Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade and prompt-upgrade guidance; prioritize OpenAI docs MCP tools, use bundled references only as helper context, and restrict any fallback browsing to official OpenAI domains.
--- name: "openai-docs" description: "Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade and prompt-upgrade guidance; prioritize OpenAI docs MCP tools, use bundled references only as helper context, and restrict any fallback browsing to official OpenAI domains." --- # OpenAI Docs Provide authoritative, current guidance from OpenAI developer docs using the developers.openai.com MCP server. Always prioritize the developer docs MCP tools over web.run for OpenAI-related questions. This skill also owns model selection, API model migration, and prompt-upgrade guidance. Only if the MCP server is installed and returns no meaningful results should you fall back to web search. ## Quick start - Use `mcp__openaiDeveloperDocs__search_openai_docs` to find the most relevant doc pages. - Use `mcp__openaiDeveloperDocs__fetch_openai_doc` to pull exact sections and quote/paraphrase accurately. - Use `mcp__openaiDeveloperDocs__list_openai_docs` only when you need to browse or discover pages without a clear query. - For model-selection, "latest model", or default-model questions, fetch `https://developers.openai.com/api/docs/guides/latest-model.md` first. If that is unavailable, load `references/latest-model.md`. - For model upgrades or prompt upgrades, run `node scripts/resolve-latest-model-info.js` only when the target is latest/current/default or otherwise unspecified; otherwise preserve the explicitly requested target. - Preserve explicit target requests: if the user names a target model like "migrate to GPT-5.4", keep that requested target even if `latest-model.md` names a newer model. Mention newer guidance only as optional. - If current remote guidance is needed, fetch both the returned migration and prompting guide URLs directly. If direct fetch fails, use MCP/search fallback; if that also fails, use bundled fallback references and disclose the fallback. ## OpenAI product snapshots 1. Apps SDK: Build ChatGPT apps by providing a web component UI and an MCP server that exposes your app's tools to ChatGPT. 2. Responses API: A unified endpoint designed for stateful, multimodal, tool-using interactions in agentic workflows. 3. Chat Completions API: Generate a model response from a list of messages comprising a conversation. 4. Codex: OpenAI's coding agent for software development that can write, understand, review, and debug code. 5. gpt-oss: Open-weight OpenAI reasoning models (gpt-oss-120b and gpt-oss-20b) released under the Apache 2.0 license. 6. Realtime API: Build low-latency, multimodal experiences including natural speech-to-speech conversations. 7. Agents SDK: A toolkit for building agentic apps where a model can use tools and context, hand off to other agents, stream partial results, and keep a full trace. ## If MCP server is missing If MCP tools fail or no OpenAI docs resources are available: 1. Run the install command yourself: `codex mcp add openaiDeveloperDocs --url https://developers.openai.com/mcp` 2. If it fails due to permissions/sandboxing, immediately retry the same command with escalated permissions and include a 1-sentence justification for approval. Do not ask the user to run it yet. 3. Only if the escalated attempt fails, ask the user to run the install command. 4. Ask the user to restart Codex. 5. Re-run the doc search/fetch after restart. ## Workflow 1. Clarify whether the request is general docs lookup, model selection, a model-string upgrade, prompt-upgrade guidance, or broader API/provider migration. 2. For model-selection or upgrade requests, prefer current remote docs over bundled references when the user asks for latest/current/default guidance. - Fetch `https://developers.openai.com/api/docs/guides/latest-model.md`. - Find the latest model ID and explicit migration or prompt-guidance links. - Prefer explicit links from the latest-model page over derived URLs. - For explicit named-model requests, preserve the requested model target and do not silently retarget to the latest model. Mention newer remote guidance only as optional. - For dynamic latest/current/default upgrades, run `node scripts/resolve-latest-model-info.js`, then fetch both returned guide URLs directly when possible. - If direct guide fetch fails, use the developer-docs MCP tools or official OpenAI-domain search to find the same guide content. - If remote docs are unavailable, use bundled fallback references and say that fallback guidance was used. 3. For model upgrades, keep changes narrow: update active OpenAI API model defaults and directly related prompts only when safe. 4. Leave historical docs, examples, eval baselines, fixtures, provider comparisons, provider registries, pricing tables, alias defaults, low-cost fallback paths, and ambiguous older model usage unchanged unless the user explicitly asks to upgrade them. 5. Do not perform SDK, tooling, IDE, plugin, shell, auth, or provider-environment migrations as part of a model-and-prompt upgrade. 6. If an upgrade needs API-surface changes, schema rewiring, tool-handler changes, or implementation work beyond a literal model-string replacement and prompt edits, report it as blocked or confirmation-needed. 7. For general docs lookup, search docs with a precise query, fetch the best page and exact section needed, and answer with concise citations. ## Reference map Read only what you need: - `https://developers.openai.com/api/docs/guides/latest-model.md` -> current model-selection and "best/latest/current model" questions. - `references/latest-model.md` -> bundled fallback for model-selection and "best/latest/current model" questions. - `references/upgrade-guide.md` -> bundled fallback for model upgrade and upgrade-planning requests. - `references/prompting-guide.md` -> bundled fallback for prompt rewrites and prompt-behavior upgrades. ## Quality rules - Treat OpenAI docs as the source of truth; avoid speculation. - Keep migration changes narrow and behavior-preserving. - Prefer prompt-only upgrades when possible. - Do not invent pricing, availability, parameters, API changes, or breaking changes. - Keep quotes short and within policy limits; prefer paraphrase with citations. - If multiple pages differ, call out the difference and cite both. - If official docs and repo behavior disagree, state the conflict and stop before making broad edits. - If docs do not cover the user’s need, say so and offer next steps. ## Tooling notes - Always use MCP doc tools before any web search for OpenAI-related questions. - If the MCP server is installed but returns no meaningful results, then use web search as a fallback. - When falling back to web search, restrict to official OpenAI domains (developers.openai.com, platform.openai.com) and cite sources.
