binance-agentic-wallet
Use when the user mentions connect/disconnect wallet, sign in, sign out, web3 wallet, wallet address, check balance, how much crypto do I have, send…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-09 00:13
Agents & models
25,956 results
consulting-experts
Assembles the experts any goal needs — research, verification, analysis of a design or prototype, a UI prototype, or anything else. Declares the goal, the…
recap
Summarise what happened in this session so far. Use when switching between Claude sessions or returning after a break.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's…
asu-discover
Semantic search across 760+ ASU GitHub repositories via RAG. Use for finding code patterns, integrations, SDKs, and ASU-specific conventions. Domains:…
pi-team
tmux-based multi-agent orchestration using pi-team CLI. Spawn multiple AI agents (PI, Claude, Codex, Gemini) in parallel tmux sessions. USE FOR: parallel…
all-subagents
Use when the user asks to work through subagents or hand work to another coding agent or model, including "work with subagents", "run it using subagents", "assign this task to Codex",…
machiavelli
Read a real business situation for power and leverage, then hand back the play and the message to send. Use when the hard part is positioning rather than…
clean-web-markdown
Retrieve clean markdown from webpages for AI agents using protocol-level content negotiation and crawl-to-markdown fallbacks. Use when users ask to…
cherry-browser
Control the user's visible Agent browser: navigate, click, type, screenshot, debug. Needs the Browser setting.
skill-creator
Create, edit, evaluate, and optimize skills, including benchmarking and description tuning for better triggering.
skills-manager
Search, install, and create Claude Code Agent Skills. Triggered when the user wants to search for skills, install tools, create a custom Skill, or says "find a skill", "搜索技能", "帮我做个 skill", "create a skill". Also applies to scenarios where the user says "is there a tool for doing X", "I want to extend the Agent's capabilities".
orca-handoff
Perform a full ownership handoff to another agent through Orca. Defines the handoff contract and task brief, then routes workspace and terminal mechanics to…
implementing-wpf-dragdrop
Implements WPF drag and drop functionality using DragDrop.DoDragDrop, DataObject, and drag/drop events. Use when building file drop zones, list reordering, or…
update-sourced-skills
Update this repository's sourced skills from their originals while preserving documented local adaptations.
skill-optimizer
Review and optimize the trigger semantics, workflow, confirmation thresholds, resource organization, security boundaries, and documentation layering of an existing skill. Use when the user mentions "optimize skill", "check skill quality", "improve a skill", "refactor skill description", or explicitly states which aspects to optimize. By default, review first and give a plan; only implement after the user explicitly confirms to start modifying.
volcengine-ai-misc-model-discovery
Discover and route Volcengine AI model capabilities. Use when users ask which model to use, need endpoint capability checks, or require model selection…
volcengine-ai-video-generation
AI video generation workflow on Volcengine. Use when users need text-to-video, image-to-video, generation parameter tuning, or async task troubleshooting for…
mcp-security-scan
Scans MCP servers, tools, prompts, and resources for security vulnerabilities using YARA rules, LLM analysis, and Cisco AI Defense API. Use this skill when the…
add-trainer-model
Add a new trainable base model to BOTH trainers end-to-end — the in-app trainer (main Next.js app, src/) and the Training Studio (apps/training-studio).…
moltbook
Interact with Moltbook (the AI agent social network) — post, browse, comment, vote, search — via shell curl.
reflect
Review a work session, transcript, or tool-call log and compound the learnings into durable improvements: agent rules (AGENTS.md/CLAUDE.md), new or updated…
reflect-feedback
Audit whether past reflect improvements are actually working. Reads the .reflect/applied.md ledger and checks each applied rule, skill, command, or script for…
reflect-memory
Lifecycle maintenance for accumulated agent memory: dedupe, merge, expire, and resolve contradictions across AGENTS.md/CLAUDE.md agent rules, .reflect/ state,…