Name: one-ai
Rating: 56.8 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

one-ai

One AI integration. Manage Organizations, Users. Use when the user wants to interact with One AI data.

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/one-ai/SKILL.md

Quality

Content

67%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 delivers concrete, executable membrane CLI guidance with a well-sequenced connection workflow and explicit state-checkpoint feedback loops. It loses points mainly to mild padding in the prose and a redundant Popular actions section rather than to any structural problem.

Suggestions

Trim the opening 'One AI provides a suite of generative AI APIs...' paragraph and the 'so you can focus on integration logic' aside, which state what Claude can infer.

Merge 'Popular actions' into 'Searching for actions' since both present the same 'membrane action list --intent' command.

Add a brief result-validation note after 'membrane action run' (e.g., check the 'output' field and handle non-zero exit/error states) to close the workflow gap.

Dimension	Reasoning	Score
Conciseness	The command examples are efficient, but the opening paragraph explaining what One AI is and phrases like 'so you can focus on the integration logic rather than auth plumbing' are padding Claude could infer, matching the 'mostly efficient with some unnecessary explanation' anchor.	3 / 5
Actionability	Concrete, executable commands appear throughout (npm install, membrane login, connection ensure, action run) plus a flags table, but placeholders like <actionId> and the redundant 'Popular actions' section leave minor gaps versus copy-paste-ready completeness.	4 / 5
Workflow Clarity	The connection setup is clearly sequenced with explicit state checkpoints (READY, BUILDING, CLIENT_ACTION_REQUIRED, CONFIGURATION_ERROR) and a re-poll feedback loop, but the 'Running actions' section lacks result validation, so it is not a 5.	4 / 5
Progressive Disclosure	Content is organized into well-labeled sections with no nested references and no bundle files to misplace, but the 'Popular actions' section duplicates 'Searching for actions' and the ~140-line body could split the proxy/connection detail, leaving minor organization gaps.	4 / 5
	Total	15 / 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 is third-person, includes an explicit 'Use when' trigger, and is tied to a specific named service, which keeps it distinct. Its main weakness is generic action language and a narrow trigger that omits the natural task keywords the body later introduces.

Suggestions

Replace the generic verb 'Manage' with concrete One AI actions (e.g., 'Create and manage Organizations and Users, run language actions').

Broaden the trigger clause to name the natural task terms users would say, e.g. 'Use when the user wants to summarize, translate, or generate content via One AI, or manage One AI Organizations and Users.'

Dimension	Reasoning	Score
Specificity	"Manage Organizations, Users" names the One AI domain plus two concrete resources, matching the anchor that names a domain with 1-2 concrete actions, but the verb "Manage" is generic and coverage is not comprehensive.	3 / 5
Completeness	Both a "what" ("One AI integration. Manage Organizations, Users.") and an explicit "when" ("Use when...") are present, but the "when" restates the domain as "interact with One AI data" rather than giving more specific trigger phrases, so it is not a 5.	4 / 5
Trigger Term Quality	The "Use when the user wants to interact with One AI data" clause supplies the brand keyword and a trigger, but it is narrow and omits natural task terms (summarization, translation, content generation) that the body itself lists, so common variations are missing.	3 / 5
Distinctiveness Conflict Risk	Being scoped to a specific named service (One AI) gives it a clear niche with low conflict risk, but the generic "Manage Organizations, Users" framing leaves minor overlap with general org/user-management skills rather than the minimal risk of a 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/one-ai/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.