Name: stability-ai
Rating: 57.599999999999994 (1 reviews)
Author: membranedev

stability-ai

Stability AI integration. Manage data, records, and automate workflows. Use when the user wants to interact with Stability AI data.

Quality

66%

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/stability-ai/SKILL.md

Quality

Content

75%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 a highly actionable, well-structured CLI integration guide with executable commands and a solid connection-state feedback loop. Its main weaknesses are a padded introductory concept paragraph and a dangling "Step 2" reference in the workflow.

Suggestions

Trim the opening "Stability AI is an open-source artificial intelligence company..." sentence and other editorial asides; assume Claude knows what Stability AI is.

Fix the dangling "skip to Step 2" references by either numbering the subsequent sections (e.g. "#### 2. Search for actions") or rewording to "skip to Searching for actions".

Add a brief validation note after `membrane action run` describing how to interpret the `output` field and confirm the action succeeded.

Dimension	Reasoning	Score
Conciseness	Mostly command-focused and efficient, but it opens with concept padding Claude already knows ("Stability AI is an open-source artificial intelligence company...") and includes editorial asides like "so you can focus on the integration logic rather than auth plumbing."	3 / 5
Actionability	Provides copy-paste ready commands throughout — install, login, connection ensure/get, action list/run, and request — plus a complete proxy flag table; placeholders like CONNECTION_ID are legitimate and well explained.	5 / 5
Workflow Clarity	A clear install → auth → connect → search → run sequence with strong feedback loops for the connection state machine (poll BUILDING, handle CLIENT_ACTION_REQUIRED, re-poll, CONFIGURATION_ERROR), but "skip to Step 2" references a Step 2 that is never defined, and action results are not validated.	4 / 5
Progressive Disclosure	Single, well-sectioned file (Overview, Working with, Install, Auth, Connecting, Searching, Actions, Proxy, Best practices) with no nested references and easy navigation; the proxy flag table and detailed clientAction handling are appropriately inline for a CLI guide, with only minor organization gaps.	4 / 5
	Total	16 / 20 Passed

Description

57%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 correctly pairs a what with an explicit "Use when" trigger tied to a distinct product, satisfying the completeness and distinctiveness bars. Its weakness is generic, non-concrete capability language that under-sells the specific Stability AI actions the skill actually exposes.

Suggestions

Replace "Manage data, records, and automate workflows" with concrete Stability AI actions, e.g. "Generate images from text (txt2img, img2img), upscale, and generate video from images."

Broaden trigger terms to include natural synonyms users say, such as "Stable Diffusion", "generate images", or "image generation".

Tie the when clause to the concrete outputs, e.g. "Use when the user wants to generate images or video with Stability AI / Stable Diffusion."

Dimension	Reasoning	Score
Specificity	Names the domain ("Stability AI integration") but the actions are generic — "Manage data, records, and automate workflows" — rather than concrete Stability AI actions like txt2img, img2vid, or upscale that appear in the body.	2 / 5
Completeness	Both what ("Manage data, records, and automate workflows") and when ("Use when the user wants to interact with Stability AI data") are present, and the when clause is explicit; the what is generic which keeps it below a 5.	4 / 5
Trigger Term Quality	"Stability AI" is a natural keyword and the trigger names it, but coverage is limited to the product name with no synonyms or natural variations (e.g. Stable Diffusion, generate images) that a user might say.	3 / 5
Distinctiveness Conflict Risk	Tying the trigger to "Stability AI" gives a clear niche with low conflict risk, but the generic action phrasing ("manage data, records") could overlap with other integration skills, so it is not a clean 5.	4 / 5
	Total	13 / 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/stability-ai/SKILL.md
Commit: f484c82

Reviewed: 4 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.