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.
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
Verify an existing implementation, fix, migration, deployment, runtime behavior, compatibility boundary, or other technical claim by mapping atomic claims to direct, fresh, reproducible primary signals and returning scoped PROVEN, PARTIAL, UNPROVEN, or CONTRADICTED verdicts with a compact proof capsule. Use when the…
Implements a reviewed plan: task breakdown, TDD sub-agents, code review, and a verification report. Use to build or execute a plan under specs/plans/, after /speq-plan and before /speq-record. Arg: plan-name.
Diagnose slow, expensive, or regressed Apache Spark and PySpark applications by comparing runtime evidence against a healthy run. Use for long stages, stragglers, skew, shuffle, spill, garbage collection, poor parallelism, small files, slow scans, scheduler delay, executor imbalance, and unexplained compute-cost…
Jira issue management skill for OpenClaw using the jirac CLI. Requires the jirac binary to be installed and authenticated before use. Use when listing, viewing, creating, updating, transitioning, commenting on, attaching files to, bulk-editing, cloning, deleting, linking, archiving, moving, changing types of Jira…
A role-based guide for analyzing AI technology and safety questions from the perspective of Ilya Sutskever, based on public material. It defines how to research factual claims, reason about decisions, and express uncertainty.
Structured Chain-of-Thought (CoT) & Deep Reasoning Protocol for complex problem analysis, architectural decisions, security evaluations, and deep troubleshooting. Activate when --deep or --cot flag is present in workflows, or when deep architectural reasoning is required. Supports MCP Graph integration for…
A visual design guide for teaching websites and content-focused single-page apps. It defines choices such as colours, fonts, spacing, cards, badges, hero sections, and dark mode.
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…
Analyzes Remotion compositions for performance issues and provides optimization recommendations. Identifies expensive computations, unnecessary re-renders, large assets, memoization opportunities, and architecture improvements. Use when optimizing render times or when asked to "improve performance", "speed up…
Plan, build, review, and debug React Three Fiber, Three.js, WebGL/WebGPU, shader, XR, asset-pipeline, physics, game, and creative 3D web app work using the R3ARXIV agent catalog plus absorbed R3F/Three.js skill patterns. Use when the task mentions @react-three/fiber, R3F, Drei, Three.js, WebGL, WebGPU, GLSL, shaders…
A Blender animation guide for changing objects, cameras, lights, and other properties over time. It covers keyframes, motion curves, shape keys for morphs, drivers, and reusable animation actions.
Drive the STAR workflow toward the goal an explicitly invoked $star-auto request states, starting each next skill itself under that invocation's grant. Do not use unless the user typed $star-auto.
NocoBase 2 only; never use in a NocoBase 3 project. INTERNAL CONTINUATION ONLY. Never select this skill from a raw user UI request. Use it only after nocobase-portal-manage has already resolved exactly one enabled Portal and confirmed portalType=no-code, or has proved the runtime has capabilities.multiPortal ===…
A process for turning selected parts of a spoken script into vertical, paper-collage-style information animations. It covers choosing suitable sections, making still preview frames, and producing a 1080×1920 video with sound effects after user approval at each stage.
Use when debugging a cubepi/cubebox agent run — a missing final reply, a tool that misbehaved, a 4xx from the model, wrong token/cache numbers, or "why did the agent do that?". Reads the JSONL traces cubepi writes per run via the cubepi trace CLI (ls / view / follow / stats) to inspect the span tree, errors, tool…
Operate a local ProxyPin workflow for iPhone or Android capture, MCP request analysis, authorized personal-data export, and Mock rule management. Use when the user mentions ProxyPin, mobile HTTPS capture, ProxyPin MCP, captured API discovery, HAR-like export, or ProxyPin Mock collections.
Guides the agent through installing, configuring, and using Capacitor plugins from six sources — official Capacitor plugins, Capawesome plugins, Capacitor Community plugins, Capacitor Firebase plugins, Capacitor MLKit plugins, and RevenueCat plugins. Covers installation, platform-specific configuration (Android and…
A writing-style tool that extracts a person's writing patterns and reuses them when drafting or rewriting Chinese text. It can also help create a reusable profile of that style and remove common AI-sounding phrases.
A Metabase AI-readiness coach, covering the data groundwork that makes AI answers trustworthy: modeling with Transforms, table and field metadata, the Glossary, saved Metrics, and marking canonical content. Use this skill whenever the user wants to check if their data is ready for AI, prep the underlying data for…
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: