From prose
ALWAYS invoke this skill when auditing reader-facing documents such as public docs, web pages, and product messages for outside readers like developers and customers. NEVER invoke for chat responses to the user (no matter how long), operational prose like code comments, commit messages, or agent-facing instructions like AGENTS.md and SKILL.md.
How this skill is triggered — by the user, by Claude, or both
Slash command
/prose:auditing-proseThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Invoke the `prose:standardizing-prose` skill before proceeding. If that skill is unavailable, report the missing skill and continue with the closest available workflow.
Invoke the prose:standardizing-prose skill before proceeding. If that skill is unavailable, report the missing skill and continue with the closest available workflow.
Detect and fix formulaic patterns that signal machine-generated or lazy writing. Flag specific violations and suggest concrete rewrites.
<essential_principles>
Six categories of patterns to detect. Each is detailed with examples in the reference file.
Word choice -- Significance adverbs ("quietly", "deeply"), authenticity adverbs ("genuinely", "truly", "actually"), overused vocabulary ("delve", "leverage", "robust", "genuine"), ornate nouns ("tapestry", "landscape", "paradigm"), pompous verbs ("serves as", "stands as").
Sentence structure -- Negative parallelism ("It's not X -- it's Y"), stacked negations ("Not X. Not Y. Just Z."), rhetorical self-answers ("The result? Devastating."), anaphora abuse, tricolon stacking, filler transitions ("It's worth noting"), tacked-on significance ("highlighting its importance"), false ranges, gerund fragment litanies, tautological definitions ("An irreversible change does not revert"), redundant paired examples.
Paragraph structure -- Strings of punchy fragments as standalone paragraphs, listicles disguised as prose ("The first... The second... The third...").
Tone -- False-suspense transitions ("Here's the kicker"), unnecessary metaphors ("Think of it as..."), hypothetical openers ("Imagine a world where..."), performed vulnerability, asserting clarity ("The truth is simple"), grandiose stakes inflation, teacher-student condescension ("Let's break this down"), vague attributions ("Experts argue"), invented concept labels ("the supervision paradox").
Formatting -- Em-dash overuse, bold-first bullets, unicode decoration.
Composition -- Fractal summaries, dead metaphors, historical analogy stacking, one-point dilution, content duplication, signposted conclusions, dismissive optimism ("Despite its challenges...").
</essential_principles>
/standardizing-prose for the anti-pattern catalog<success_criteria>
Review is complete when:
</success_criteria>
<reference_index>
| Skill | When to Read |
|---|---|
/standardizing-prose | Always -- before auditing |
</reference_index>
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Applies a firm's KYC/AML rules grid to parsed onboarding records: assigns risk rating, checks required documents, outputs rule outcomes with citations, and routes for escalation.
Generates daily or weekly digests of activity from connected sources (chat, email, docs, tasks, CRM), highlighting action items, decisions, mentions, and project updates.
npx claudepluginhub outcomeeng/plugins --plugin prose