Name: stein
Rating: 59.2 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

stein

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

Quality

69%

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/stein/SKILL.md

Quality

Content

68%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 real, executable Membrane CLI commands and a well-structured connect→discover→run flow, but it carries some padding in the intro and omits validation/verification steps for destructive proxy and action operations. Solid and usable, with room to tighten and add safety checkpoints.

Suggestions

Add a verification step after destructive action runs or proxy writes (e.g. re-query the record or check the `output`/`error` fields) before reporting success.

Trim the marketing intro to a one-line platform context and remove filler like "Use action names and parameters as needed".

Consider moving the proxy flags table and clientAction state reference into a separate REFERENCE.md to keep SKILL.md a lean overview.

Dimension	Reasoning	Score
Conciseness	Most of the body is concrete commands, but the marketing-flavored intro ("low-code platform... designed for non-technical users") and filler like "Use action names and parameters as needed" add unnecessary explanation that could be trimmed.	3 / 5
Actionability	Provides fully executable, copy-paste-ready commands throughout — install, login, connection ensure/get, action list/run, and the proxy with a complete flags table — covering the common cases with real invocations.	5 / 5
Workflow Clarity	The connect→discover→run sequence is clear and the connection-state polling loop is a good feedback checkpoint, but destructive operations (action runs and proxy with POST/PUT/DELETE) lack any validation or verification step, which caps this dimension at 3 per the rubric.	3 / 5
Progressive Disclosure	A single well-organized file with clearly headed sections and no nested references; the proxy-flags table and clientAction state docs could arguably live in a reference file, but keeping them inline is reasonable for a CLI integration skill.	4 / 5
	Total	15 / 20 Passed

Description

70%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 well-formed with an explicit "Use when..." trigger and a clear, named niche (Stein), but its action verbs are generic and it lacks the concrete, multi-action specificity of top-tier descriptions. It sits solidly above average but short of exemplary.

Suggestions

Replace generic verbs with concrete actions, e.g. "Read and write worksheet rows, manage records, and trigger Stein workflows" instead of "Manage data, records, and automate workflows".

Add natural synonyms and concrete triggers to the when-clause, e.g. "Use when the user wants to query, update, or automate Stein spreadsheet records or workflows".

Mention the underlying artifact type (spreadsheets/worksheets) so the trigger matches user language like "Stein spreadsheet" or "Stein worksheet".

Dimension	Reasoning	Score
Specificity	Names the Stein domain and a few action areas ("Manage data, records, and automate workflows"), but the verbs are generic rather than concrete, so it does not reach the "several specific actions" level of a 4.	3 / 5
Completeness	Explicitly answers both what ("Stein integration. Manage data, records, and automate workflows") and when ("Use when the user wants to interact with Stein data"), but the what/when phrasing is generic rather than the concrete trigger phrases that would earn a 5.	4 / 5
Trigger Term Quality	Includes natural terms users would say — "Stein", "data", "records", "workflows", "interact with Stein data" — giving good keyword coverage anchored on the specific app name, though a few synonyms or extensions are missing.	4 / 5
Distinctiveness Conflict Risk	Tying triggers to the specific named app "Stein" gives a clear niche with low conflict risk, though the generic verbs (manage/automate data) leave minor overlap with other data-integration skills.	4 / 5
	Total	15 / 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/stein/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.