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.
Draft and revise academic prose in the author's voice, repair sentence-level reasoning, trace systems-paper claims to evidence, prepare reviewer responses, and critically appreciate papers for transferable lessons. Use for manuscript writing, scoped editing, logic checks, response letters, and paper appreciation…
Turn meeting recordings into notes with an unbroken chain of custody from audio to claim. Use when the user has recordings or audio to transcribe or summarize, or when an existing transcript or auto-summary reads as garbled or untrustworthy.
Drive a running Flutter app (debug or profile) with Marionette — an AI agent's hands and eyes for the app — tapping/typing/scrolling, screenshots, logs, hot reload/restart, device sweeps, custom extensions, and the session report, via marionettemcp or the marionette CLI. Use whenever asked to test, click through…
Organize bookmarks, folders, and markdown notes in the Arcmark macOS app. ALWAYS use this skill when the user asks to save a link, create a folder, move bookmarks between workspaces, take notes, or otherwise tidy their Arcmark sidebar.
Drive Chrome via the DevTools Protocol from JavaScript. Run JS snippets through the browser-harness-js CLI — it auto-spawns a long-lived bun HTTP server holding a fully-typed CDP Session, and every call (browser-harness-js 'await session.Page.navigate(...)') executes against the same persistent connection. Session…
Run vet immediately after ANY logical unit of code changes. Do not batch your changes, do not wait to be asked to run vet, make sure you are proactive.
Long-running iterative development loops with pacing control and verifiable progress. Use when tasks require multiple iterations, many discrete steps, or periodic reflection with clear checkpoints; avoid for simple one-shot tasks or quick fixes.
Use when working in an SDL-MCP-enabled repository, including repository exploration, task context, code inspection, runtime execution, edits, or SDL-MCP tool calls.
Manage authorized project work through Agent Kanban and Realmroot Toolbox, typically in scheduled-task or heartbeat-triggered Sessions. Proactively inspect what needs doing, delegate execution to other Agents, and coordinate and review their Tasks as a manager.
Use when an author has received peer-review comments and scores for an academic paper and needs to diagnose underlying reviewer concerns, decide whether a rebuttal is worthwhile, plan rebuttal experiments, or prepare evidence-grounded response material and revision plans for the author to review and finalize. Produces…
The pipeline driver for the Hermes Multi-Agent Workflow. Triggered by new intake tasks on the triage board. Dedups, scores, fans out research, routes, proposes at the human gate, and on approval lets the engine spawn the fulfillment chain. It is DELIBERATELY THIN: it calls engine/ for every deterministic step and only…
Use when helping someone USE Infomap as an analysis tool — running the map equation for community detection via the Infomap CLI, Python package, R package, or notebooks; choosing a network representation or flow model (multilayer, memory/state, metadata, bipartite); reproducible analysis; result interpretation; or…
Panel design for DEVELOPING / dynamic systems (embryonic organs, differentiation, regeneration). The target experiment is usually a LATE / terminal stage, but the biology is a trajectory: terminal cell types are end-products of earlier lineage programs. A panel built from the target stage alone resolves terminal…
Create, test, and publish plugins for the Digital Garden Eleventy template (oleeskild/digitalgarden, used by the obsidian-digital-garden plugin and Forestry.md). Use when asked to build a garden plugin, add a feature to a digital garden as a plugin, write or edit a garden-plugin.json manifest, or publish a plugin to…
Automate source-grounded research with Google NotebookLM. Create notebooks from URLs, text, or local files; ask cited questions; run fast or deep web research; create articles and social drafts; and generate or download audio, video, cinematic video, slides, reports, study guides, quizzes, flashcards, mind maps…
Secure dependency upgrades with supply chain protection, cooldowns, and staged rollout. Use when upgrading deps, configuring security policies, or preventing supply chain attacks.
Multi-LLM collaborative brainstorming and planning. Use when user explicitly requests consultation with multiple AI models (ChatGPT, Gemini, other LLMs) before presenting an implementation plan, or asks to "consult the council", "ask other models", or "get perspectives from other AIs". Queries external LLM APIs…
A writing workflow for the literature-review and research-commentary sections of an NSFC grant proposal, China's National Natural Science Foundation application.
An SEO link-checking skill that examines websites linking to you, planned link sources, and links you already have. It reports signals and evidence under Google’s link-spam guidance, not Google’s official decision.
Use this skill for genetics, genome source, variant, gene, phenotype, disease, screen, pharmacogenomics, and Genomi install/setup maintenance questions.
Drive the user's existing Chromium-family browser with deterministic Playwright. Use when asked to inspect, automate, test, or interact with a visible browser tab; continue an authenticated browser workflow; handle 2FA, passkeys, CAPTCHAs, or payment confirmation; record browser behavior; or capture an authenticated…
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: