Name: cartql
Rating: 60.8 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

cartql

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

Quality

71%

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/cartql/SKILL.md

Quality

Content

76%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 concrete, executable Membrane CLI commands and clear structure, but it lacks explicit validation/verification checkpoints around destructive action runs and proxy mutations and leaves a dangling "Step 2" reference. Tightening those would lift workflow clarity.

Suggestions

Add an explicit verify step after `membrane action run` and proxy mutating calls (e.g. re-query or check the `output`/response status before declaring success).

Resolve the undefined "Step 2" reference or renumber the connection-readiness flow so steps are contiguous and labeled.

Move the verbose clientAction field breakdown and the proxy flag table to a short reference section or note, keeping the main flow lean.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient command-first content that assumes CLI competence, though lines like the "Membrane handles authentication... so you can focus on the integration logic rather than auth plumbing" aside add mild padding that could be trimmed.	4 / 5
Actionability	It provides copy-paste-ready executable commands throughout (login, connection ensure, action list/run, request proxy with a full flag table), with concrete examples covering the common cases and machine-readable --json output.	5 / 5
Workflow Clarity	The connection flow has a sequence and a polling loop, but destructive/batch operations (action run, proxy POST/DELETE) have no validate-before-proceed or verify-after-run checkpoints, and "Step 2" is referenced but never defined, capping clarity at 3.	3 / 5
Progressive Disclosure	Content is well organized into focused sections with no bundle files and no nested references; the only gap is a large block of clientAction detail and the proxy flag table inlined in the main file rather than pointed to a separate reference.	4 / 5
	Total	16 / 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 benefits from a distinctive product name and an explicit "Use when" clause, but its action language is generic and it omits the concrete CartQL verbs (carts, products, GraphQL queries) that would sharpen activation. It is solidly competent yet not exemplary.

Suggestions

Replace "Manage data, records, and automate workflows" with CartQL-specific actions, e.g. "query and update carts, cart items, and products via CartQL's GraphQL API".

Add natural trigger terms a user would actually say ("shopping carts", "cart items", "products", "GraphQL", "e-commerce checkout").

Tighten the when clause to concrete triggers: "Use when the user wants to query or modify CartQL carts, cart items, or products."

Dimension	Reasoning	Score
Specificity	It names the domain and a couple of generic actions ("Manage data, records, and automate workflows") but these are abstract; no CartQL-specific concrete actions like querying carts or products are stated, so it sits at the domain-plus-1-2-generic-actions anchor rather than above it.	3 / 5
Completeness	It gives a clear what ("CartQL integration. Manage data, records, and automate workflows") plus an explicit when clause ("Use when the user wants to interact with CartQL data"); the when is present but slightly generic, so it is just above the midpoint.	4 / 5
Trigger Term Quality	"CartQL" and "CartQL data" appear but the natural phrases a user would say (carts, products, cart items, checkout, GraphQL API) are missing, leaving only some relevant keywords without common variations.	3 / 5
Distinctiveness Conflict Risk	The repeated product name "CartQL" carves out a clear niche with distinct triggers, making it unlikely to collide with other skills or fire for the wrong skill.	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/cartql/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.