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

kern-ai

Kern AI integration. Manage data, records, and automate workflows. Use when the user wants to interact with Kern 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/kern-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 content is action-oriented with executable Membrane CLI commands and a connection-readiness polling loop, but it carries some unnecessary background explanation, an inconsistent CLI invocation form, and a dangling "Step 2" reference. Tightening the intro and fixing the step numbering would raise it further.

Suggestions

Trim the opening overview paragraph and Membrane auth rationale to the minimum needed for action; assume Claude knows general auth concepts.

Pick one invocation form (membrane vs npx @membranehq/cli) and use it consistently, or state the alias explicitly once.

Replace the undefined "skip to Step 2" reference with a concrete section anchor or numbered step so the workflow sequence is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but the intro explains what Kern AI is and Membrane's auth role in language Claude can infer, and the proxy prose could be trimmed, matching the mostly-efficient-but-could-be-tightened anchor.	3 / 5
Actionability	It provides concrete, copy-paste-ready CLI commands and a flag table, but invocation is inconsistent ("membrane" vs "npx @membranehq/cli") and placeholders like CONNECTION_ID are left to the reader, matching mostly-executable with minor gaps.	4 / 5
Workflow Clarity	The install-authenticate-connect-search-run sequence is clear with a state-polling feedback loop (READY/BUILDING/CLIENT_ACTION_REQUIRED), but "skip to Step 2" references a Step 2 that is never labelled, leaving a minor sequencing gap.	4 / 5
Progressive Disclosure	The single SKILL.md is well-organized into clearly headed sections with no external references needed for this CLI-usage skill, but the thin "Popular actions" section is underdeveloped, leaving minor organization gaps.	4 / 5
	Total	15 / 20 Passed

Description

66%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 answers both what and when and targets a distinct niche (Kern AI), but the listed actions are generic and the trigger vocabulary is narrow. Tightening the action list and adding synonyms would lift specificity and trigger quality.

Suggestions

Replace generic verbs ("Manage data, records, and automate workflows") with concrete Kern AI actions such as labeling records, training models, or querying projects.

Add natural trigger synonyms and file/URL cues (e.g., "kern.ai", "labeling tasks", "record curation") so users phrase the request more ways.

Make the when clause more specific, e.g. "Use when the user wants to label records, train models, or query Kern AI projects."

Dimension	Reasoning	Score
Specificity	It names the domain ("Kern AI") and a couple of actions ("Manage data, records, and automate workflows"), but those actions are generic rather than comprehensive and concrete, matching the 1-2 concrete actions anchor.	3 / 5
Completeness	It states both what ("Manage data, records, and automate workflows") and when ("Use when the user wants to interact with Kern AI data"), but the when clause is somewhat generic and could be more specific, matching the both-present-but-could-be-more-explicit anchor.	4 / 5
Trigger Term Quality	The natural keywords ("Kern AI", "interact with Kern AI data") are relevant but limited, missing common variations or synonyms users might say, fitting the some-relevant-keywords-but-missing-variations anchor.	3 / 5
Distinctiveness Conflict Risk	Kern AI is a clearly distinct platform niche with its own trigger term ("Kern AI"), giving minimal conflict risk with other skills, matching the clear-niche anchor.	5 / 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/kern-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.