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

/pstack:unslop

Auto

In one lineTakes the "AI flavor" out of writing: stock phrases, empty words, lists of three, em dashes.

When to use
READMEs, PR descriptions, commit messages, or an AI reply that's too wordy.
Say it like this
/pstack:unslop Clean up the new README content, no em dashes

Just asking vs. using it

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

Just askingWith /pstack:unslop
Writes feel-good lines like "SQL you can read".Names the mechanism or a number, like "a column rename fails the build".
Says "experts believe" without naming anyone.Names the source, or deletes the claim.
Opens with "Great question!" and closes with "Let me know if...".Drops the pleasantries and flattery and answers directly.

What the document says

8 sections, about 850 words, 4 min to read. Click a section to read it.

OpeningIt scans the text for the patterns listed below, then rewrites it, keeping the meaning and the intended tone.

  1. 1Patterns to detect and fixRules carry fixed numbers that other skills cite. A removed rule leaves its number empty.
  2. 2ContentCuts empty "-ing" phrases like "highlighting", and makes "experts believe" name a source or go.
  3. 3LanguageSwaps AI words like "delve" for plain ones, says "is" for "serves as", and drops forced threes and synonym cycling.
  4. 4StyleBans em dashes, limits colons and bold, uses sentence-case headings, drops decorative emojis, and uses straight quotes.
  5. 5Communication artifactsDeletes chatbot lines like "I hope this helps!" and flattery like "Great question!", and answers directly.
  6. 6FillerShrinks "in order to" to "to" and stacked hedges to "may", and swaps generic endings for specific facts.
  7. 7JargonReplaces technical-sounding metaphor nouns like "substrate", "north star" and "flywheel" with the concrete word.
  8. 8Plain speechMakes each sentence name a mechanism or number, splits dense sentences, names the actor, and spells out arrows.

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. Give each rule a fixed number

    Rule numbers are stable ids that other skills cite.

    Makes the AI
    Other skills can just say "apply rule 13", and the numbers still line up after rules are added or removed.
    Why it works
    Fixed numbers make references short and exact, and they don't shift when the list changes.
    Borrow it
    Number your team's writing rules, then say in a review: "This paragraph breaks rule 4."
  2. Describe a scannable pattern

    Catch "is/are/was/were + past participle" and name the actor

    Makes the AI
    It picks out passive sentences one by one and names who does the action.
    Why it works
    A visible surface pattern tells the AI exactly what to search for, instead of judging by feel.
    Borrow it
    To remove a habit, show its shape: "Find every 'make use of' and change it to 'use'."
  3. Test filler by moving it

    if the sentence could appear unchanged in another project's docs, it says nothing about this one.

    Makes the AI
    Sentences that would fit any project get cut; what stays is about this project.
    Why it works
    "Filler" is hard to judge, but "would it still fit elsewhere?" is a quick test anyone can run.
    Borrow it
    When you ask for an intro edit, add: "Delete any sentence that stays true with a competitor's name in it."
  4. Say where the problem comes from

    An adverb propping up a weak verb means the verb is wrong.

    Makes the AI
    It doesn't just delete "quickly" or "significantly"; it picks an exact verb or a number instead.
    Why it works
    Naming the cause lets the AI fix the source and handle cases the list never mentions.
    Borrow it
    Give the cause with the rule: "A long title usually tries to say two things; split it."

Full text

The SKILL.md the AI reads, as written.

descriptionCut AI tells from any writing.

Unslop

Edit text to remove AI patterns. Scan for the patterns below, then rewrite. Preserve meaning and match the intended tone.

Patterns to detect and fix

Rule numbers are stable ids that other skills cite. A removed rule leaves a gap.

