openai-docs-skill
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.
73
89%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly communicates what the skill does (queries OpenAI documentation via an MCP server using CLI tools), when to use it (explicit 'Use whenever' clause with extensive trigger terms), and occupies a distinct niche. The description is concise yet comprehensive, with excellent trigger term coverage spanning APIs, SDKs, and common developer concerns like migrations and limits.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions and domains: querying OpenAI docs via MCP server using CLI (curl/jq), and enumerates specific APIs (Responses, Chat Completions, Realtime), SDKs, endpoint schemas, parameters, limits, and migrations. | 3 / 3 |
Completeness | Clearly answers both 'what' (query OpenAI developer documentation via MCP server using CLI) and 'when' (explicit 'Use whenever a task involves...' clause with comprehensive trigger conditions). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'OpenAI API', 'Chat Completions', 'Realtime', 'OpenAI SDKs', 'ChatGPT Apps SDK', 'Codex', 'MCP integrations', 'endpoint schemas', 'parameters', 'limits', 'migrations'. These are terms developers naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — specifically targets OpenAI documentation querying via a specific MCP server. The combination of OpenAI docs, MCP server, and CLI tools (curl/jq) creates a clear niche unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
79%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, concise skill that provides clear, actionable guidance for querying OpenAI docs via an MCP server CLI wrapper. Its main strengths are token efficiency and concrete executable examples. The primary weaknesses are the lack of error handling/validation in the workflow and the missing bundle script file that the skill depends on.
Suggestions
Add error handling guidance to the workflow: what to do if search returns no results, if fetch fails, or if the MCP server is unreachable.
Include the referenced `scripts/openai-docs-mcp.sh` script in the bundle so the skill is self-contained and the reference can be verified.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It assumes Claude knows what OpenAI APIs are, doesn't explain basic concepts, and every section serves a clear purpose. No unnecessary padding or explanations of things Claude already knows. | 3 / 3 |
Actionability | Provides concrete, executable bash commands for searching and fetching docs. The subcommand reference with exact syntax (arguments, optional params) is copy-paste ready. The workflow steps are specific and tied to concrete actions. | 3 / 3 |
Workflow Clarity | The 3-step workflow (Discover → Read → Apply) is clear and well-sequenced, but lacks validation checkpoints. There's no guidance on what to do if a search returns no results, if a fetch fails, or how to verify the fetched content is current/relevant. For a tool-invocation workflow, error handling guidance would improve this. | 2 / 3 |
Progressive Disclosure | The content references `scripts/openai-docs-mcp.sh` but no bundle files are provided, so we can't verify the script exists or its contents. The skill is well-organized with clear sections, but the script reference section contains inline detail that could potentially live in the script's own documentation. For a skill of this size (~40 lines), the structure is adequate but the missing bundle file is a concern. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- am-will/codex-skills
- Commit
d3983b1
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.