
Write
Strip obvious AI writing tics and keep your voice before publishing docs, landing copy, or lifecycle emails.
Overview
write is a journey-wide agent skill that strips predictable AI writing patterns and keeps human voice—usable whenever a solo builder needs to polish English prose before committing to publish.
Install
npx skills add https://github.com/tw93/waza --skill writeWhat is this skill?
- 9 core rules: cut filler, break formulas, active voice, specificity, reader-in-room, rhythm, trust, anti-pull-quotes
- Smell-based catalog—not a top-to-bottom checklist; preserve voice and genre per SKILL.md stance
- Targets predictable AI patterns: throat-clearing, binary contrasts, false agency, vague extremes
- Rhythm guidance: mix lengths, prefer two items over three, no em dashes
- Over-editing is explicit failure mode—natural sentences stay untouched
- 9 core anti-AI writing rules in the English scenario
Adoption & trust: 6.5k installs on skills.sh; 5.6k GitHub stars.
What problem does it solve?
Your draft sounds like generic AI copy—filler openers, formula contrasts, and vague slogans—and you risk losing reader trust.
Who is it for?
Indie founders editing landing pages, docs, emails, or posts who want an agent editor grounded in anti-AI-smell rules.
Skip if: Non-English workflows, highly stylized fiction where deliberate fragmentation is the genre, or cases where you need factual research rather than tone editing.
When should I use this skill?
English prose sounds templated, filler-heavy, or pull-quote ready and you want smell-matched edits without destroying voice.
What do I get? / Deliverables
You get tighter, voice-preserving prose with concrete subjects and varied rhythm, without running a destructive global rewrite.
- Revised prose with reduced AI smells
- Edits scoped to matched issues only
Recommended Skills
Journey fit
Useful at every journey phase - explore requirements and options before committing to a direction.
Where it fits
Tighten hero and FAQ copy so benefits are specific instead of vague structural claims.
Revise README sections that read like narrator-from-a-distance into direct, task-focused guidance.
Edit launch thread or newsletter drafts to cut quotable slogans and throat-clearing openers.
Polish changelog and blog posts for rhythm and active voice before publish.
How it compares
An editorial smell guide for agents—not a grammar linter plugin or SEO keyword stuffing tool.
Common Questions / FAQ
Who is write for?
Solo builders and small teams publishing English content who want agents to reduce AI tells while respecting author voice.
When should I use write?
Use it in Idea when drafting research notes for clarity, in Validate on landing copy, in Build for docs, in Launch for distribution posts, and in Grow for lifecycle content—whenever prose sounds templated.
Is write safe to install?
It is editorial guidance only with no shell or network calls; still review the Security Audits panel on this Prism page like any third-party skill.
SKILL.md
READMESKILL.md - Write
> **How to use this file**: it is a catalog of smells, not a checklist to run top to bottom. The principles in `SKILL.md` Core Stance apply here too: over-editing is failure, the author's voice and genre win, and these lists are examples, not find-and-replace. A sentence that already reads natural stays. Match the smell, not the word. ## English Scenario Eliminate predictable AI writing patterns. Write like a human: varied, imperfect, specific. ### Core Rules 1. **Cut filler phrases.** Remove throat-clearing openers, emphasis crutches, and adverbs that only signal emphasis. Keep adverbs that carry real meaning. 2. **Break formulaic structures.** Avoid binary contrasts, negative listings, dramatic fragmentation, rhetorical setups, false agency. 3. **Use active voice.** Every sentence needs a human subject doing something. No inanimate objects performing human actions ("the complaint becomes a fix"). 4. **Be specific.** No vague declaratives ("The reasons are structural"). Name the specific thing. No lazy extremes ("every," "always," "never") doing vague work. 5. **Put the reader in the room.** No narrator-from-a-distance voice. "You" beats "People." Specifics beat abstractions. 6. **Vary rhythm.** Mix sentence lengths. Two items beat three. End paragraphs differently. No em dashes. 7. **Trust readers.** State facts directly. Skip softening, justification, hand-holding. 8. **Cut quotables.** If it sounds like a pull-quote, rewrite it. 9. **Do not replace one formula with another.** “Human” does not mean slangy, quirky, or performatively casual. 10. **No emoji.** Remove any emoji from the text being edited. ### Word Choice Examples, not exhaustive -- any word used to signal importance rather than to say something is suspect. **Overused emphasis adverbs (cut these when they only signal importance, not every adverb):** "quietly", "deeply", "fundamentally", "remarkably", "arguably", "certainly", "really", "just", "literally", "genuinely", "honestly", "simply", "actually" > NO: "quietly orchestrating workflows" / "fundamentally reshape how we think" > OK: Say what it does. Drop the adverb. **AI vocabulary: replace with plain language:** | Avoid | Use instead | |-------|-------------| | delve (into) | examine, look at, explore | | leverage (as verb) | use | | utilize | use | | robust | strong, reliable, solid | | streamline | simplify, cut | | harness | use, apply | | navigate (challenges) | handle, address | | unpack | explain, examine | | paradigm | system, approach, model | | synergy | combination, cooperation | | ecosystem | community, network, field | | tapestry | mix, combination | | landscape | situation, field, area | | game-changer | significant, important | | deep dive | analysis, examination | | moving forward | next, from now | **Pompous copulas: use "is" instead:** > NO: "serves as", "stands as", "marks", "represents" > OK: "is" ### Sentence Structures to Avoid Examples, not exhaustive -- any construction that performs insight rather than delivers it belongs here. **Negative parallelism**: the single most common AI tell: > NO: "It's not bold. It's backwards." / "Not because X, but because Y." / "The question isn't X. The question is Y." > OK: State Y directly. Drop the negation entirely. **Negative countdown:** > NO: "Not a bug. Not a feature. A fundamental design flaw." > OK: "It's a fundamental design flaw." **Rhetorical self-questions:** > NO: "The result? Devastating." / "The worst part? Nobody saw it coming." > OK: State it: "The result was devastating." **Anaphora abuse**: repeating the same sentence opener: > NO: "They assume that... They assume that... They assume that..." > OK: Combine or restructure. One statement, clear subject. **Tricolon abuse**: rule of three, used three times back to back: > NO: "Products impress people; platforms empower them. Products solve problems; platforms create worlds." > OK: Make the point once, cleanly. **False ranges:** > NO: "From innovation to cultural transf