline in the order of the reader's questions. Separate the problem, method, observations, interpretation and limitations. Draft without optimizing every sentence. For planning details, read process.md.
  4. Revise factual accuracy and scope before organization, paragraphs, sentences, words, graphics and mechanics. Use checklists.md. A shorter sentence that changes a condition or a technical term is not an improvement.
  5. Reopen the revised artifact, verify references/values/notation and the requested change. Follow the project's existing section ownership and review/publication workflow. A style pass never constitutes independent technical verification or permission to submit or send a document.

Load only the needed reference

  • Paper outline, abstract, introduction, results or conclusion: structure.md.
  • Paragraph flow, voice, emphasis and word choice: paragraphs-sentences-words.md.
  • Captions, plots, tables or publication layout: graphics-design.md.
  • Punctuation, units, notation and confused words: handbook.md.
  • Articles, tense, agreement or writing for multilingual readers: esl.md.
  • Reviewer response, cover letter, technical email, proposal or progress report: other-documents.md.

Optional read-only style scan

python scripts/style_check.py draft.tex
python scripts/style_check.py draft.md --only wordy,passive,acronym

Paths above are relative to this skill directory. The checker flags phrases with line numbers; it never edits a file and exits zero when a scan succeeds, including when it finds suggestions. Invalid arguments or unreadable input return a nonzero exit. Use --help for categories. Flags are prompts to reread, not errors or publication acceptance criteria. Passive voice, specialist vocabulary and long sentences can be appropriate. Read the complete sentence before changing it.

This is a lexical heuristic, not a grammar checker, citation validator, statistical test or full Markdown/LaTeX parser. It skips common displayed math and bibliography blocks in TeX; complex macros, inline definitions and formatting can still produce false positives or omissions. Verify captions in the rendered manuscript as well. Meaning, evidence and house style decide whether a suggestion is useful.

Evidence and collaboration boundaries

Keep result, inference and recommendation distinct. Report the comparison, sample/workload, uncertainty and limitations actually supported; do not generalize from a narrow test. State practical magnitude when known and distinguish it from statistical significance. Missing journals or failed cases cannot be hidden by fluent prose.

Keep internal task routing, private paths and audit bookkeeping out of reader-facing prose. Retain limitations, unfavorable findings and reproducibility information needed to judge the work; put supplementary detail in appropriately referenced appendices or supporting material. Do not move a material qualification out of view merely to improve style. Preserve coauthor ownership and make proposed edits through the existing authorized workflow. When reviewer responses promise a revision or experiment, verify it exists before claiming completion.

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.