Name: openai
Rating: 55.2 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

openai

OpenAI integration. Manage Assistants, Files. Use when the user wants to interact with OpenAI data.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/openai/SKILL.md

Quality

Content

63%Weight 40%Scale 1-5

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

The body is highly actionable with concrete CLI commands and a well-validated connection workflow, but it spends tokens on background Claude already knows and inlines reference material that would benefit from a separate file. Step numbering and validation for destructive actions are minor gaps.

Suggestions

Remove the opening 'OpenAI is an artificial intelligence research and deployment company...' paragraph; Claude already knows this.

Move the full 'Popular actions' table and proxy flag reference into a references/ file (e.g. ACTIONS.md) and link to it from SKILL.md to apply progressive disclosure.

Add a validation/confirmation note before destructive actions (e.g. 'Confirm with the user before running delete-file or other irreversible actions') and fix the inconsistent 'Step 2' / '1b' numbering.

Dimension	Reasoning	Score
Conciseness	Most of the body is efficient, copy-paste command blocks, but it opens with background Claude already knows ('OpenAI is an artificial intelligence research and deployment company...') and inlines a 9-row actions catalog and a proxy-flag table that pad the token budget, fitting 'mostly efficient but includes some unnecessary explanation'.	3 / 5
Actionability	It provides concrete, executable commands throughout (npm install, membrane login, connection ensure, action run/list, request) with real flags and a JSON-input example, reaching 'mostly executable guidance' but stopping short of 5 because examples rely on placeholders (<actionId>, CONNECTION_ID) without a fully filled-in end-to-end case.	4 / 5
Workflow Clarity	The connection flow is a clear sequence with explicit validation checkpoints and feedback loops (poll --wait until state leaves BUILDING; branch on READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR; re-poll after user action), but step labeling is inconsistent ('skip to Step 2' and '1b' without a cleanly numbered Step 1/2) and the action-running section adds no validation for destructive actions like Delete File.	4 / 5
Progressive Disclosure	No bundle files exist and all content — including the bulk 'Popular actions' catalog and proxy flag reference that could live in a separate file — is inlined in SKILL.md; sections are reasonably organized but content that should be split out is inline and there are no external references, matching the 'some structure; content that should be separate is inline' anchor.	3 / 5
	Total	14 / 20 Passed

Description

62%Weight 40%Scale 1-5

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 cleanly states both capability and an explicit 'Use when' trigger, with a clear OpenAI niche. Its main weakness is generic action verbs ('Manage') and thin keyword coverage that omits common user synonyms like GPT or chat completions.

Suggestions

Replace the generic 'Manage Assistants, Files' with specific verbs, e.g. 'Create and manage Assistants, Threads, Messages, and Files'.

Expand the trigger clause with concrete natural phrases: 'Use when the user wants to work with OpenAI Assistants, Files, GPT chat completions, embeddings, or images'.

Add common synonyms (GPT, chat completions, models, embeddings, DALL·E) to improve trigger-term coverage and distinctiveness.

Dimension	Reasoning	Score
Specificity	The description names the OpenAI domain and two concrete resources ('Manage Assistants, Files'), but the verb 'Manage' is generic and coverage is not comprehensive, matching the 'names domain and 1-2 concrete actions' anchor rather than the fuller 4 or the minimal 2.	3 / 5
Completeness	Both 'what' ('OpenAI integration. Manage Assistants, Files.') and 'when' ('Use when the user wants to interact with OpenAI data.') are explicitly present, but the trigger phrase is fairly generic rather than packed with concrete triggers, fitting 'both what and when; when could be more explicit' below the 5 anchor.	4 / 5
Trigger Term Quality	It includes 'OpenAI', 'Assistants', 'Files', and 'OpenAI data' — relevant natural terms — but omits common variations and synonyms users would say (GPT, chat, completions, models, embeddings), so it sits at 'some relevant keywords but missing common variations' rather than the comprehensive 4.	3 / 5
Distinctiveness Conflict Risk	'OpenAI' is a clear, recognizable niche with distinct resource triggers (Assistants, Files), giving mostly-distinct classification with only minor overlap risk against other AI-integration skills, short of the minimal-conflict 5.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: membranedev/application-skills
Path: skills/openai/SKILL.md
Commit: f484c82

Reviewed: 5 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.