Instructor
技能 已验证 活跃Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library
To reliably extract and validate structured data from LLM responses, simplifying complex data processing tasks and improving the accuracy of LLM outputs.
功能
- Extract structured data with Pydantic validation
- Automatic retries on extraction failures
- Parse complex JSON with type safety
- Stream partial results for real-time processing
- Support for multiple LLM providers (Anthropic, OpenAI, local models)
使用场景
- Reliably extracting entities, classifications, or complex objects from unstructured text.
- Ensuring LLM outputs conform to predefined schemas and data types.
- Building applications that require real-time processing of LLM-generated data through streaming.
- Integrating LLM-driven data extraction into existing Python applications with type safety.
非目标
- Performing LLM inference directly without structured output requirements.
- Replacing core LLM providers or their fundamental APIs.
- Handling complex multi-turn conversational logic beyond structured response generation.
Execution
- info:Pinned dependenciesWhile the SKILL.md lists dependencies, it does not explicitly mention a lockfile (e.g., `requirements.txt` or `Pipfile.lock`) for pinning specific versions, which could be an area for improvement.
安装
请先添加 Marketplace
/plugin marketplace add Orchestra-Research/AI-Research-SKILLs/plugin install AI-Research-SKILLs@ai-research-skills质量评分
已验证类似扩展
Instructor
75Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library
创建原子工具
99构建一个 `BaseTool[InSchema, OutSchema]` 子类 — 输入/输出模式，`BaseToolConfig`，`run()`（和可选的 `run_async()`），环境变量驱动的 secret，类型化的失败输出。当用户要求“添加工具”、“创建工具”、“将 API 包装成工具”、“构建 `BaseTool`”、“制作计算器/搜索/天气工具”或运行 `/atomic-agents:create-atomic-tool` 时使用。
Guidance
99Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework
Create Atomic Schema
98设计和编写 Atomic Agents 代理或工具的 `BaseIOSchema` 输入/输出对 — 文档字符串、字段描述、验证器、错误变体。当用户要求“创建 schema”、“设计输入/输出 schema”、“定义 `IOSchema`”、“编写 `BaseIOSchema`”、“建模代理的输出”或运行 `/atomic-agents:create-atomic-schema` 时使用。
Chatgpt Search
100Search ChatGPT and extract the full response + hydration JSON that powers the UI. Attaches to a running Chrome instance (port 9222 by default), opens ChatGPT, submits a query, waits for the streamed response, and returns structured data: messages, product cards, hydration JSON, and API calls. Use when asked to "search chatgpt", "ask chatgpt", "chatgpt search", "get chatgpt response", or "scrape chatgpt".
Website Extraction Api
100Extract typed JSON from public website pages using a schema.