Name: product-fruits
Rating: 60.8 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

product-fruits

Product Fruits integration. Manage ProductFruitsApps. Use when the user wants to interact with Product Fruits 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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/product-fruits/SKILL.md

Quality

Content

81%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 highly actionable, with concrete executable CLI commands and a clear connection-state workflow, but it loses points on conciseness for front-loading platform background Claude already knows and on progressive disclosure because everything lives inline with no companion reference files.

Suggestions

Cut the introductory paragraph explaining what Product Fruits is (a product managers will recognize) and jump straight to the Membrane integration steps.

Add a post-action verification step for mutating actions (e.g. re-query the affected entity via action run or request GET to confirm the change landed) to close the workflow feedback loop.

Move the clientAction schema detail and the proxy flag table into a companion reference file (e.g. references/connections.md, references/proxy.md) and link to them from the body to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean command-driven prose with executable CLI snippets and a tight flag table, though the opening paragraph ('Product Fruits is a SaaS platform that helps product managers...') explains platform concepts Claude largely already knows and could be trimmed.	4 / 5
Actionability	It provides copy-paste-ready commands for install, login, headless completion, connection ensure/get, action list/run, and proxy requests, each with exact flags and example JSON payloads covering the common cases.	5 / 5
Workflow Clarity	The connection workflow is well sequenced with explicit state-checking (READY / BUILDING / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR) and a poll loop, but there is no validate-after-run checkpoint and the destructive/batch proxy path (request with DELETE/PUT bodies) has no verification step, holding it below 5.	4 / 5
Progressive Disclosure	Structure is good with clear sections and an overview bullet list rather than a monolithic wall, but no bundle files exist so all reference material (API/clientAction details, flag tables) is inlined in SKILL.md rather than split one level deep; minor organization gaps remain.	4 / 5
	Total	17 / 20 Passed

Description

62%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 is functional and correctly follows the 'what + Use when' pattern with a clear third-person voice, but its capability list is minimal and its trigger terms are limited to the brand name rather than the natural product-management vocabulary (tours, checklists, onboarding, surveys) users would actually say.

Suggestions

Add concrete capability verbs to the 'what' clause, e.g. 'Create and manage product tours, checklists, release notes, and user segments in Product Fruits.'

Expand trigger terms beyond the brand name to include natural phrasings like 'product tours', 'in-app onboarding', 'user checklists', and 'product feedback surveys'.

Consider naming the entity (ProductFruitsApps) more consistently — the description mixes 'Product Fruits' and 'ProductFruitsApps' which slightly weakens trigger matching.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Product Fruits integration') and one concrete action ('Manage ProductFruitsApps') but offers only a single generic verb rather than a comprehensive list of actions like tours, checklists, or user segments.	3 / 5
Completeness	It answers both 'what' ('Manage ProductFruitsApps') and 'when' ('Use when the user wants to interact with Product Fruits data'), with an explicit Use-when clause, though the 'what' is thin compared to the 5-anchor.	4 / 5
Trigger Term Quality	It includes the natural brand term 'Product Fruits' and the file/entity term 'ProductFruitsApps', but lacks common variations users might say (tours, onboarding, in-app surveys, checklists) and any file-extension-style synonyms.	3 / 5
Distinctiveness Conflict Risk	The niche is fairly distinct — 'Product Fruits' / 'ProductFruitsApps' is a specific third-party SaaS — with only minor overlap risk against other Membrane-managed integration skills using the same template.	4 / 5
	Total	14 / 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/product-fruits/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.