gpt
OpenAI GPT integration. Chat completions, image generation, embeddings, and fine-tuning via OpenAI API.
65
Quality
60%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./public/skills/0xterrybit/gpt/SKILL.mdQuality
Discovery
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description effectively lists specific OpenAI API capabilities and is clearly distinguishable from other skills. However, it lacks explicit trigger guidance ('Use when...') and could benefit from more natural user-facing keywords like 'ChatGPT' or 'DALL-E' that users commonly say.
Suggestions
Add a 'Use when...' clause with trigger scenarios like 'Use when the user wants to integrate with OpenAI, call GPT models, generate images with DALL-E, or create embeddings'
Include common user-facing terms like 'ChatGPT', 'DALL-E', 'GPT-4', 'GPT-3.5' that users naturally mention when requesting OpenAI functionality
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Chat completions, image generation, embeddings, and fine-tuning' - these are distinct, actionable capabilities rather than vague language. | 3 / 3 |
Completeness | Clearly answers 'what' (chat completions, image generation, embeddings, fine-tuning via OpenAI API) but lacks an explicit 'Use when...' clause or trigger guidance for when Claude should select this skill. | 2 / 3 |
Trigger Term Quality | Includes 'OpenAI', 'GPT', and 'OpenAI API' which are relevant keywords, but misses common variations users might say like 'ChatGPT', 'DALL-E', 'GPT-4', 'AI chat', or 'generate images with AI'. | 2 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to OpenAI/GPT specifically with distinct technical capabilities; unlikely to conflict with other AI integration skills due to explicit 'OpenAI API' mention and specific feature set. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
52%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is concise and well-structured but lacks depth in actionability. It lists multiple features (image generation, embeddings, fine-tuning, Assistants API) without providing executable examples or workflows for them, making it more of a feature list than an actionable skill guide.
Suggestions
Add executable curl or Python examples for image generation, embeddings, and at least one other listed feature
Provide a basic workflow for fine-tuning with clear steps and validation checkpoints
Either add references to external documentation for advanced features or include minimal working examples inline
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, with no unnecessary explanations of what GPT or APIs are. Every section serves a purpose without padding. | 3 / 3 |
Actionability | Provides one concrete curl example for chat completions, but image generation, embeddings, fine-tuning, and Assistants API are only listed as features without executable code or commands. | 2 / 3 |
Workflow Clarity | No workflow or sequence is provided for any multi-step processes like fine-tuning or using the Assistants API. The skill lists features but doesn't guide through how to actually accomplish them. | 1 / 3 |
Progressive Disclosure | Content is brief and organized into clear sections, but there are no references to additional documentation for the advanced features mentioned (fine-tuning, Assistants API, embeddings). | 2 / 3 |
Total | 8 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 9 / 11 Passed | |
- Repository
- Demerzels-lab/elsamultiskillagent
- Commit
45f9fac
- 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.