菜单
Detect and eliminate common AI writing tropes from prose. Use when drafting, editing, or reviewing text to avoid the predictable patterns that mark AI-generated writing.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | ai-writing-tropes |
| description | Detect and eliminate common AI writing tropes from prose. Use when drafting, editing, or reviewing text to avoid the predictable patterns that mark AI-generated writing. |
| metadata | {"trigger":"Writing prose, editing drafts, reviewing content for AI tells, or when user mentions \"tropes\", \"AI patterns\", \"slop\", or \"tropes.fyi\"","author":"tropes.fyi"} |
Comprehensive catalog of AI writing patterns that make text feel machine-generated. Any single pattern used once might be fine. The problem is when multiple tropes appear together or when one trope repeats throughout a piece.
When writing or editing prose:
Overused vocabulary and phrasing that AI defaults to. See references/word-choice.md.
Key offenders: "quietly", "delve", "tapestry", "landscape", "serves as", "leverage", "robust", "harness", "streamline".
Formulaic sentence patterns that no human writes at scale. See references/sentence-structure.md.
Key offenders: negative parallelism ("not X — it's Y"), dramatic countdowns ("Not X. Not Y. Just Z."), self-posed rhetorical questions, anaphora abuse, tricolon abuse, gerund fragment litanies.
Layout and organization patterns that betray AI generation. See references/paragraph-structure.md.
Key offenders: short punchy fragments as standalone paragraphs, listicles disguised as prose.
Voice and framing habits that sound performative. See references/tone.md.
Key offenders: false suspense ("Here's the kicker"), patronizing analogies ("Think of it as..."), false vulnerability, stakes inflation, vague attributions, invented concept labels.
Visual and typographic tells. See references/formatting.md.
Key offenders: em-dash addiction, bold-first bullets, unicode decoration.
Document-level structural problems. See references/composition.md.
Key offenders: fractal summaries, dead metaphors beaten into the ground, historical analogy stacking, one-point dilution, signposted conclusions.
Before delivering prose, ask:
Write like a human: varied, imperfect, specific.
Find and flatten "fake layer" indirection in a TypeScript codebase — functions with exactly one caller that only forward, reshape, or inject dependencies and add no fact. Runs a deterministic AST detector that flags candidates, then uses agent judgment to inline the real slop while keeping functions that do real work (type narrowing, throwing, validation, lifecycle). Use when asked to reduce over-abstraction, "un-slop" or simplify code, flatten dependency-injection ceremony, delete single-use wrappers, or clean up AI-generated indirection. Pairs with a goal/loop prompt to run iteratively across a codebase until clean.
Guides maintainability-first cleanup, refactoring, and review in strict TypeScript repos and monorepos. Use when improving code health, deleting dead code, reducing duplication, or enforcing boundaries.
Use when writing or improving README files. Not all READMEs are the same — provides templates and guidance matched to your audience and project type.
Write, review, and restructure useful documentation with Diataxis, audience-specific README patterns, and AI-writing trope cleanup. Use when creating docs, improving READMEs, reorganizing documentation, or editing prose for clarity.
Designs and reviews WebMCP instrumentation for existing web apps, especially SPAs. Use when adding agent-accessible tools, route maps, prompts, or WebMCP workflows to a React, Vue, Angular, or vanilla browser app, or when deciding whether WebMCP is the right fit.
