Prioritizes official OpenAI documentation, model cards, and API references when researching integration details, model capabilities, or API behavior changes. This avoids the noise and staleness of third-party blog posts that may summarize older model versions or incomplete information.
Use cases
- Selecting which OpenAI model to use for a new feature based on capability and pricing requirements
- Integrating the OpenAI API into a product and needing accurate parameter documentation for the current API version
- Troubleshooting an API error where the error code or behavior is not covered in community tutorials
- Evaluating whether to upgrade to a newer model version and needing the changelog and migration guide
- Setting up a new OpenAI project and wanting to configure the correct API base URL, headers, and request format
Key features
- Start your search at platform.openai.com/docs, which is kept in sync with the current production API version
- Locate the relevant API reference page and cross-check the described behavior against the SDK or library you are using
- Extract the specific parameters, limits, and error codes you need, noting any version constraints or deprecation timelines
- Verify the information against the model cards when choosing between models, as capability claims belong there rather than in opinionated blog posts
When to Use This Skill
- When integrating OpenAI APIs and needing accurate, version-specific parameter documentation
- When comparing OpenAI models for a specific task and wanting reliable capability comparisons
- When troubleshooting an OpenAI API error that is not covered in community forums or tutorials
Expected Output
Verified API parameters, endpoint URLs, request/response schemas, and version constraints extracted from official documentation, ready to use in integration code.
Frequently Asked Questions
- Why not use third-party tutorials for OpenAI integration?
- Third-party tutorials often lag behind API version changes by weeks or months. They also frequently simplify edge cases (rate limits, token counting, error handling) that cause production issues. Use them for conceptual understanding, but always verify against the official docs for implementation.
- How do I stay current with OpenAI API changes?
- Subscribe to the OpenAI API changelog and model deprecation announcements. When starting a new integration, pin to a specific API version rather than always using the latest.
- What about OpenAI's system prompts and safety documentation?
- These are also on the official docs site and are authoritative for understanding content filtering, abuse detection, and rate limit policies. Do not rely on secondhand summaries for safety-critical configuration.
Related
Related
3 Indexed items
Brainstorming before build
Explores goals, constraints, risks, and design options before committing to a specific implementation path. This technique is most valuable when facing product or UX decisions where the wrong choice is expensive to reverse—new features with uncertain user value, architectural pivots, or cross-functional dependencies where each team has a different mental model of the problem.
Threat modeling
Systematically identifies threats to a system by mapping data flows, defining trust boundaries, and enumerating adversaries and misuse cases before shipping. This produces a security-focused diagram and prioritized mitigation list that makes subsequent security reviews faster and more substantive than starting from a generic checklist.
Context-Aware QA Skill
Context-Aware QA is a prompting technique where an AI model is instructed to retrieve and cite authoritative sources before answering factual questions. By combining retrieval-augmented generation (RAG) with explicit verification instructions, it dramatically reduces hallucinations in production AI systems.