writing-personal
Write essays, blog posts, newsletters, and opinion pieces in a personal first-person voice — concrete cold open, argument by historical analogy, deliberate sentence rhythm, aphoristic kicker. Use when drafting or editing personal essays, blog posts, op-eds, newsletter issues, or any first-person long-form meant to persuade or reflect.
What this skill does
# Personal Writing A first-person essay voice: personal, opinionated, culturally omnivorous, skeptical of hype, warm toward the reader, and honest about its own limits. The through-line is humanist — care less about the gadget than about what it does to people. Conversational but earned: a smart friend thinking out loud, not a pundit performing certainty. ## The essay arc A skeleton, not a cage. 1. **Cold open on something concrete and personal** — an object, a scene, a date, a late-night message. Never open on the abstract thesis. 2. **Zoom out from the particular to the larger point.** The specific object becomes the parable: a pen becomes an essay about ambient deception; a product shortage becomes an argument about architecture. 3. **Build through analogy — especially historical precedent.** Line up past cycles and find the pattern that explains the present. This is the core argumentative engine. 4. **Use evocative section headers** that name an idea (`The Light Nobody Sees`), never `Section 2`. 5. **Ground every abstraction in a hard number or specific** — watts, dollars, dates, named examples. Earn conclusions with data. 6. **Land on an aphoristic kicker** — a short, resonant closing line that reframes the whole piece. e.g. *"The optical fiber is already in the ground. We just don't know yet what runs on it."* 7. **Sign off with date and place**, italicized: *"June 3, 2026. San Francisco."* > **Curated-link / roundup variant:** a short personal preamble, then a list where > each item is a **bold linked title** + *publication* in italics, followed by 2–4 > sentences of opinionated annotation. Often closes with an ICYMI self-links section. ## Sentence mechanics and rhythm - **Alternate long and short.** Unspool a mechanism in a long sentence, land the point in a clipped one. *"…it is two tokens per second. That feels like waiting."* - **Use the very short sentence as a hammer** — one to four words on its own. *"I do."* *"The base was the base."* - **Build triads and anaphora.** *"Courts punish victims. Authority figures perform competence without exercising it. Experts are decorative."* - **Repeat a phrase to drive it home.** *"One fiber becomes many."* - **Ask the reader a direct question, then answer it.** *"Have you wondered why?"* - **Concede, then complicate.** *"Both are true. And yet, that is not the whole story."* - **Reframe the question** rather than answer the obvious one. *"The question is not whether 25x revenue is too much. The question is whether the revenue is the revenue."* - **Correct or intensify yourself mid-stride.** *"…good for AI. Make that very good for AI."* - **Punctuation:** em-dashes for the pivot and the aside; parentheses for dry wit; *italics* to stress a phrase; standalone **bold lines** to plant a thesis. ## Explaining a complex idea Homely analogy first, then specifics. Introduce the jargon term, define it in plain words immediately, return to the human stakes. A model is *"a giant warehouse of numbers… the chip walks through the entire warehouse."* Never leave an acronym undefined. ## Diction and verbal tics - Address the audience as **"dear readers."** - Plain Anglo-Saxon verbs over Latinate ones; contractions throughout. - A slightly vintage, colloquial register dropped into serious analysis is welcome, used sparingly. - Pop-culture and literary references as analytic shorthand. - The wit is dry, carried in em-dash asides — never zany. - Reuse your own coinages and link back to your past pieces; build a personal lexicon. ## Do / Don't **Do** — open with a concrete scene; arrive at the thesis by paragraph three; earn claims with numbers and named examples; reason by historical analogy; vary sentence length and end on a short line; link generously; admit uncertainty and revise in public. **Don't** — open with the abstract argument or a definition; stack adjectives or reach for breathless hype (you are the skeptic in the room); leave jargon undefined; write uniform mid-length sentences; perform certainty you haven't earned or punch down. ## Checklist before publishing - [ ] Concrete, personal cold open — not the thesis. - [ ] A historical analogy doing real argumentative work. - [ ] At least one homely analogy that makes a hard idea click. - [ ] Hard numbers grounding the big claims. - [ ] Evocative section headers, if sectioned. - [ ] Deliberate long/short rhythm; a few one-line hammers. - [ ] One triad or anaphora passage. - [ ] Links to sources and to your own past pieces. - [ ] An aphoristic kicker as the last line. - [ ] Italic date + place sign-off.
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.