Agent skill · Backend & API

openai-docs

Access OpenAI developer documentation via Context7 MCP. Provides up-to-date docs for Codex CLI, OpenAI API, Python/Node SDKs, Agents SDK, and MCP configuration. Use when: (1) configuring Codex CLI or MCP servers, (2) writing OpenAI API integrations, (3) building agents with OpenAI SDKs, (4) troubleshooting Codex execution. Triggers: 'openai docs', 'codex documentation', 'openai api reference', 'codex mcp', 'agents sdk'.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill openai-docs-alfredolopez80-multi-agent-ralph-lo-2 --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 5 KB
Bundled scripts: none
Path: skills/ai-llm/openai-docs-alfredolopez80-multi-agent-ralph-lo-2/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

**ultrathink** - Take a deep breath. We're not here to write code. We're here to make a dent in the universe. ## The Vision Documentation lookups should feel inevitable and authoritative. ## Your Work, Step by Step 1. **Identify target**: Pick the right library and query. 2. **Resolve ID**: Use Context7 to get exact docs. 3. **Query precisely**: Ask for focused, answerable snippets. 4. **Apply results**: Convert docs into actionable guidance. ## Ultrathink Principles in Practice - **Think Different**: Seek the most direct source of truth. - **Obsess Over Details**: Use exact IDs and query wording. - **Plan Like Da Vinci**: Decide the lookup path before querying. - **Craft, Don't Code**: Keep results concise and relevant. - **Iterate Relentlessly**: Re-query when ambiguity remains. - **Simplify Ruthlessly**: Avoid unnecessary sources. # OpenAI Documentation Access Skill Access OpenAI's complete developer documentation through Context7 MCP integration. ## Quick Start ```yaml # Query Codex CLI documentation mcp__context7__query-docs: libraryId: "/websites/developers_openai_codex" query: "your question about Codex CLI" # Query OpenAI API documentation mcp__context7__query-docs: library

What's inside
Steps it walks through
  1. The Vision
  2. Your Work, Step by Step
  3. Ultrathink Principles in Practice
  4. Quick Start
  5. Available Documentation Libraries
  6. Common Queries
  7. Codex CLI Configuration
  8. OpenAI API Integration
  9. SDK Usage
  10. MCP Configuration Reference
  11. Context7 (Already Configured)
  12. Remote MCP Servers
  13. STDIO Servers
  14. Integration with Codex CLI Skill
Ships with 1 file
  • metadata.json
Commands it runs
Use mcp__context7__query-docs with libraryId="/websites/developers_openai_codex"
codex exec -m gpt-5.2-codex --full-auto "task"
More from claude-skill-registry
All skills →
About this skill
What does the openai-docs skill do?

Access OpenAI developer documentation via Context7 MCP. Provides up-to-date docs for Codex CLI, OpenAI API, Python/Node SDKs, Agents SDK, and MCP configuration. Use when: (1) configuring Codex CLI or MCP servers, (2) writing OpenAI API integrations, (3) building agents with OpenAI SDKs, (4) troubleshooting Codex execution. Triggers: 'openai docs', 'codex documentation', 'openai api reference', 'codex mcp', 'agents sdk'.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill openai-docs-alfredolopez80-multi-agent-ralph-lo-2 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going