Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Build frame-exact motion graphics — animated logos, kinetic typography, brand videos, animated titles and social clips — as a single HTML file driven by a paused Web Animations timeline, then export them to MP4 in 1:1, 4:5 and 9:16. Use this whenever someone wants to animate a wordmark or logo, make a video from text…
Use when named delegation is a genuine option for current work, when preparing or reviewing a handoff, or when continuing delegated work to a verified outcome. It supplies context recovery, deliberate skill selection, necessary-only delegation, evidence requirements, and continuation discipline. Do not use for…
Clone a ChatCut project into Final Cut Pro via FCPXML with frame accuracy — cuts, multi-track overlays, zoom moves (static punch-ins and keyframed slow pushes), music/SFX with volumes and fades, and native iTT captions. Use this skill whenever a user wants to export, hand off, convert, or "open in Final Cut Pro / FCP"…
Diagnose and safely repair Codex "Reconnecting... 1/5" through "5/5" loops in the CLI, desktop app, or IDE on macOS, Linux, and Windows. Use when a Codex turn stalls on repeated stream reconnects or only succeeds after HTTPS fallback; do not use for generic login, quota, model, or rate-limit errors.
Integrate AI detection into PACS workflow. Also use when setting up, configuring, or optimizing AI detection systems for medical imaging. Also covers Aidoc, Nvidia Clara, Zebra Medical, MaxQ AI, and Qure AI integration.
Persistent file-based notebook (.carnet/ / .md, auto-expiring after 30 days of disuse) for AI agents and humans. Use whenever saving, recalling, or organizing notes across sessions — IMPLICIT cues include the user recapping a tricky fix worth not redoing, asking 'what did we decide about X', handing off mid-task…
Run a bounded SPEC → BUILD → REVIEW → REPAIR workflow until verified or blocked. Explicit invocation only: $specloop in Codex or /specloop in Claude Code.
Use when a problem involves interacting actors, feedback loops, delays, incentives, constraints, unintended consequences, or repeated patterns over time. Use when applying systems thinking, causal loop analysis, system mapping, leverage point identification, or dynamic complexity diagnosis.
Run the anti-AI-writing checklist on any text before it leaves the agent. Use this skill whenever you produce text humans will read — social posts, emails, blog content, video scripts, Slack messages, newsletter copy, anything. Also triggers on "slop scrub", "check for AI-isms", "scrub this", "check this copy"…
Fetches Google Trends data including daily trending topics, real-time trends, interest by region, related topics, related queries, and autocomplete suggestions. Use when the user asks about trending searches, search popularity, keyword trends, or Google Trends data.
A business-strategy discussion role based on Jeff Bezos’s publicly known ways of thinking, including starting with customer needs, planning for the long term and looking for reinforcing business activities.
Retrieve evidence-backed viewpoints from the kol-transcripts repository. Use when a user wants to compare a thesis with KOL opinions, find who expressed a similar or opposing view, recover exact original wording from transcript Markdown files, or cite a video URL and timestamp. Especially useful for strategy research…
ColPali-style Vision RAG: embed rendered PDF pages, retrieve via ColBERT MaxSim, feed top-k pages to Qwen2-VL, no OCR. Use for PDF/document QA over figures and tables, multimodal retrieval, or Recall@k/MRR eval.
Use when a task specifically concerns Adobe InDesign: InDesign documents, layouts, pages, spreads, frames, styles, publishing, UXP, or layout scripting; this is the product subskill routed from adobe-products.
Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a verdict. MANDATORY TRIGGERS (always invoke on these exact phrases) 'council this', 'run the council', 'convene the council', 'war-room this', 'pressure-test this'…
Evidence-first opportunity discovery — finds novel, defensible product/startup/project opportunities by researching before ideating, and mechanically rejects generic "AI-powered X" slop with deterministic validators. Use whenever the user asks for startup ideas, product or business opportunities, "what should I…
Review a Markdown design document, consume an accepted fix queue, or independently verify accepted fixes with layered contract extraction, architecture reasoning, adversarial falsification, deterministic evidence gates, risk-based partial re-review, and human-only admission. Use only when the user explicitly invokes…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: