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.

Quality

89%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

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, well-crafted skill description that clearly identifies what the skill does (queries OpenAI docs via MCP server), when to use it (any task involving OpenAI APIs, SDKs, or related topics), and includes rich trigger terms covering the breadth of OpenAI's ecosystem. The only minor note is the use of second person 'you need' in the trigger clause, but the primary voice is third person, so the impact is minimal.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions and domains: querying OpenAI docs via MCP server using CLI (curl/jq), and enumerates specific APIs (Responses, Chat Completions, Realtime), SDKs, ChatGPT Apps SDK, Codex, MCP integrations, endpoint schemas, parameters, limits, and migrations.	3 / 3
Completeness	Clearly answers both 'what' (query OpenAI developer documentation via MCP server using CLI) and 'when' ('Use whenever a task involves the OpenAI API... and you need up-to-date official guidance'), with explicit trigger conditions.	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms users would say: 'OpenAI API', 'Chat Completions', 'Realtime', 'OpenAI SDKs', 'ChatGPT', 'Codex', 'endpoint schemas', 'parameters', 'limits', 'migrations'. These are terms developers naturally use when seeking OpenAI documentation help.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive — specifically targets OpenAI documentation querying via a specific MCP server, with clear domain boundaries (OpenAI API, SDKs, Codex). Unlikely to conflict with other skills unless there's another OpenAI docs skill.	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-crafted, concise skill that provides actionable CLI commands and a clear subcommand reference. Its main weakness is the workflow section, which lacks error handling guidance and validation steps (e.g., what to do when search returns irrelevant results or fetch fails). The progressive disclosure is adequate for the content size but could benefit from separating the script reference.

Suggestions

Add error handling guidance to the workflow: what to do if search returns no/irrelevant results (refine query, try list), or if fetch fails (check URL, retry).

Consider adding a brief example of search output (even just a one-line JSON snippet) so Claude knows what to expect and how to pick the best result to fetch.

Dimension	Reasoning	Score
Conciseness	The content is lean and efficient. It assumes Claude knows what OpenAI APIs are, doesn't explain MCP concepts, and every section serves a clear purpose. No unnecessary padding or explanations of things Claude already knows.	3 / 3
Actionability	Provides concrete, copy-paste-ready bash commands for the core operations (search and fetch). The script reference section gives a complete subcommand listing with argument signatures, making it immediately usable.	3 / 3
Workflow Clarity	The 3-step workflow (Discover → Read → Apply) is clear and logically sequenced, but lacks validation checkpoints. There's no guidance on what to do if search returns no results, if fetch fails, or if the returned docs are outdated/incomplete — no feedback loop for error recovery.	2 / 3
Progressive Disclosure	The content is well-structured with clear sections (Overview, Core rules, Quick start, Workflow, Script reference), but the script reference is inlined rather than being in a separate file. For a skill of this size it's borderline acceptable, but the reference section could be split out for cleaner navigation.	2 / 3
	Total	10 / 12 Passed

Validation

100%

Warnings & errors only

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: ca2c3b3

Reviewed: 10 days ago

Table of Contents

Discovery Implementation Validation

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.