Name: cursor
Rating: 53.6 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

cursor

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

Quality

60%

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/cursor/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 a well-structured, actionable guide to the Membrane/Cursor integration with concrete commands and a clear state-driven connection workflow. Its main weakness is conciseness, with several padded explanatory passages that could be cut, plus minor inconsistencies in workflow step numbering.

Suggestions

Trim explanatory padding such as 'so you can focus on the integration logic rather than auth plumbing' and the 'fastest way to get a connection' paragraph to keep only what Claude cannot infer.

Fix the workflow numbering inconsistency: label 'Step 1a' alongside '1b', and explicitly label the referenced 'Step 2' (searching/running actions) so the cross-references resolve.

Replace the generic 'QUERY' intent placeholder with a concrete example intent and show a sample action list/run invocation with real values to push actionability toward copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is mostly command-driven and efficient, but includes padded prose such as 'so you can focus on the integration logic rather than auth plumbing' and the explanatory 'This is the fastest way to get a connection... a connector is built automatically' that could be trimmed, matching 'mostly efficient but includes some unnecessary explanation or could be tightened'.	3 / 5
Actionability	It provides concrete, copy-paste-ready commands throughout (npm install, membrane login, connection ensure, action list/run, request) with flags and JSON examples covering the common cases, matching 'mostly executable guidance; concrete code or commands with minor gaps'; it does not reach 5 because placeholders like CONNECTION_ID and the generic 'QUERY' intent are left for the user to resolve.	4 / 5
Workflow Clarity	The connect-wait-search-run sequence is clear with state-based polling checkpoints (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) and a re-poll feedback loop after user action, matching 'clear sequence with most checkpoints present; minor validation gaps'; the inconsistent step labels (a '1b' with no '1a', and a referenced 'Step 2' that is never labeled) keep it below 5.	4 / 5
Progressive Disclosure	The body is well-organized into clearly signaled sections (Overview, Working with Cursor, Authentication, Connecting, Searching, Popular actions, Best practices) with no nested references and no bundle files, matching 'good structure; most content appropriately placed; minor organization gaps'; the proxy flag table and clientAction details are reasonable to keep inline for a single-purpose integration skill.	4 / 5
	Total	15 / 20 Passed

Description

53%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 covers both what and when with an explicit trigger clause, but its capability language is generic and it lacks the natural, varied trigger terms a user would actually say. Specificity and distinctiveness are the weakest dimensions.

Suggestions

Replace generic verbs ('Manage data, records, and automate workflows') with concrete Cursor capabilities such as sending chat messages, working with documents, and running searches.

Add natural trigger phrases users would say, e.g. 'Use when the user wants to send Cursor chat messages, search or edit Cursor documents, or automate Cursor workflows.'

Tie the 'when' clause to Cursor-specific artifacts (chat, documents, search) to reduce overlap with generic data-management skills.

Dimension	Reasoning	Score
Specificity	It names the domain ('Cursor integration') but the stated actions — 'Manage data, records, and automate workflows' — are minimal and generic rather than concrete capabilities, matching the 'names the domain but actions are minimal or generic' anchor and falling below the 3 anchor which requires 1-2 concrete actions.	2 / 5
Completeness	It states both a what ('Manage data, records, and automate workflows') and an explicit when ('Use when the user wants to interact with Cursor data'), satisfying both halves; it does not reach 5 because neither the what nor the when is concretely specific with multiple trigger phrases.	4 / 5
Trigger Term Quality	'Cursor' is a relevant keyword and 'Use when the user wants to interact with Cursor data' provides a trigger phrase, but natural user phrasings ('edit code in Cursor', 'chat with Cursor', file extensions) are missing, matching 'some relevant keywords but missing common variations or synonyms'.	3 / 5
Distinctiveness Conflict Risk	'Cursor integration' is a fairly distinct niche, but the generic action language ('manage data, records, automate workflows') creates overlap risk with other data-management skills, so it sits at 'somewhat specific but could still overlap' rather than the mostly-distinct 4 anchor.	3 / 5
	Total	12 / 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/cursor/SKILL.md
Commit: f484c82

Reviewed: ~15 hours 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.