mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-03 00:11
Agents & models
25,529 results
proactive-agent
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer,…
qwen-enhance
Enhance the adaptation capabilities of the Tongyi Qianwen (Qwen) model, especially Qwen-VL multimodal input formatting. Use when handling visual tasks.
skill-vetter
Security vetting protocol before installing any AI agent skill. Red flag detection for credential theft, obfuscated code, exfiltration. Risk classification…
claude-code
Activate when users ask about Claude Code installation, slash commands (/cook, /plan, /fix, /test, /docs, /design, /git), creating/managing Agent Skills,…
sentiment-analyst
Crypto market sentiment and positioning analysis. Use this skill whenever the user asks about market mood, trader positioning, leverage, or crowd behavior.…
heretic-abliteration
Heretic — fully automatic LLM censorship removal (abliteration) and serving the result via Ollama. Wraps p-e-w/heretic: directional ablation…
agent-builder
Creates and configures Claude Code agent files (.claude/agents/*.md) with YAML frontmatter, tool permissions, model selection, and system prompt structure. Use…
hooks-builder
Creates and configures Claude Code hooks for lifecycle automation. Use when implementing PreToolUse validation, PostToolUse formatting, PermissionRequest…
writing-a-good-claude-md
Write, review, audit, or improve CLAUDE.md (or AGENTS.md) files for Claude Code and other AI coding agent harnesses (OpenCode, Zed, Cursor, Codex). Use this…
byted-contextsearch-operator
Manages Volcano Engine ContextSearch control-plane and application-console operations. Use for ContextSearch scene, AgenticSearch, data source, indexer,…
byted-vms-configure
Volcengine Cloud Communication "General Configuration" Skill (general layer). Only responsible for cross-business number callability / risk control / caller authentication queries QueryRiskDenyInfo / QueryCanCall / QueryAuth. Note: all TTS template operations (create/update/delete/query) as well as recording files / general resource management (create_voice /…
agent-skills-best-practices
Agent-skill design conventions for focused scope, precise discovery, and progressive disclosure. Use when creating, restructuring, or reviewing…
vault-guide
Interactive onboarding agent for content marketing associate candidates and vault orientation for Charlie. Walks candidates through the OpenEd content system,…
prompt-engineering
Universal prompt engineering techniques for any LLM. Use when crafting, optimizing, or reviewing prompts for AI models. Triggers on requests like "improve this…
web-browser
Browse the web using agent-browser CLI with Lightpanda engine. Read pages, extract content, interact with elements.
grill-me
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to…
task-plan
Decompose input into a structured task backlog for automated agent loops. Use when asked to "create a task plan", "break this into tasks", "decompose this…
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…
uunet
Engineer at global scale in the style of UUNET (now Verizon Business). Emphasizes massive infrastructure resilience, "plumbing" the internet, pragmatic problem…
corrinehu-kimi-usebrowser
Browser automation troubleshooting and best practices for Kimi CLI using agent-browser. Use when encountering issues with browser automation, timeouts,…
loom-prompt-engineering
Designs and optimizes prompts for large language models including system prompts, agent signals, and few-shot examples. Use for instruction design, prompt…
fact-check
Multi-model fact-checking within Claude. Opus checks on its own, has a Sonnet subagent perform an independent check, and compares/discusses the results from both to output a consensus report.
quad-fact-check
Claude + Gemini + Codex 4-way cross-fact-check. Four parties—Opus itself, Gemini Flash, Gemini Pro, and Codex (gpt-5.3-codex)—independently check → extract points of contention → discuss → output a consensus report.