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.
Apply Gang of Four and related design patterns in JavaScript and TypeScript. Use when implementing creational, structural, or behavioral patterns, or when the user mentions factories, builder, prototype, flyweight, singleton, object pool, adapter, wrapper, decorator, proxy, bridge, composite, facade, chain of…
Meta-skill for building and managing agent persona skill packs (instruction-only; no bundled installer or auto-downloaded binaries). Credentials are never written into generated packs by the framework; publish/ACN/register require explicit user CLI. Use when the user wants to create a new agent persona, install/manage…
A tool for turning books and other reading materials into a conversational persona that answers in the book's style of thinking. It can also combine several related books into a versioned, evolving perspective while keeping their disagreements visible.
Tactical user interface design guide for fixing layouts, selecting colors/fonts, and creating professional UIs. Use when the user asks to "make this look better," needs help with CSS/styling decisions, wants to create a design system, or needs to fix a cluttered interface.
Generate and execute AFSIM (Advanced Framework for Simulation, Integration and Modeling) scripts. Use when the user needs to: (1) Create AFSIM/WSF scenario scripts, (2) Generate simulation scripts with proper syntax, (3) Run AFSIM simulations using mission.exe, (4) Debug or fix AFSIM script syntax errors, (5) Work…
Create and browse Anki flashcards during coding sessions. Use when the user invokes /anki, asks to create a flashcard, or when you notice the user learning something new and worth remembering (a concept, trick, gotcha, or mental model).
Build and maintain a semester-long Obsidian course vault with course overviews, lesson notes, concept pages, graph hubs, replay-sync trackers, and replay-to-note workflows. Use when Codex needs to manage course knowledge in Obsidian, especially when BUAA replay artifacts should become structured lesson notes rather…
Tutor the user toward deep understanding of a topic, codebase, paper, artifact, or concept through incremental explanation, active recall, and verification. Use when the user asks to be taught, wants to understand something deeply, says "teach me", "walk me through", "explain until I get it", "quiz me", asks for…
Connect OpenClaw to Vault Agent Memory as a local-first governed project memory layer. Search first, then bounded-read cited source ranges; propose new memories as candidates instead of writing directly into active memory.
Deep-investigation methodology for OmniSeek. Sweep in parallel with omniseekgather, judge the signals, zoom through walled sources, structure the evidence, and close with an explicit gap ledger.
A Yandex Direct advertising tool for checking and managing pay-per-click campaigns in Russia through Yandex’s API. It covers campaigns, keywords, ads, reports, budgets, and optimization suggestions.
Create, repair, validate, and package SVG, APNG, or hybrid desktop pets using pet-forge templates, Codex image generation, animation conventions, state mappings, and generation tools. Use when the user asks to make a desktop pet, create or edit character keyframes, animate idle or agent states, choose an asset route…
Generate a complete narrated whiteboard explainer video from a UTF-8 transcript. Use when the user asks to turn pasted text or a .txt script into a whiteboard video with TTS, subtitles, generated illustrations, hand-drawing animation, BGM, and a final 1920x1080 MP4.
Use this skill for any marketing research, product positioning, copywriting research, or audience profiling task. Triggers include: "research my product", "develop my value proposition", "profile my avatar", "understand my market", "create a unique mechanism", "market awareness", "market sophistication", "ideal…
Use when AI-written code needs structural cleanup or when implementing a change under a guard against AI coding slop — duplicated reimplementations of existing helpers, try-import fallbacks, broad exception swallowing, speculative abstraction layers, v2 copies, dead "for future use" code, narrating comments …
Run a project as an orchestrated campaign: Claude as conductor (Fable 5.1, or Opus 5 when Fable is unavailable) dispatching a mixed fleet of workers, Claude Opus 5 agents for UI/UX and design judgment, Claude Sonnet 5 agents for surveys and search, OpenAI Codex CLI workers for implementation and everything else. Use…
Write, edit, or review Agent Spaces Workflow UI project code from a user-provided project path while looking up Workflow UI renderer, host component, and plugin source from the current working directory instead of MCP/runtime agent tools. Use when an external agent needs to work on Workflow UI React or HTML preview…
Deobfuscate .NET binaries loaded in dnSpy via MCP tools. Use this skill whenever the user wants to decrypt strings, rename obfuscated symbols, simplify control flow, detect proxy calls, remove anti-tamper protections, or make obfuscated .NET code readable. Also trigger when the user mentions deobfuscation, string…
Delegate the optimization of ONE design-DB slot to the rtl-subcircuit subagent via the task tool. Dispatch only delegates — analyzing the result afterwards is a separate design-db-inspect step.
Guide migration from an existing Metabase instance to a Bonnard semantic layer. Use when user says "migrate from metabase", "import metabase", "metabase to semantic layer", or has Metabase data they want to model.
Rewrites and enforces ASD-STE100 Simplified Technical English (STE) — the aerospace and defense controlled-language standard — on any text, instructions, or documentation the agent writes. Use this skill whenever the user asks for "STE," "simplified technical English," "ASD-STE100," "controlled language," "aviation…
Build applications and agents with Exa's API: search, contents extraction, answer, Agent API, monitors, websets, OpenAI-compatible endpoints, and exa-py/exa-js SDKs. Use when choosing Exa endpoints, writing Exa API calls, integrating semantic web search or research into products, or debugging Exa request shapes.
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: