技能详情（站内镜像，无评论）
许可证：MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本：v1.0.0
统计：⭐ 1 · 1.9k · 10 current installs · 10 all-time installs
⭐ 1
安装量（当前） 10
🛡 VirusTotal ：良性 · OpenClaw ：良性
Package：am-will/openai-docs
安全扫描（ClawHub）
- VirusTotal ：良性
- OpenClaw ：良性
OpenClaw 评估
The skill's code and instructions match the stated purpose (querying the OpenAI docs via an MCP server); it requests no secrets and has no install steps, though there are small metadata inconsistencies you should note before use.
目的
The name/description, SKILL.md, and the included script all implement the same capability: searching and fetching OpenAI developer docs via an MCP server. No unrelated services, credentials, or excessive capabilities are requested.
说明范围
The runtime instructions are narrowly scoped to search/list/fetch docs via the provided CLI script. However, the script invokes curl and jq (and checks for them at runtime); the registry metadata listed no required binaries, which is a minor mismatch in the declared requirements.
安装机制
There is no install specification (instruction-only skill with a shipped script). Nothing is downloaded or executed from unknown remote URLs during install.
证书
The skill does not require credentials and only exposes an optional MCP_URL environment override. That is reasonable, but setting MCP_URL to an untrusted endpoint would redirect all queries (and their contents) to that server — users should only use the official endpoint or a trusted proxy.
持久
The skill does not request always:true, does not modify other skills, and does not persist credentials or alter system-wide settings. It runs only when invoked.
综合结论
This skill is coherent and appears to do what it says: it queries an OpenAI MCP docs endpoint and returns content. Before installing: (1) verify you trust the MCP endpoint (default: https://developers.openai.com/mcp); do not set MCP_URL to an untrusted server because your queries (which may include sensitive content) would be sent there; (2) ensure curl and jq are available on the agent host (the script will fail otherwise) — the registry meta…
安装（复制给龙虾 AI）
将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「OpenAI Developer Docs」。简介：Query the OpenAI developer documentation via the OpenAI Docs MCP server using C…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/am-will/openai-docs/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
---
name: openai-docs-skill
description: Query the OpenAI developer documentation via the OpenAI Docs MCP server using CLI (curl/jq). Use whenever a task involves the OpenAI API (Responses, Chat Completions, Realtime, etc.), OpenAI SDKs, ChatGPT Apps SDK, Codex, MCP integrations, endpoint schemas, parameters, limits, or migrations and you need up-to-date official guidance.
---
# OpenAI Docs MCP Skill
## Overview
Use the OpenAI developer documentation MCP server from the shell to search and fetch authoritative docs. Always do this for OpenAI platform work instead of relying on memory or non-official sources.
## Core rules
- Always use this skill for OpenAI API/SDK/Apps/Codex questions or when precise, current docs are required.
- Query the MCP server via the CLI wrapper in `scripts/openai-docs-mcp.sh` (do not rely on Codex MCP tools).
- Use `search` or `list` to find the best doc page, then `fetch` the page (or anchor) for exact text.
- Surface the doc URL you used in your response so sources are clear.
## Quick start
```bash
scripts/openai-docs-mcp.sh search "Responses API" 5
scripts/openai-docs-mcp.sh fetch https://platform.openai.com/docs/guides/migrate-to-responses
```
## Workflow
1. Discover: `search` with a focused query. If unsure, use `list` to browse.
2. Read: `fetch` the most relevant URL (optionally add an anchor).
3. Apply: summarize and/or quote relevant sections; include the URL.
## Script reference
The CLI wrapper is at `scripts/openai-docs-mcp.sh` and uses `curl` + `jq` against `https://developers.openai.com/mcp`.
Subcommands:
- `init`: initialize and inspect server capabilities.
- `tools`: list available tools on the MCP server.
- `search <query> [limit] [cursor]`: return JSON hits from the docs index.
- `list [limit] [cursor]`: browse docs index.
- `fetch <url> [anchor]`: return markdown for a doc page or section.
- `endpoints`: list OpenAPI endpoints.
- `openapi <endpoint-url> [lang1,lang2] [code-only]`: fetch OpenAPI schema or code samples.
Environment:
- `MCP_URL`: override the default MCP endpoint.