Skip to content

backnotprop/pstack / skills/technical-writing

technical-writing

Verified

Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.

Technical writing

Write so a tired engineer understands on the first read.

  • Cut every word that does no work.
  • Use the short, everyday word: "use", not "utilize".
  • When a rule makes a sentence worse, fix the sentence another way or leave it alone.
  • Write the real symbol, file, flag, or command name, not a synonym or a description of it.
  • Don't invent jargon. Use the words a developer would say out loud. Say what a named pattern means the first time.

Vary the rhythm

  • Mix sentence lengths. Split the sentence that carries two thoughts. Keep the long sentence that carries one.
  • Have a view in explanation. Keep reference dry.
  • Be specific. Not "schema changes can cause issues" but "a column rename fails the build".

Pick the mode first (Diátaxis)

One document, one mode. Don't mix modes. Split and link instead.

  • Tutorial: learning by doing. Say what the learner will build. Every step produces a visible result, and you say what they should see. Explanation gets one clause and a link.
  • How-to: steps to a goal. Solve the reader's problem. Assume competence. Action only. Allow forks. Name the guide by the task.
  • Reference: facts for lookup. Only describe. Be dry, complete, and sure. Mirror the structure of the thing described.
  • Explanation: understanding and why. One bounded topic. Give context: design decisions, history, constraints, alternatives. Opinion is allowed here and nowhere else.

Write sentences to the reader (Google developer style)

  • Talk to the reader as "you", in the present tense.
  • Say who does what. Passive is fine only when the actor is unknown or beside the point.
  • Write instructions as commands. Put the condition before the instruction and the common case first.
  • No buzzwords, no figurative language, no "please", and never "simply", "easy", or "quickly" in a procedure.
  • Don't pre-announce, and don't start consecutive sentences with the same phrase.
  • Link with words that say where the link goes.
  • Headings carry the point, in sentence case. One h1 per page, no skipped levels.
  • Numbered lists for sequences, bullets for everything else. Introduce a list with a complete sentence. Keep items parallel.
  • Code goes in code font. UI elements go in bold. Use serial commas. Drop "etc.".

Make statements load one at a time (STE rules)

  • One instruction per sentence. One thought per sentence everywhere else.
  • Split instructions longer than about 20 words and other sentences longer than about 25.
  • Put the warning or condition before the step it guards.
  • Keep "the" and "a".
  • Give each word one meaning, and pick one word per action.
  • Write procedures as direct commands, never as narration and never in the passive.
  • Avoid "-ing" words where you can.

Leave no sentence open to two readings (Global English)

  • Keep words like "only" and "not" next to the word they change.
  • Break up long noun strings.
  • Make every "it", "they", and "this" point at one obvious thing. Never use "this" or "which" to point at a whole clause.
  • Don't drop verbs, or the small words that show structure, such as "that".
  • Repeat the article in a series when it prevents a misread. Say which parts "and" or "or" joins.
  • Use periods, not semicolons or em dashes. No slashes, and no "(s)". Make text in parentheses a full grammatical unit.
  • Call each thing by one name, everywhere.
  • Skip idioms, colloquialisms, Latin abbreviations, and metaphors.

Voice and repo specifics

  • Apply the unslop skill to every doc this skill touches. That skill owns the slop-pattern catalog: AI vocabulary, filler, hedging, formatting tells.
  • PR descriptions and commit messages are writing too. Every layer except Diátaxis applies to them. A PR body is a briefing that a reviewer can read in under a minute. Do not paste swarm logs, SHA lists, or metric tables. Link them.
  • Product UI strings are not documentation. Use your product's copy guidelines for those.
  • Indent code snippets with tabs. Write real paths. Make every count or tree claim true at the commit that lands it, and include the command that regenerates it.
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 466kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 196kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 196kUpdated Claude CodeCodexVerifiedInstall