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。
Dude, come on. You write at the density of your own thinking and leave the reader to unpack it. Apply whenever explaining anything to a human — not just end-of-run summaries, every message.
Use when creating or iterating staged planning artifacts for a complex feature: design discussion, structure outline, final executor plan, or supporting research/research questions. Also use when designing before coding, breaking work into vertical slices, or deepening a high-value roadmap item, NNN improve plan, architecture candidate, or HumanLayer-style task.
Use when turning a roadmap, repo priorities, architecture priorities, chosen opportunities, accepted feature outlines/plans, or “roadmap to plans” request into grouped improvement plan batches for future executors. Writes README.md indexes, 001-*.md/NNN-style plans, optional memo-*.md files, verification gates, drift checks, STOP conditions, rejected approaches, and executor handoff notes.
Use when a user asks “what should I work on in this repo?”, “what’s worth doing next?”, repo audit, tech-debt priorities, architecture priorities, old-plan reconciliation, or repo-grounded opportunity discovery. Produces .agents/ROADMAP.md with generated opportunities, user-seeded ideas, Now/Next/Later sequencing, rejected/not-now items, and next-artifact recommendations. Not for standard product/release roadmaps; if multiple repos are requested, create one roadmap per repo.
Use when reviewing code quality, asking whether a refactor or design is good, looking for code smells, or evaluating architecture tradeoffs. Identifies shallow interfaces, invalid state models, unclear boundaries, hidden effects, weak failure contracts, over-mocking, over-abstraction, compatibility glue, and clean-looking code that preserves bad models.
Build evidence-backed software/product roadmaps from repo state, tickets, ideas, audit findings, or user goals — prioritize and sequence work across Now/Next/Later, milestones, dependencies, risks, and handoffs. Use when asked for a roadmap, feature roadmap, technical roadmap, release plan, milestone plan, backlog prioritization, sequencing, what to build next, or to turn improve/ideate/brainstorm/design-discussion outputs into an execution sequence. Not for implementing code or writing PR-level plans.
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.
