skills.rest
jakubbartnik
jakubbartnikCOMMUNITY
Explore all skills by this author →
GitHub

openai-docs

Retrieves official OpenAI documentation for model selection, API migration, and prompt upgrades.

Updated Aug 19, 2026
Search Tags:#prompt engineering#mcp#openai#gpt-5#model selection#api documentation#model migration
One-click install
npx skills add https://github.com/jakubbartnik/honey-barrel-finale --skill openai-docs-jakubbartnik
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: openai-docs
Source: https://github.com/jakubbartnik/honey-barrel-finale/tree/main/honey-barrel-finale/workspace/openclaw-config/agents/main/agent/codex-home/skills/.system/openai-docs
Command: npx skills add https://github.com/jakubbartnik/honey-barrel-finale --skill openai-docs-jakubbartnik

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve? Developers building with OpenAI APIs often rely on outdated blog posts or stale training data when choosing models, migrating model strings, or rewriting prompts. This Skill grounds every answer in current official OpenAI documentation with citations, so guidance on models, APIs, and prompting stays accurate. ## Core Features & Use Cases - Authoritative docs lookup: Searches and fetches pages from the OpenAI Developer Docs MCP server, with fallback restricted to official OpenAI domains. - Model selection and migration: Resolves the latest recommended model, preserves explicitly requested target models, and applies narrow model-string plus prompt upgrades with a compatibility gate. - Prompt-upgrade guidance: Provides bundled prompting and upgrade references for rewriting prompts when moving to newer models like GPT-5.5. - Use Case: A developer asks to migrate an existing integration from GPT-5.4 to the latest model. The Skill resolves the current latest model, checks compatibility, updates only the model string and directly related prompts, and reports any blocked paths. ## Quick Start Ask the assistant to check the official OpenAI docs for the latest recommended model and migrate your current API integration to it.

Frequently Asked Questions about openai-docs

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I find the latest OpenAI model for my use case?▼

The Skill fetches the official latest-model guide from developers.openai.com and matches your use case to the recommended model ID. If remote docs are unavailable, it falls back to a bundled model map covering text, coding, image, audio, and embedding models.

How do I migrate an existing integration to a newer OpenAI model?▼

The Skill inventories current model usage, classifies the upgrade as model-string-only, model-string plus light prompt rewrite, or blocked, then applies the narrowest safe change. Explicitly requested target models are preserved rather than silently retargeted.

What happens if the OpenAI docs MCP server is not installed?▼

The Skill attempts to install the MCP server with the codex mcp add command, retrying with escalated permissions if needed. If installation fails, it falls back to web search restricted to official OpenAI domains and bundled reference files.

Does the upgrade change my API code or tool definitions?▼

No. Upgrades are limited to model-string replacements and directly related prompt edits. Changes requiring API-surface rewrites, tool rewiring, SDK migrations, or phase-handling code are reported as blocked rather than improvised.

How should prompts change when moving to GPT-5.5?▼

The bundled prompting guide recommends shorter outcome-oriented prompts with explicit success criteria, stopping conditions, retrieval budgets, and formatting rules. It advises removing legacy over-specified step-by-step instructions that narrow the model's search space.

Related Skills

Explore More Software Engineering Skills→
tarabakz25tarabakz25
1

openai-docs

Retrieve official OpenAI documentation and GPT-5.4 upgrade guidance via MCP tools.

Community
Advanced
tanveerriaztanveerriaz
1

llm-eval-golden-set

Builds a golden set of test cases and an eval runner to detect LLM output regressions.

Community
Intermediate
nexus-labs-automationnexus-labs-automation
7

llm-call-tracing

Trace LLM API calls to capture model, latency, tokens, cost, and success status.

Official
Advanced
evolution-foundationevolution-foundation
520

dev-ask

Query one target model for a labeled advisory answer.

Official
Intermediate