prompt-enhance
Enhance and improve existing AI prompts using professional techniques from a 2,500+ prompt database. Adds detail, fixes structure, optimizes for specific…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-04 00:13
Agents & models
25,605 results
agent-browser
Browser automation for web testing, screenshots, data extraction. Use when: navigating websites, filling forms, testing web apps. Triggers on: 'open browser',…
ai-llm-app-attack
AI/LLM application attacks: prompt injection, Agent tool abuse RCE, RAG poisoning, MCP supply chain, torch.load pickle RCE. Use when testing LLM apps, agents, RAG, MCP plugins, or AI model file risks.
langgraph-workflow
Design and implement stateful multi-agent workflows using LangGraph StateGraph. Use when building production AI pipelines that need checkpointing, conditional…
insights-zh
Translate or generate the Chinese insights report for Claude Code. Automatically triggered when the user says any of the following: - "translate insights", "translate report", "Chinese version insights" - "/insights-zh", "generate Chinese report", "insights Chinese translation" - "translate insights…
raison-sdk
Raison JavaScript/TypeScript prompt management SDK. Use when working with the `raison` npm package to render templates or query prompt data.
retro-copilot
Run a retro for personal global ~/.copilot assets and turn incident learnings into updates for copilot-instructions, instructions, skills, agents, and hooks.…
langfuse-traces
Query Langfuse traces for debugging LLM calls, analyzing token usage, and investigating workflow executions. Use when debugging AI/LLM behavior, checking trace…
second-opinion
Consult peer LLM for alternative perspectives when you need second opinion, peer review, or fresh take on technical decisions; useful for validating approaches…
alibabacloud-dataworks-data-agent
Interact with DataWorks Data Agent for conversational data analysis, session lifecycle management, and artifact download. Use this Skill when users want to…
alibabacloud-mcp-connector
Operate, run O&M for, and manage Alibaba Cloud through local commands, with no MCP configuration needed. CallCLI runs Alibaba Cloud CLI/API commands to create,…
credit-industry-analysis
Due Diligence Report - Credit Industry In-Depth Analysis Skill. Conduct systematic research on a specific industry, applying classic frameworks such as PEST macroeconomic environment analysis, Porter's Five Forces competitive model, and industry chain value chain decomposition, to comprehensively portray the industry's current state from multiple dimensions including market size estimation (TAM/SAM/SOM), competitive landscape evolution, supply-demand balance projection, policy environment review, and technology trend assessment, and use scenario analysis to provide forward-looking projections of the industry's short-, medium-, and long-term development trends, providing support for credit decisions and industry...
asta artifacts
Use this skill when the user asks to view, export, or open agent output artifacts — "show me the artifacts", "export the results", "open the report", "convert…
weave-integration
Add W&B Weave observability and LLM tracing to any project. Use when instrumenting LLM calls for token visibility, latency tracking, cost analysis, or…
analyze-ai-topics
Analyzes what users ask AI agents about and how well each topic is served. Only use when the user has Amplitude Agent Analytics instrumented in their project.…
mixture-of-experts
Run a Mixture of Experts (MoE) audit on any topic, plan, codebase, evidence archive, or process. Dynamically spawns specialized subagents with different…
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
plugin-authoring
Make a mod: a live pane, band, status line, toast or hook inside Claude Code (terminal or desktop Code tab), written as a plugin of function hooks that…
plan-run
Advance the implementation according to plan.md's Dependencies DAG — the order and dependencies are determined by the state file, and the default continuation force is provided by the built-in /goal (zero install); for long plans spanning sessions, you can instead attach a Stop hook. Triggers: the user asks to advance according to the plan, continue across sessions, or complains that the LLM skips or misses steps.
verify-evidence-loop
Iterative evidence verification subagent architecture — a convergence loop that runs 4 dimensions (academic / industry standards / best practices / community + dissenting opinions) × up to 3 iterations × dual independent reviewer on technical claims, outputting a structured verdict. Difference from evidence-check: the latter is...
setup-xhs-mcp
Install and deploy the xiaohongshu-mcp service and configure the MCP connection, guiding the user through the complete process from scratch to a usable state. Use when the user uses Xiaohongshu features for the first time, mentions installing/deploying/configuring Xiaohongshu, environment setup, MCP service connection failure, or when MCP tools such as check_login_status are unavailable.
codex-agent-setup
Explicit-only installer for the Gemskills Lisa Codex custom agent. Use ONLY when the user explicitly asks to install, update, check, uninstall, or set up the…
bankr-communities
Bankr Space ↔ bankr.bot/agents two-way sync (BANKR-PROJECT-SYNC.md Paths B+C). Original tweets from GET /agent-profiles/:id/tweets shown on Spaces. Holder…
skill-creator
Create new Claude Agent Skills. Use when asked to create, build, or develop a skill.