cringelinter
Lints writing for AI slop tells, including overused words, cringe phrases, structural patterns, and bro-speak declaratives that are fingerprints of LLM-generated text. Use this skill any time the user asks to check, clean, lint, or review writing for AI tells, AI slop, cringe phrases, or generic LLM-sounding language. Also use it when the user says things like "does this sound AI-written?", "make this sound more human", "remove the AI vibes", "de-slop this", or "clean up my draft". If the user shares a piece of writing and expresses any concern about it sounding robotic, generic, or artificial, use this skill.
What this skill does
# Cringelinter Lints a piece of writing for the tells that signal LLM-generated text. Returns a flagged report and a cleaned version. --- ## Rules ### 100 — Vocabulary #### Rule 101: AI Fingerprint Words These appear statistically far more often in AI output than in human writing. Flag every instance: > delve, tapestry, landscape (used abstractly), realm, underscore (as a verb), pivotal, robust, leverage, harness, streamline, empower, unlock, innovative, seamless, cutting-edge, game-changer, synergy, underpinnings, nuanced, palpable, camaraderie, intricate, utilize, holistic, transformative, elevate, foster, navigate, unpack **Fix:** Replace with a plain, specific alternative. #### Rule 102: Fancy/Latinate Words Flag Latinate or formal words where a plain equivalent exists: > "commence" → "start" / "terminate" → "end" / "facilitate" → "help" / "endeavor" → "try" / "purchase" → "buy" / "demonstrate" → "show" / "assistance" → "help" / "utilize" → "use" / "obtain" → "get" **Fix:** Replace with the plain equivalent. Fancy words signal effort spent on dressing rather than substance. #### Rule 103: Qualifiers Flag weak qualifiers that dilute the sentence: *rather, very, little, pretty, quite, somewhat, fairly, kind of, sort of, a bit, slightly.* **Fix:** Cut the qualifier. If the claim can't stand without it, reconsider whether the claim belongs. #### Rule 104: Overstatement Flag superlatives and absolutes used loosely: "the most important," "revolutionary," "absolutely," "completely," "totally," "always," "never," "the best ever," "unprecedented." **Fix:** Replace with an accurate, specific claim, or cut. Let the reader decide if it's impressive. --- ### 200 — Syntax #### Rule 201: Passive Voice Flag passive constructions that could be active. "The results were analyzed by the team" → "The team analyzed the results." **Fix:** Rewrite as active. Exception: leave passive when the actor is unknown, irrelevant, or deliberately de-emphasized. #### Rule 202: Negative Form Flag negative formulations when a positive would be more direct. "He was not very often on time" → "He usually came late." "The approach is not without merit" → "The approach has merit." "Not unlike" → "similar to." **Fix:** Rewrite in positive form. The positive says the thing; the negative circles around it. #### Rule 203: Needless Words Flag phrases where words can be cut without losing meaning: - "the fact that" → cut or restructure - "in order to" → "to" - "due to the fact that" → "because" - "at this point in time" → "now" - "it is important to note that" → cut; just say the thing - "as previously mentioned" → cut - "The reason for this is that" / "The reasoning is that" → cut; make the claim directly - Redundant pairs: "each and every," "first and foremost," "various different" - Filler openers: "So," / "Well," / "Look," / "Basically," / "Essentially," — flag when they introduce nothing **Fix:** Cut or restructure as shown above. #### Rule 204: Adjective and Adverb Overload Flag writing that leans on adjectives and adverbs where strong nouns and verbs would do more work. "She walked quickly and nervously" → "She hurried." "A very large number of significant problems" → "Many problems." **Fix:** Replace adjective/adverb combinations with stronger nouns and verbs. #### Rule 205: Fragmented Punchy Sentences Flag stacked short declarative sentences. "These are not bad words. They are fingerprints." **Fix:** Combine using End-Focus (Joseph Williams). "These aren't bad words so much as fingerprints." #### Rule 206: Flat Sentence Rhythm Flag passages where every sentence is roughly the same length. Monotonous rhythm signals no sentence is being emphasized over others. **Fix:** Vary sentence length. Do not add filler — restructure or combine to create contrast. #### Rule 207: Wrong Subject Flag sentences where the grammatical subject doesn't match what the sentence is actually about. "Readers are better guided when the subject matches the main idea" is about sentence structure, not readers. **Fix:** Rewrite so the grammatical subject is the thing the sentence is actually about. "Choosing the right subject keeps the writing clear." #### Rule 208: Misused Em Dash Flag em dashes used purely as a dramatic pause before a punchline or restatement — where the clause after the dash adds nothing the sentence doesn't already imply. **Fix:** Cut the clause after the dash, or restructure the sentence to remove the pause entirely. Do not flag em dashes used to