全部能力

Use when writing Roblox game scripts that handle player actions, currencies, stats, damage, or any RemoteEvent/RemoteFunction communication. Use when reviewing…

Guidance for creating, running, fixing, and promoting behavioral evaluations. Use when verifying agent decision logic, debugging failures, debugging prompt…

Integrate Lighthouse CI accessibility audits. Detects configuration, parses results, maps findings to severity model, and tracks score regressions.

Meta-agent for creating new custom agents, skills, and MCP integrations. Expert in agent design, MCP development, skill architecture, and rapid prototyping.…

Design and implement memory architectures for agent systems. Use when building agents that need to persist state across sessions, maintain entity consistency,…

Expert patterns for Godot 2D physics including collision layers/masks, Area2D triggers, raycasting, and PhysicsDirectSpaceState2D queries. Use when…

Deprecated. Best practices for creating high-quality, executable Dart CLI applications. Use the upstream `dart-build-cli-app` skill instead.

Appwrite Ruby SDK skill. Use when building server-side Ruby applications with Appwrite, including Rails and Sinatra integrations. Covers user management,…

Knowledge graph orchestration layer with entity extraction, natural language query parsing, deduplication (>85% similarity), and cross-reference boosting.…

Use when workflow components are inconsistent, naming conventions vary, or a new team member's work needs alignment to project standards.

Control macOS applications with Pi agents using semantic Accessibility API targets and optional screenshots

kwc-react-development — an installable skill for AI agents, published by kingdee/kwc-skills.

ERC-8004 on-chain agent identity management — register agent identities, update URI and metadata, manage operator approvals, set/unset agent wallet, transfer…

Write follow-up emails that re-engage without being annoying. Uses proven psychology for follow-up sequences. 42% of replies come from follow-ups.

Use when responding to touch or click interactions - button presses, drag feedback, swipe responses, tap ripples, or any direct manipulation animation.

Side role: recruit new agents to uncovered or underserved beats, earn +25 leaderboard points when they file their first signal (max 1/week)

Transcribes audio to text with timestamps and optional speaker identification. Use when you need to convert speech to text, create subtitles, transcribe…

Entry point to the Context Mate toolkit - skills, agents, and slash commands that work with Claude Code's natural flow. Project lifecycle (/explore-idea → /plan-project → /wrap-session), session handoff across context windows, developer agents for specialized tasks, and quality auditing. Use when: starting new projects, understanding the toolkit, needing workflow guidance. "It's all about the context, maaate!"

A guided, zero-friction installer and maintenance assistant for OpenClaw. Use this skill when the user wants to install OpenClaw, set up OpenClaw on a local machine or remote server, connect OpenClaw to DingTalk, get OpenClaw skill recommendations for their use case, or perform post-installation maintenance (health checks, troubleshooting, installing new skills, changing AI models, adding chat channels, updating OpenClaw). Handles full environment detection, installation, optional DingTalk integration, scene-based skill recommendations, and daily maintenance — all interactively, with no wasted steps.

Audit CSS for pseudo-element best practices and View Transitions API usage. Use when reviewing hover effects, decorative layers, or page transitions. Outputs…