Skip to content
  1. Skills at a glance
  2. Build and clean up
  3. /pstack:technical-writing

/pstack:technical-writing

Auto

In one lineWrites docs to a clear standard, editing line by line until a tired engineer gets it in one read.

When to use
Writing docs, RFCs, READMEs, PR descriptions or commit messages.
Install with
unslop
Say it like this
/pstack:technical-writing Review the README changes

Just asking vs. using it

The same request, typed plainly or with /pstack:technical-writing. Here's what changes.

Just askingWith /pstack:technical-writing
Writes steps with "simply", "easy" or "should be done".Writes each step as a direct command, with the condition first.
Clips every sentence to one length, so it reads machine-written.Mixes short and long sentences and takes a view in explanations.
Pastes logs and SHA lists into the PR body.Writes the PR body as a one-minute briefing and links the logs.

What the document says

7 sections, about 1500 words, 7 min to read. Click a section to read it.

OpeningIt sets three rules above the four layers, then requires real code names and no invented jargon.

  1. 1Vary the rhythmMixes short and long sentences, takes a view in explanations, and writes specifics like "a column rename fails the build".
  2. 2Pick the mode first (Diátaxis)Tutorials show a visible result each step, how-tos give only actions, reference only describes, and opinion lives in explanations.
  3. 3Write sentences to the reader (Google developer style)Addresses "you" in present tense, writes commands, puts conditions first, makes headings carry the point, and labels links clearly.
  4. 4Make statements load one at a time (STE rules)One instruction per sentence, a split past about 20 words, warnings before the step, and one word per action.
  5. 5Leave no sentence open to two readings (Global English)Keeps "only" and "not" beside their word, breaks up noun strings, gives each "it" one referent, and drops semicolons and slashes.
  6. 6Voice and repo specificsRuns unslop on every touched doc, applies the rules to PRs and commits, and leaves UI strings to product copy guidelines.
  7. 7Worked exampleRewrites a tangled paragraph about budget.json into three sentences: what reads what, when CI fails, and when to use --write.

See the wording worth borrowingRead the full text

Wording worth borrowing

A few sentences from the original: what each one makes the AI do, why it works, and how you can borrow it.

  1. Write for one concrete reader

    Write so a tired engineer understands on the first read.

    Makes the AI
    The doc reads clearly the first time, with no need to go back.
    Why it works
    "A tired engineer" on "the first read" is a picture you can imagine, far easier to aim at than "be clear".
    Borrow it
    For a notice people must follow, say: "Write it so a support rep finishing a night shift can act on it after one read."
  2. Make long words earn their place

    A long word has to buy its length with precision.

    Makes the AI
    It uses short everyday words by default, and a long word only when a short one is not exact.
    Why it works
    It doesn't ban long words outright. It gives a test: the long word has to buy more precision.
    Borrow it
    To control jargon, write: "Technical terms are fine, but each must be more exact than the plain word, or swap it."
  3. Give the rules a way out

    When a rule makes a sentence worse, fix the sentence another way or leave it alone.

    Makes the AI
    It won't twist a sentence into something worse just to obey a rule.
    Why it works
    Saying the rules serve readability, not the other way round, stops the AI from applying them mechanically.
    Borrow it
    After a list of style rules, add: "If a rule makes a sentence harder to read, skip it. Readability wins."
  4. Name one source for words

    The codebase is the word list.

    Makes the AI
    The doc uses the real function, file, and command names, not friendlier aliases.
    Why it works
    Pointing "which word to use" at a source that already exists stops the AI from inventing names.
    Borrow it
    For a user guide, add: "Write every button name exactly as it appears in the app."
  5. Sort with two questions

    Two questions pick it: does the content inform action (doing) or understanding (thinking), and does it serve learning or work?

    Makes the AI
    Before writing, it decides whether the doc is a tutorial, how-to, reference, or explanation, and writes only one.
    Why it works
    Two either-or questions make four boxes, so the AI sorts by answering them instead of by feel.
    Borrow it
    Have the AI sort before it writes: "First decide: does the reader want to act now or understand, and are they new or experienced?"

Full text

The SKILL.md the AI reads, as written.

descriptionLayered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /pstack: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. Apply all four layers.

Three rules sit above the layers:

  • Cut every word that does no work. If the sentence survives without a word, the word goes. "In order to" is "to". "It is important to note that" is nothing.
  • Use the short, everyday word. "Use", not "utilize". "Help", not "facilitate". "Do", not "perform". A long word has to buy its length with precision.
  • When a rule makes a sentence worse, fix the sentence another way or leave it alone. A sentence that follows every rule and sounds like a machine wrote it has failed.

The codebase is the word list. 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: "move", "delete", "a budget that only decreases", not "evacuate", "ratchet", or "endgame". A named pattern is fine when the doc says what it means the first time. Propose a new offender and its replacement as an addition to unslop's abstract-metaphor rule in your reply, with the diff. Don't edit that skill.

Vary the rhythm

A doc can obey every layer and still read machine-written: every sentence clipped short, no view anywhere, nothing specific.

