// 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.
Use when reviewing PRs, simplifying over-engineered code, judging architecture, or renaming unclear concepts — inline fake helpers, delete meatless ceremony, rename lying names, merge over-split files, reject premature abstraction, say no to speculative config/modes/layers, then end with the smallest safe next change. Triggers when code is too fancy, too abstract, too clever, too many files/helpers/layers, or too well-factored but painful to change. Embody Grug brain: complexity very bad, small words, no consultant speak, no hard pivot to opposite dogma.
Use when authoring an agent skill that wraps a command-line tool — covers hands-on tool exploration, required vs. recommended sections, installation/usage structure, trigger-rich descriptions, task-grouped commands, progressive disclosure, and a pre-publish checklist. Triggers for CLI / command-line / terminal / shell-command tools and binary wrappers; for review, run the Checklist section.
Use when optimizing CLAUDE.md, AGENTS.md, custom commands, or skill files — diagnose the concrete failure first, then apply current documented Anthropic best practices (explicit instructions, context/motivation, examples, output and verbosity control, thinking/effort, CLAUDE.md size and skill-description rules) instead of inventing improvements. Triggers when a prompt isn't followed, a skill won't activate, CLAUDE.md is too long or ignored, or migrating prompts to current Claude models.
Jujutsu (jj) — the Git-compatible version control system. Activate ONLY when a .jj/ directory is present in the project or when jj/jujutsu is explicitly mentioned. Do NOT activate for plain git repos without .jj/. Use for any VCS operations in jj-managed projects: commit, push, pull, branch, bookmark, rebase, squash, merge, diff, log, status, working copy, change ID, revset, fileset, template, configuration, workspaces.
Use when authoring, creating, refining, or troubleshooting agent skills — scaffold SKILL.md and frontmatter, write and optimize the trigger description, structure the body with progressive disclosure, validate structure, and test or debug activation. Also when building a new skill from scratch, when a skill won't trigger, loads incorrectly, or the agent ignores it entirely. Use when a skill misbehaved in the current session and needs adjustment based on learnings.
Use when building or reviewing frontend UI — dashboards, admin panels, landing pages, marketing sites, web apps. Drives domain-specific design decisions (typography, color world, layout, CSS token naming, depth and spacing systems) instead of generic AI defaults; routes to app.md (product/data UIs) or marketing.md (public/creative pages) by context.
| 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.