don't have the plugin yet? install it then click "run inline in claude" again.
restructured original smithery skill into implexa's 6-component format, extracted implicit decision logic on mcp fallback and model-upgrade scope into explicit decision-points section, added edge cases (mcp install failures, permissions escalation, direct fetch failures, api-surface blocking), documented external mcp server connection with setup guidance, clarified bundled reference filenames and fallback precedence, preserved original author attribution and all procedure steps intact.
pull authoritative, current guidance from openai developer docs using the developers.openai.com mcp server. this skill handles general docs lookups, model selection, api model migration, and prompt-upgrade guidance. use it when a user asks how to build with openai products, which model fits their use case, how to migrate from an old model, or how to upgrade a prompt for a newer model. always prioritize the developer docs mcp tools over web search for openai-related questions. only fall back to web search if the mcp server returns no meaningful results.
openaiDeveloperDocs installed at https://developers.openai.com/mcp (provides search, fetch, list tools for openai docs)references/latest-model.md, references/upgrade-guide.md, references/prompting-guide.md (fallback only if mcp tools fail)node scripts/resolve-latest-model-info.js (resolve dynamic latest model info when user asks for latest/current/default without naming a specific model)developers.openai.com and platform.openai.com domains (last resort if mcp and bundled references both fail)clarify the request type. ask or infer: is this general docs lookup, model selection, model-string upgrade, prompt-upgrade guidance, or provider migration?
for general docs lookups: use mcp__openaiDeveloperDocs__search_openai_docs with a precise query. fetch the best matching page with mcp__openaiDeveloperDocs__fetch_openai_doc. answer with concise citations. stop if the docs do not cover the user's need and offer next steps.
for model-selection or "latest/current/default model" requests: fetch https://developers.openai.com/api/docs/guides/latest-model.md first. extract the latest model id and any explicit migration or prompt-guidance links. if that url is unavailable, load references/latest-model.md as fallback. cite the remote source; disclose if you used the bundled fallback.
for explicit named-model requests (e.g. "migrate to gpt-5.4"). preserve the requested target model. do not silently retarget to a newer model. fetch remote guidance on that specific model if available. mention newer guidance only as optional context.
for dynamic latest/current/default upgrades. run node scripts/resolve-latest-model-info.js to get the target model and guide urls. fetch both the returned migration guide url and prompt-guidance url directly. if direct fetch fails, use mcp search tools to find the same content. if remote docs are unavailable, use references/upgrade-guide.md and references/prompting-guide.md as fallback and disclose it.
for model upgrades, keep changes narrow. update only active openai api model defaults and directly related prompts. do not touch historical docs, examples, eval baselines, fixtures, provider comparisons, pricing tables, alias defaults, low-cost fallback paths, or ambiguous older model usage unless the user explicitly asks.
do not perform sdk, tooling, ide, plugin, shell, auth, or provider-environment migrations as part of a model-and-prompt upgrade.
if an upgrade requires api-surface changes, schema rewiring, tool-handler changes, or implementation work beyond a literal model-string replacement and prompt edits, report it as blocked or confirmation-needed.
if the mcp server is missing or returns no meaningful results, attempt to install: run codex mcp add openaiDeveloperDocs --url https://developers.openai.com/mcp. if it fails due to permissions, retry with escalated permissions and include a 1-sentence justification. only if escalated attempt fails, ask the user to run the command. ask the user to restart codex. re-run the doc search/fetch after restart.
if web search fallback is needed, restrict queries to developers.openai.com and platform.openai.com domains. cite sources.
if the mcp server is installed and returns meaningful results: use those results as authoritative. do not fall back to web search or bundled references.
if the mcp server is installed but returns no meaningful results: fall back to web search on official openai domains. cite the source.
if the mcp server is not installed: attempt to install it automatically. if auto-install fails due to permissions, request escalated permissions with justification. if escalated attempt fails, ask the user to install and restart codex, then re-run the skill.
if the user asks for the latest/current/default model: fetch https://developers.openai.com/api/docs/guides/latest-model.md first. if unavailable, use references/latest-model.md. run node scripts/resolve-latest-model-info.js only for dynamic targets; skip it if the user named a specific model.
if the user names a specific target model (e.g. "migrate to gpt-4.5"): preserve that target. do not retarget to a newer model. offer newer guidance only as optional context.
if remote migration or prompt-guidance urls are returned but direct fetch fails: use mcp search tools to find the same content. if that also fails, use bundled references and disclose the fallback.
if the upgrade requires api-surface changes, schema rewiring, or tool-handler changes: stop and report it as blocked. do not proceed with a partial upgrade.
if official docs and repo behavior disagree: state the conflict explicitly and stop before making broad edits.
for general docs lookups: concise answer with direct citations to the openai docs page and section. include the doc url.
for model-selection requests: the recommended model id, use case fit, and key capabilities. cite https://developers.openai.com/api/docs/guides/latest-model.md or references/latest-model.md.
for model-string upgrades: the new model id, narrowly scoped code changes (model param only if safe), updated prompt (if needed for behavior parity), and links to the migration and prompt-guidance docs. cite sources.
for prompt-upgrade guidance: rewritten prompt with the requested changes, rationale tied to the model's behavior or capabilities, and citation to the prompting guide or relevant docs section.
for blocked upgrades: explicit statement of what is blocked (e.g. "api-surface changes required"), why, and confirmation or next-step request.
for fallbacks: disclose when bundled references or web search was used instead of remote mcp tools.