llm-issue-discovery
Use this skill when a developer wants to find out what's going wrong with their LLM or AI system in production. Triggers on: "analyze my LLM logs", "find…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-04 00:13
Agents & models
25,593 results
llm-regression-runner
Use this skill when a developer wants to test a prompt change against a golden dataset and see what broke. Triggers on: "run my evals", "test this prompt…
chatgpt-use
Turn the user's ChatGPT web subscription (Plus/Pro) into a coding-agent backend — no API key, no Codex billing. Use when the user wants to delegate a question,…
effective-agent-skills
How to write effective agent skills — what to do, what not to do, anatomy, progressive disclosure, design patterns, anti-patterns, testing, security. Read this…
crm-customer-retention-agent
Develops segmentation, loyalty, repeat-purchase, churn-prevention, and win-back strategies.
skill-learning-patterns
Meta-skill for recognizing learnings, validating improvements, and contributing back to the collective knowledge base. Use when agents discover better…
deepsearch-service
An LLM-based deep iterative search and reasoning service. Skilled at handling complex questions, it automatically decomposes queries, performs multi-round iterative retrieval, evaluates and verifies information, and ultimately generates comprehensive and structured in-depth analysis reports.
search-guide
Search tool invocation decision guide. Clearly define when an Agent should invoke the search tool (such as real-time information, specific facts) and when it should rely on internal knowledge. As a reference specification, optimize the Agent's tool usage strategy.
run-claude
Send an assistance request to the assistant, suitable for scenarios that require executing complex programming tasks, task planning, or document writing in an isolated, independent environment.
run-codex
Send a request for assistance to the assistant, suitable for task scenarios such as code review, logical reasoning, scientific and philosophical thinking, in-depth analysis, strategy formulation, and market analysis.
lov-skill-add-case
Organize accepted results into official website cases; ordinary users can manually import after logging in, or an Agent can submit them, with no GitHub permissions required. Use when the user asks to add or publish an accepted Skill case.
lov-solution-architect
Create research-backed product and technical solution plans from a user's requirement. Use when the user asks for detailed feasibility analysis, technology…
anthropic-connector-submit
Prepare and submit an MCP server to Anthropic's Connectors Directory. Use this skill whenever the user wants to list their MCP server on Claude's connector…
mcp-vercel
Deploy a remote MCP server on Vercel with Next.js and mcp-handler. Use this skill whenever the user wants to create an MCP server, deploy MCP to Vercel, set up…
tmux-agent-comms
Manage AI agents in tmux: spawn sessions, send messages, wait, capture replies, inspect fleets, and tear down safely. Use for tmux-hosted CLI agents. Don't use…
learn
Extract cross-session patterns from git history, PRs, and handoffs, then recommend artifacts (skill/rule/hook/agent) based on frequency thresholds. Use when…
flowguard
Guard long, ambiguous, or stateful AI-agent work from drift. Use when the user asks to run or continue a multi-step task, autonomous loop, bug fix, repo…
xiaohongshu-netfeel-guardian
Use when users write content such as Xiaohongshu posts, WeChat official account articles, or video scripts with Claude, and the output has a translationese tone, English-style thinking, or Western frameworks, making it seem like "a foreigner pretending to write in Chinese." Typical trigger phrases: - "Claude's Xiaohongshu writing has too much translationese" "English-style thinking output is a disaster" - "Help me rewrite this note into pure Chinese internet feel" "Remove Claude's translationese" - "The WeChat official account article turned into English midway" "50...
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…
skill-creator
A guide for developing effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities through specialized knowledge, workflows, or tool integrations.
foundation-models
Apple's FoundationModels framework for on-device LLM integration in apps. Covers SystemLanguageModel availability checking, LanguageModelSession creation with…
mcp-skill
Use this skill when working with the mcp-skill CLI to create generated MCP app wrappers, list available generated apps, list functions for a specific app,…
unsloth
Guide for fine-tuning LLMs, embedding models, vision-language models, and TTS models efficiently with Unsloth. Covers LoRA/QLoRA SFT, reinforcement learning…
agent-browser
Headless browser automation CLI optimized for AI agents. Use when automating multi-step browser workflows, web scraping, form filling, or testing SPAs. Uses…