发现 tools llm ai 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
Automatically discover and recommend relevant Claude skills when users encounter tasks that could benefit from specialized capabilities. Use this skill proactively when detecting any of these patterns: (1) User...
使用AI驱动的浏览器自动化工具集，支持自然语言指令执行网页交互、数据提取、表单填写等任务。集成Amazon Bedrock AgentCore、Nova Act和Browser Use，提供实时浏览器视图和批量数据采集能力。
Full-text search and search engine implementation. Use when implementing search functionality, autocomplete, faceted search, relevance tuning, or working with search indexes. Keywords: search, full-text search,...
Designs and optimizes prompts for large language models including system prompts, agent signals, and few-shot examples. Covers instruction design, prompt security, chain-of-thought reasoning, and in-context lea...
Evaluates machine learning models for performance, fairness, and reliability using appropriate metrics and validation techniques. Trigger keywords: model evaluation, metrics, accuracy, precision, recall, F1, RO...
Designs RESTful APIs, GraphQL schemas, and RPC interfaces following best practices for consistency, usability, and scalability. Trigger keywords: api design, REST, RESTful, REST API, GraphQL, GraphQL schema, gR...
View and analyze Hawk evaluation results. Use when the user wants to see eval-set results, check evaluation status, list samples, view transcripts, or analyze agent behavior from a completed evaluation run.
This skill enables AI agents to generate new DHTI elixir projects from a cookiecutter template. Elixirs provide backend GenAI capabilities as HTTP endpoints hosted by LangServe. The skill guides the agent throu...
Provides a Model Context Protocol (MCP) server interface to the skills library, allowing any MCP-compliant agent (e.g. Claude Desktop) to invoke Antigravity skills as native tools.
Enables mid-stream course correction by monitoring a FEEDBACK.md file for user interventions. Allows the agent to incorporate new instructions without restarting the task.
Rapidly ingest documentation via the /llms.txt standard to gain "fast-track" understanding of libraries without scraping entire sites.
Prepares isolated sub-workspaces for parallel agent execution. Copies context and generates specific mission instructions for "Worker" agents.
Analyzes failures or user requests to automatically scaffold new skills, ensuring structural evolution.
Detects when the agent is stuck in a reasoning loop or unproductive state by analyzing tool usage and sentiment patterns.
Master Effect AI streaming response patterns including start/delta/end protocol, accumulation strategies, resource-safe consumption, and history management with SubscriptionRef.
Create and update ai-context.md files that document modules for AI assistants. Use when adding documentation for packages, apps, or external references that should be discoverable via /modules commands.
Build prompts for Effect AI using messages, parts, and composition operators. Covers the complete Prompt API for constructing, merging, and manipulating conversations with language models.
Configure and compose AI provider layers using @effect/ai packages. Covers Anthropic, OpenAI, OpenRouter, Google, and Amazon Bedrock providers with config management, model abstraction, and runtime overrides fo...
Orchestrate lawyer agents to review code for compliance with codebase laws. Spawns counsel in parallel to produce a unified legal brief.
Master the Effect AI LanguageModel service for text generation, structured output, streaming, and tool calling. Use when working with LLM interactions, schema-validated responses, or building conversational AI...
Define and implement AI tools using @effect/ai's Tool and Toolkit APIs. Use when building LLM integrations with type-safe tool definitions, parameter validation, and handler implementations. Covers user-defined...
Review code using GPT-5.2 Pro via Claude Code's Chrome integration. Use when the user asks to review code with ChatGPT, use their ChatGPT Pro subscription, get GPT-5.2 Pro to review code, or wants a second opin...
Manually write response back to Claude. Use if read-task did not auto-complete or to finalize response.
Read and execute task delegated from Claude. Use when user says read task, get task, or pick up claude task.
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。