  • Mix sentence lengths on purpose. Short sentences land a point. Longer ones carry a fact with its condition or consequence.
  • One thought per sentence does not mean one length per sentence. Split the sentence that carries two thoughts. Keep the long sentence that carries one.
  • Have a view where the mode allows it. Explanation weighs trade-offs, so say what you make of them instead of listing pros and cons. Reference stays dry.
  • Be specific over sterile. Not "schema changes can cause issues" but "a column rename fails the build".

Pick the mode first (Diátaxis)

One document, one mode. Two questions pick it: does the content inform action (doing) or understanding (thinking), and does it serve learning or work?

  • Action + learning: tutorial.
  • Action + work: how-to.
  • Understanding + work: reference.
  • Understanding + learning: explanation.

Use the compass on a whole document or on one sentence.

Tutorial: learning by doing. The learner's success is your job, not theirs. Open by saying what the learner will build, not what they will "learn". Every step produces a visible result, early and often. Tell them what they should see: the expected output, the prompt change, the log line. Cut explanation to one clause and a link. Stay concrete. Write as "we", in commands: "First, do x. Now, do y."

How-to: steps to a goal. Solve a problem a person has, not an operation the machine can perform. Assume competence and skip teaching. Action only: no digressions, no background, no completeness for its own sake. Link those instead. Allow forks and judgment: "If you want x, do y." Name the guide by the task: "How to calibrate the radar array", not "Radar array calibration".

Reference: facts for lookup. Only describe. No instruction, no persuasion, no opinion. Be dry, complete, and sure. State facts, options, limits, and errors with no hedging. Mirror the structure of the thing described, so code and docs can be navigated together. Put material where readers expect it. Generate from code where possible.

Explanation: understanding and why. One bounded topic, readable away from the product. Each title should tolerate an implicit "About..." in front. Anchor on a real why question. Give context: design decisions, history, constraints, alternatives. Opinion is allowed here and nowhere else.

Don't mix modes: no reference tables inside a tutorial, no tutorial hand-holding inside reference, no arguing inside a how-to. Split and link instead.

Write sentences to the reader (Google developer style)

  • Talk to the reader as "you", in the present tense. "Will" only for things that genuinely happen later.
  • Say who does what: "the compiler checks", not "is checked". Passive is fine only when the actor is unknown or beside the point.
  • Write instructions as commands: "Click Submit." State facts plainly. Never "should be done".
  • Put the condition before the instruction: "To delete the document, click Delete."
  • Put the common case first. Exceptions after.
  • Sound like a knowledgeable friend. No buzzwords, no figurative language, no "please" in instructions, and never "simply", "easy", or "quickly" in a procedure. If it were simple, the reader would not be here.
  • Don't pre-announce ("we will soon support...") and don't start consecutive sentences with the same phrase.
  • Link with words that say where the link goes: the page title or a short description. Never "click here". Prefer a sentence of context on the page over a link off it.
  • Headings carry the point, not just the topic ("Pick the mode first", not "Modes"). Sentence case. A task heading is a bare verb phrase ("Create an instance"). A concept heading is a noun phrase. 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." and say up front that a list is partial.

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: "If hot oil touches your skin, injuries can occur."
  • Keep "the" and "a": "Remove backup file" reads two ways. "Remove the backup file" reads one.
  • Give each word one meaning and one job, then keep it. If "check" means inspect, don't also use it for restrain.
  • Pick one word per action and stick to it: "start", not "start" here and "initiate" there.
  • Write procedures as direct commands, never as narration and never in the passive: "Install the component", not "the component must be installed".
  • 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: "only fails on growth" and "fails only on growth" say different things.
  • Break up long noun strings: "the proto import budget check script" becomes "the script that checks the proto-import budget".
  • Make every "it", "they", and "this" point at one obvious thing. Repeat the noun when in doubt. Never use "this" or "which" to point at a whole clause.
  • Don't drop verbs: "Phase 1 moves the converters and Phase 2 the runtime" leaves Phase 2 without one. Give it one.
  • Keep the small words that show structure, such as "that" in "Ensure that the switch is off". Never trade clarity for word count.
  • Repeat the article in a series when it prevents a misread: "the client and the host", not "the client and host", when they are two things.
  • Say which parts "and" or "or" joins when a sentence can group two ways. "Both...and", "either...or", and "if...then" are free disambiguators.
  • Use periods, not semicolons. Replace an em dash with a new sentence.
  • Make text in parentheses a full grammatical unit or its own sentence. Never form plurals with "(s)".
  • No slashes: write "a, b, or both" instead of "a/b" or "and/or".
  • Call each thing by one name, everywhere. A doc that says "the gate", "the ratchet", and "the budget check" for one thing teaches three things. Don't churn what didn't change.
  • 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.

Worked example

Before:

Configuration of the proto import ratchet budget script parameters is performed via budget.json. Note that it's important to remember that running with --write, which updates the committed budget to reflect the current count, should only be done when lowering it. If exceeded, CI fails.

After:

budget.mjs reads the committed budget from budget.json and counts the files that import protos. If the count exceeds the budget, CI fails. Run budget.mjs --write only to lower the budget.

Original by Lauren Tan (poteto), MIT license. Checked against the pstack mirror at 97de40d. View on GitHub

An unofficial beginner's guide to pstack, not its official docs. pstack is made by poteto; the official repo is the source of truth for commands and behavior. The original guide source is on GitHub.

Hosted by airali. Adapted from Xiaoxiaodong's MIT-licensed guide.