gpt

OpenAI GPT integration. Chat completions, image generation, embeddings, and fine-tuning via OpenAI API.

Quality

52%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./public/skills/0xterrybit/gpt/SKILL.md

Quality

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 is concise and lists specific capabilities well, making it clear what the skill does. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. Adding common user-facing trigger terms and variations would also improve discoverability.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to call OpenAI APIs, generate text with GPT, create images, compute embeddings, or fine-tune models.'

Include common user-facing trigger term variations such as 'GPT-4', 'GPT-3.5', 'DALL-E', 'ChatGPT', 'text generation', or 'AI completions' to improve matching.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'Chat completions, image generation, embeddings, and fine-tuning via OpenAI API.' These are distinct, well-defined capabilities.	3 / 3
Completeness	Clearly answers 'what does this do' with specific capabilities, but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this dimension at 2 per the rubric.	2 / 3
Trigger Term Quality	Includes relevant keywords like 'OpenAI', 'GPT', 'chat completions', 'image generation', 'embeddings', 'fine-tuning', and 'OpenAI API'. However, it misses common user variations like 'DALL-E', 'ChatGPT', 'text generation', 'AI model', or 'GPT-4'.	2 / 3
Distinctiveness Conflict Risk	Clearly scoped to OpenAI's specific API and GPT ecosystem. The mention of 'OpenAI API' and specific services like 'chat completions, image generation, embeddings, fine-tuning' makes it highly distinguishable from other AI integration skills.	3 / 3
	Total	10 / 12 Passed

Implementation

37%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill provides a single useful curl example for chat completions but fails to deliver actionable guidance for the majority of its advertised features (image generation, embeddings, fine-tuning, Assistants API). It lacks any workflow structure, error handling, or validation steps. The content is a thin overview that doesn't sufficiently teach Claude how to perform the tasks described.

Suggestions

Add concrete, executable code examples (curl or Python) for each advertised feature: image generation, embeddings, fine-tuning, and Assistants API.

Include error handling guidance—at minimum, how to detect and respond to common failures like 401 auth errors, 429 rate limits, and malformed requests.

Add a basic workflow for multi-step operations like fine-tuning (upload data → create job → poll status → use model) with validation checkpoints.

Either link to separate reference files for advanced features or remove them from the feature list to avoid promising content that isn't delivered.

Dimension	Reasoning	Score
Conciseness	Reasonably brief but the feature bullet list and usage examples section add little value—Claude already knows what GPT-4, DALL-E, and embeddings are. The natural-language usage examples ('Ask GPT: Explain quantum computing') don't teach Claude anything actionable.	2 / 3
Actionability	The curl example for chat completions is concrete and executable, but image generation, embeddings, fine-tuning, and Assistants API have zero concrete code or commands. Only one of five advertised features has actionable guidance.	2 / 3
Workflow Clarity	There is no sequenced workflow, no error handling, no validation steps, and no guidance on how to chain API calls or handle failures (rate limits, auth errors). The skill is essentially a single curl snippet with no surrounding process.	1 / 3
Progressive Disclosure	The content is short and organized into sections, which is fine for a simple skill. However, it lists five features but only covers one, with no references to additional files or documentation for the remaining four, leaving the reader with no path to deeper information.	2 / 3
	Total	7 / 12 Passed

Validation

81%

Warnings & errors only

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: f45fcb5

Reviewed: 22 days ago

Table of Contents

Discovery Implementation Validation

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.