Name: knit
Rating: 60 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

knit

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

Quality

70%

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/knit/SKILL.md

Quality

Content

82%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 a strong, action-oriented integration guide built around executable Membrane CLI commands and a clear connection-state workflow with retry semantics. Its main weaknesses are minor verbosity and an internal "Step 2" reference that is not explicitly labeled.

Suggestions

Label the post-connection section explicitly as "Step 2" (or reword the "skip to Step 2" references) so the cross-reference resolves.

Trim marketing-style asides like "so you can focus on the integration logic rather than auth plumbing" to tighten token efficiency.

Consider moving the detailed clientAction state table and proxy flag reference into a separate reference file linked from the body, improving progressive disclosure for this longer-than-50-line skill.

Dimension	Reasoning	Score
Conciseness	The body is dominated by lean, copy-paste command blocks with only minor over-explanation (e.g. "so you can focus on the integration logic rather than auth plumbing"), matching the "efficient; minor instances of over-explanation" anchor rather than the fully lean anchor above.	4 / 5
Actionability	It provides fully executable commands for every stage (install, login, connection ensure, action list/run, request) plus a flags table for the proxy, covering the common cases copy-paste ready, which matches the top anchor.	5 / 5
Workflow Clarity	The connect workflow is sequenced with a state machine (READY/BUILDING/CLIENT_ACTION_REQUIRED) and a poll-and-retry feedback loop, but the "skip to Step 2" reference points to an unlabeled step, leaving a minor gap below the explicit-checklist anchor.	4 / 5
Progressive Disclosure	With no bundle files present, the single SKILL.md is organized into clear, well-labeled sections that keep related content together; the inlined state-machine and proxy-flag detail could conceivably be split out, placing it just below the well-signaled-reference anchor.	4 / 5
	Total	17 / 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 successfully states both what the skill does and when to use it, anchored by a distinctive product name, but its capability list relies on generic verbs (manage data/records, automate workflows) rather than concrete actions. It reads as functional but under-specific, capping it at a mid-strong result.

Suggestions

Replace generic verbs with concrete Knit capabilities, e.g. "Create threads, send messages, list users, and retrieve thread details" instead of "Manage data, records, and automate workflows".

Expand the trigger clause with natural user phrases such as "Use when the user wants to send Knit messages, list threads, or look up Knit users" to improve trigger-term coverage.

Add the file extension or app URL reference (e.g. knitpeople.com) to further distinguish it from similarly named skills.

Dimension	Reasoning	Score
Specificity	The description names the Knit domain but the listed actions ("Manage data, records, and automate workflows") are generic verbs with no concrete capabilities, fitting the "names the domain but actions are minimal or generic" anchor rather than the concrete-action anchors above.	2 / 5
Completeness	Both the "what" (Knit integration that manages data, records, and automates workflows) and a "when" clause ("Use when the user wants to interact with Knit data") are present, but the trigger is generic rather than concrete, so it sits at the "both present, when could be more specific" anchor and not the level above.	4 / 5
Trigger Term Quality	It includes the natural product keyword "Knit" and the phrase "interact with Knit data", but coverage is thin with no synonyms or common variations beyond the product name, matching the "some relevant keywords but missing common variations" anchor.	3 / 5
Distinctiveness Conflict Risk	The distinct product name "Knit" gives it a clear niche with minimal conflict risk, but the generic action verbs (manage data, automate workflows) leave minor overlap with adjacent integration skills, placing it just below the minimal-risk anchor.	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/knit/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.