Name: brandfetch
Rating: 56.8 (1 reviews)
Author: membranedev

brandfetch

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

Quality

65%

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/brandfetch/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 body is a mostly executable, well-structured guide to driving Brandfetch through the Membrane CLI, with genuine validation checkpoints in the connection workflow. Its main weaknesses are conceptual padding in the intro and a broken 'Step 2' cross-reference that slightly muddles the sequence.

Suggestions

Trim the marketing-style opening paragraph to one factual line about what Brandfetch provides; remove the 'so you can focus on the integration logic rather than auth plumbing' aside.

Fix the dangling step references: either label sections 'Step 1: Install', 'Step 2: Connect' or replace 'skip to Step 2' with a concrete section link.

Consider moving the detailed connection-state explainer (READY/BUILDING/CLIENT_ACTION_ERROR) into a references/ file and summarizing the happy path inline.

Dimension	Reasoning	Score
Conciseness	The bulk is efficient commands and a flag table, but the opening paragraph ('It allows marketing teams and designers to easily access and share their brand assets... helps maintain brand consistency') and lines like 'so you can focus on the integration logic rather than auth plumbing' are explanatory padding Claude does not need, fitting 'mostly efficient but includes some unnecessary explanation'.	3 / 5
Actionability	It provides concrete, copy-paste-ready commands for install, login, connection ensure/get, action list/run, and proxy requests plus a flags table, with only minor gaps (placeholders like <actionId> and CONNECTION_ID) keeping it just below the fully-covered 5 anchor.	4 / 5
Workflow Clarity	The install → authenticate → connect → wait/search → run sequence is clear with validation checkpoints (poll --wait, state checks READY/BUILDING/CLIENT_ACTION_REQUIRED) and a re-poll feedback loop, but the dangling 'skip to Step 2' references with no matching Step 1/Step 2 headers are a minor sequencing gap that prevents 5.	4 / 5
Progressive Disclosure	No bundle files exist, and the body is well-organized into clearly headed sections (Install, Authentication, Connecting, Searching, Running actions, Proxy, Best practices) with content appropriately self-contained; it stops at 4 rather than 5 because the lengthy connection-state explainer is inlined where a one-level-deep reference could live.	4 / 5
	Total	15 / 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 correctly includes an explicit 'Use when' trigger and ties the skill to a distinct named platform, but its capability list relies on generic verbs and omits the natural terms (logos, colors, fonts) users would actually say. It is adequate but could be much sharper with concrete Brandfetch capabilities.

Suggestions

Replace 'Manage data, records, and automate workflows' with concrete capabilities, e.g. 'Fetch brand logos, colors, fonts, and screenshots; manage API keys and brand records.'

Add natural trigger terms users would say, such as 'logos', 'brand colors', 'fonts', 'brand assets', or 'brand identity'.

Tighten the 'when' clause to reference those assets, e.g. 'Use when the user wants to look up or use a brand's logos, colors, fonts, or screenshots.'

Dimension	Reasoning	Score
Specificity	It names the domain and enumerates actions ('Manage data, records, and automate workflows'), but those actions are generic marketing-style verbs rather than concrete Brandfetch capabilities like fetching logos, colors, or fonts, so it stops at the 'names domain and 1-2 actions but not comprehensive' anchor rather than reaching 4.	3 / 5
Completeness	It supplies a 'what' ('Manage data, records, and automate workflows') and an explicit 'when' clause ('Use when the user wants to interact with Brandfetch data'), so it clears the missing-trigger cap; the 'when' is somewhat generic, which keeps it at 4 rather than the fully concrete trigger phrases of 5.	4 / 5
Trigger Term Quality	The only natural trigger keyword is the brand name itself ('interact with Brandfetch data'); common user synonyms such as 'logos', 'brand colors', 'fonts', or 'brand assets' are missing, matching the 'some relevant keywords but missing common variations' anchor rather than the fuller coverage of 4.	3 / 5
Distinctiveness Conflict Risk	'Brandfetch integration' plus a Brandfetch-specific trigger carves a clear niche with minimal conflict risk, but the generic 'what' actions leave minor overlap risk with other data-integration skills, fitting 'mostly distinct; minor overlap risk' better than the fully concrete niche of 5.	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/brandfetch/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.