insert a clarifying detail or sharp aside. #### Rule 209: Nominalization Flag nominalized verbs where the verb form is stronger: "make a decision" → "decide," "provide a summary" → "summarize," "conduct an analysis" → "analyze," "give consideration to" → "consider." **Fix:** Replace with the verb form. Nominalizations bury the action; verbs surface it. --- ### 300 — Rhetorical Patterns #### Rule 301: Banned Transition Openers Flag sentences that open with: > Notably, / Importantly, / Furthermore, / Moreover, / Consequently, / Additionally, / It's worth noting that / It is important to note that / In today's world, / At its core, / At the end of the day, / The bottom line is, / In conclusion, **Fix:** Cut the opener and restructure the sentence to open with the actual claim. #### Rule 302: Bro-Speak Declaratives Flag these and close variants: > "Here's the thing..." / "Here's why that matters." / "And that's the point." / "That's it. That's the whole idea." / "This is where it gets interesting." / "So what does that mean in practice?" / "Let that sink in." / "Think about that for a second." / "No, really." / "Seriously." / "Full stop." / "That's not a bug. That's a feature." / "The secret? [x]" / "The result? [restatement]" / "Stick with me here." / "Bear with me." / "This might sound obvious, but..." / "Stay with me." / "Let's dive in." / "Let's unpack that." **Fix:** Cut entirely. #### Rule 303: Mic-Drop Flag a single short sentence dropped after a paragraph for dramatic effect, carrying no new information. **Fix:** Cut entirely. #### Rule 304: Performative Informality Flag a breezy, hey-we're-all-friends tone the writing hasn't earned. Signs: unsolicited asides to the reader, rhetorical winks, conspiratorial "we." The test: would this register as warm from a stranger, or presumptuous? **Fix:** Rewrite in a register the content has earned. Remove the aside or restate it as a direct claim. #### Rule 305: Empty Summary Sentences Flag sentences at the end of a paragraph that sound conclusive but say nothing new: "By following these steps, we achieve better performance." / "By internalizing these principles, you can cut through the noise." **Fix:** Cut, or replace with a sentence that adds new information. #### Rule 306: Preview/Summary Structure Flag two related structural tells: - **Outro summaries**: a closing paragraph that restates what the section just said - **Intro previews**: an opening that describes what is about to be said instead of saying it **Fix:** Cut the outro or preview. Say the thing directly. #### Rule 307: Rhetorical Questions Flag rhetorical questions posed and immediately answered in the next sentence. "So why does this matter? Because it affects everything downstream." **Fix:** Rewrite as a direct statement. "It affects everything downstream." --- ### 400 — Substance #### Rule 401: Vagueness and Unsupported Claims Flag claims that invoke unnamed authority or avoid specificity: "some experts say," "research shows," "many people believe," "it has been shown that." Also flag adjectives that describe without specifying — "powerful, flexible, intuitive" applied without evidence. **Fix:** Name the source or drop the attribution. Replace vague adjectives with specific evidence or cut them. #### Rule 402: Fluency Without Understanding Flag sentences that are grammatically correct but explain nothing — writing that sounds authoritative while glossing over substance. Signs: defin
Related in Image & Video
watch
IncludedWatch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.
physical-ai-defect-image-generation
IncludedUse when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.
accelint-react-best-practices
IncludedReact performance optimization and best practices. ALWAYS use this skill when working with any React code - writing components, hooks, JSX; refactoring; optimizing re-renders, memoization, state management; reviewing for performance; fixing hydration mismatches; debugging infinite re-renders, stale closures, input focus loss, animations restarting; preventing remounting; implementing transitions, lazy initialization, effect dependencies. Even simple React tasks benefit from these patterns. Covers React 19+ (useEffectEvent, Activity, ref props). Triggers - useEffect, useState, useMemo, useCallback, memo, inline components, nested components, components inside components, re-render, performance, hydration, SSR, Next.js, useDeferredValue, combined hooks.
elevenlabs-agents
IncludedBuild conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs. Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT. Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflows or tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labs packages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication
humanizer
IncludedHumanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
generating-mermaid-diagrams
IncludedSalesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. TRIGGER when: user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user wants PNG/SVG image output (use generating-visual-diagrams), or asks about non-Salesforce systems.