Name: cheddar
Rating: 50.4 (1 reviews)
Author: membranedev

cheddar

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

Quality

55%

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/cheddar/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 a solid, executable reference for the Membrane-Cheddar workflow with concrete commands and a useful popular-actions table. Its main weakness is workflow_clarity: destructive and batch actions like deleting customers or cancelling subscriptions are offered without any validate-then-confirm or verify-after-run checkpoint.

Suggestions

Add an explicit validation/confirmation step before destructive actions (e.g. 'Before running delete-customer or cancel-subscription, confirm the target with the user and re-run get-customer to verify the result afterward').

Tighten the repeated auth-handling prose into one concise note, and remove the filler line 'Use action names and parameters as needed'.

Show a worked example of invoking one action with a real --input JSON payload (e.g. create-customer) so the action-run guidance is fully executable rather than schematic.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean executable commands with minimal padding; the only mild bloat is restating that Membrane handles auth/credentials in a few places and the boilerplate 'Use action names and parameters as needed', but it largely assumes Claude's competence.	4 / 5
Actionability	Provides concrete, copy-pasteable CLI commands for install, login, connection ensure, polling, action list/run, and proxy requests, plus a popular-actions table; minor gaps are that action parameter schemas are described rather than shown and input shapes rely on 'as needed'.	4 / 5
Workflow Clarity	There is a clear connect-and-poll sequence with state handling (READY/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR), but the destructive/batch actions (delete-customer, cancel-subscription) have no validation or verification step before/after running, so the feedback-loop checkpoint is missing.	3 / 5
Progressive Disclosure	Content is well sectioned (Overview, Working with Cheddar, Popular actions, Best practices) with no external bundle files to reference; it stays one level deep and is easy to navigate, though some sections (proxy flags table) could arguably live in a reference file.	4 / 5
	Total	15 / 20 Passed

Description

42%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 anchors itself to a named product (Cheddar) which aids distinctiveness, but the stated capabilities are generic ('manage data, records, automate workflows') rather than concrete accounting actions, and the trigger guidance is thin. It communicates what app the skill targets but not precisely what it does or when to reach for it.

Suggestions

Replace 'Manage data, records, and automate workflows' with concrete Cheddar actions, e.g. 'Create customers, manage subscriptions, add charges, and retrieve invoices and plans'.

Expand the 'Use when...' clause with natural accounting triggers: 'Use when the user needs to manage Cheddar customers, subscriptions, charges, invoices, or pricing plans'.

Drop the generic word 'data' in favor of Cheddar-specific nouns (customers, subscriptions, plans, charges) that users would actually say.

Dimension	Reasoning	Score
Specificity	Names the domain (Cheddar) and lists generic actions ('Manage data, records, and automate workflows') but these are abstract categories rather than concrete operations like 'add a charge' or 'create a customer', so coverage is shallow rather than comprehensive.	3 / 5
Completeness	There is a clear 'what' (manage Cheddar data/records/workflows) and a 'Use when...' clause, but the 'when' is thin ('when the user wants to interact with Cheddar data') and could be far more specific about accounting scenarios.	3 / 5
Trigger Term Quality	The only natural trigger phrase is 'interact with Cheddar data'; the phrase 'Manage data, records, and automate workflows' is generic and omits the natural accounting/invoice terms users would actually say (invoices, customers, subscriptions, charges).	2 / 5
Distinctiveness Conflict Risk	Naming the specific app 'Cheddar' gives it a distinct niche, but 'Manage data, records, and automate workflows' is broad boilerplate that could overlap with any data-management skill.	3 / 5
	Total	11 / 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/cheddar/SKILL.md
Commit: f484c82

Reviewed: 3 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.