openai-api
Build with OpenAI stateless APIs - Chat Completions (GPT-5.2, o3), Realtime voice, Batch API (50% savings), Embeddings, DALL-E 3, Whisper, and TTS. Prevents 16 documented errors. Use when: implementing GPT-5 chat, streaming, function calling, embeddings for RAG, or troubleshooting rate limits (429), API errors, TypeScript issues, model name errors.
87
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
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 excels across all dimensions. It provides specific API names and capabilities, includes natural trigger terms users would actually search for, has an explicit 'Use when:' clause with concrete scenarios, and is clearly distinguishable as an OpenAI-specific skill. The mention of '16 documented errors' and specific error codes like 429 adds practical value for troubleshooting scenarios.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and APIs: Chat Completions, Realtime voice, Batch API, Embeddings, DALL-E 3, Whisper, TTS, plus specific capabilities like streaming and function calling. | 3 / 3 |
Completeness | Clearly answers both what (build with OpenAI APIs, prevents errors) AND when (explicit 'Use when:' clause with specific triggers like implementing GPT-5 chat, troubleshooting rate limits). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'GPT-5', 'chat', 'streaming', 'function calling', 'embeddings', 'RAG', 'rate limits', '429', 'API errors', 'TypeScript issues', 'model name errors'. | 3 / 3 |
Distinctiveness Conflict Risk | Very clear niche focused specifically on OpenAI APIs with distinct triggers like 'GPT-5', 'OpenAI', specific error codes (429), and OpenAI-specific products (DALL-E 3, Whisper). Unlikely to conflict with other API skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive, production-ready OpenAI API reference with excellent actionability - nearly every section includes executable code examples. The main weaknesses are its length (could benefit from splitting into separate files for different APIs) and some verbosity in model comparison sections. The documented gotchas and common mistakes sections add significant value.
Suggestions
Split into separate files: move Embeddings, Images, Audio, and Moderation APIs into dedicated reference files (e.g., EMBEDDINGS.md, IMAGES.md) and link from the main skill
Condense the model comparison tables - the GPT-5 series section repeats information that could be a single reference table
Move the 'Official Documentation' links section to a separate REFERENCES.md file to reduce main skill length
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | While the skill is comprehensive and avoids explaining basic concepts Claude knows, it's quite lengthy (~2000+ lines) with some redundancy. The model comparison tables and extensive API coverage could be more condensed, though most content earns its place. | 2 / 3 |
Actionability | Excellent executable code examples throughout - every API section includes copy-paste ready TypeScript/JavaScript with proper imports, error handling patterns, and real endpoint URLs. The function calling loop pattern and streaming examples are particularly well-documented. | 3 / 3 |
Workflow Clarity | Multi-step processes like batch API usage (create JSONL → upload file → create batch → check status) and function calling loops are clearly sequenced with explicit validation steps. The error handling section includes proper retry logic with exponential backoff. | 3 / 3 |
Progressive Disclosure | The skill has a clear table of contents and logical section organization, but it's monolithic - all content is inline rather than split into separate reference files. The 'What's Next' section mentions planned templates and reference docs that would improve this, but they don't exist yet. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
75%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 12 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (1138 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 12 / 16 Passed | |
- 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.