Content
  1. Superficial -ing phrases. "highlighting...", "ensuring...", "reflecting...", "showcasing...", "fostering...". Delete or expand with real sources.
  2. Vague attributions. "Experts believe", "Industry reports suggest", "Some critics argue". Name the source or delete.
Language
  1. AI vocabulary. Additionally, crucial, delve, enduring, enhance, fostering, garner, interplay, intricate, landscape (abstract), pivotal, showcase, tapestry (abstract), testament, underscore, vibrant. Replace with plain words.
  2. Fancy ways to say "is". "serves as", "stands as", "boasts", "features". Say "is" or "has".
  3. "Not just X, but Y." State the point directly instead.
  4. Rule of three. Don't force ideas into groups of three. Use the natural number.
  5. Synonym cycling. Protagonist, main character, central figure, hero all in one paragraph. Pick one, repeat it.
  6. False ranges. "from X to Y" where X and Y aren't on a meaningful scale. List topics directly.
Style
  1. Em dash overuse. Avoid em dashes entirely. Use periods or commas only (no parentheses, no en dashes, no hyphen-as-dash substitutes). If a thought needs separation, end the sentence or use a comma.
  2. Colon overuse. Colons are fine before a list or example, not as mid-sentence connectors. "If you're coming from traditional automation: instead of registering event handlers, you describe conditions" adds nothing with the colon. Rewrite to let the point stand on its own without comparison framing. "Describing when the scheduler should fire works best as plain English." Same meaning, no crutch punctuation.
  3. Boldface overuse. Don't bold every proper noun or acronym.
  4. Inline-header lists. The tell is a bold label and colon that restates the line: "Performance: Performance improved...". Convert those to prose. A bold lead-in that ends in a period, names the item, and is followed by genuinely new detail ("Schema in TypeScript. Tables live in one file.") is fine, not a tell.
  5. Title case headings. Use sentence case.
  6. Decorative emojis. Remove from headings and bullets.
  7. Curly quotes. Use straight quotes.
Communication artifacts
  1. Chatbot phrases. "I hope this helps!", "Let me know if...", "Of course!", "Certainly!", "Found the smoking gun!" Remove.
  2. Sycophantic tone. "Great question! You're absolutely right!" Respond directly.
Filler
  1. Filler phrases. "In order to" becomes "To". "Due to the fact that" becomes "Because". Delete "It is important to note that".
  2. Excessive hedging. "could potentially possibly be argued that it might" becomes "may".
  3. Generic conclusions. "The future looks bright." State specific plans or facts.
Jargon
  1. Abstract metaphor nouns. Substrate (base), wedge, wedge in (add), vector (way, method), locus, vantage, nexus, primitive as a noun, harness as a metaphor, surface as in "API surface", bedrock, scaffolding as a metaphor, modality, paradigm, gold-plating (more than the job needs), ratchet as a metaphor (the mechanism's real name, or a limit that only tightens), evacuate for moving code (move out), endgame (the last phase), north star, flywheel. These read as technical but usually have a plainer concrete word. Pick the concrete word.
Plain speech
  1. Say what it does, not how it feels. "the database stays close at hand", "SQL you can read", "types that follow your schema" name a feeling. The fix names the mechanism or a number: ".toSQL() returns the exact string sent to the database", "a column rename fails the build". Ask what the sentence tells the reader to do or know, then write that. If you can't restate it as a concrete instruction, fact, or number, cut it. One more check: if the sentence could appear unchanged in another project's docs, it says nothing about this one. Cut it.
  2. Shorten or split dense sentences. If the reader has to backtrack to parse a sentence, break it in two or drop clauses. One idea per sentence.
  3. Active voice. Prefer it. Catch "is/are/was/were + past participle" and name the actor: "queries are validated" becomes "the compiler validates queries", "the file is parsed by the loader" becomes "the loader parses the file". Passive is fine only when the actor is unknown or genuinely doesn't matter.
  4. Cut adverbs, or use a stronger verb. "runs quickly" becomes "is fast" or the number, and "significantly improves" becomes the measured delta. An adverb propping up a weak verb means the verb is wrong.
  5. Prefer the plain word. "utilize" and "leverage" become "use", "facilitate" becomes "help", "numerous" becomes "many", "in the event that" becomes "if". The fancier synonym is rarely clearer.
  6. Mannered prose. Metaphor or flourish where a literal phrase exists: aphorisms ("wire it or delete it"), rhetorical fragments for effect, personified code ("the plan holds it"), figurative verbs ("rides along", "stands on"), stock framing phrases. "A dial worth turning" becomes "a parameter worth varying". Say what you mean. Rule 26 covers the metaphor nouns.
  7. Over-compression. Dropped articles, verbless fragments, symbol-speak, and abbreviations that make the reader decode instead of read. "Parser rejects bad date → exit 2, no write" becomes "The parser rejects a bad date, exits with code 2, and writes nothing." Write whole sentences with their articles and verbs, and spell out arrows and abbreviations.

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.