Tessl • The management layer for AI agent skills

SkillPublic

brandfetch

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

Quality

69%

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 strong, actionable CLI guide with a well-documented connection state machine and sensible fallback path to proxy requests. Its main weaknesses are template-style marketing padding, a dangling 'Step 2' reference, and no worked example that strings the commands together with real values.

Suggestions

Trim the marketing prose (the 'Brandfetch is a brand asset management platform...' paragraph and the URL-normalization internals) to command-relevant facts only.

Fix the dangling 'skip to **Step 2**' references by numbering the actual workflow steps (1. Install, 2. Connect, 3. Discover actions, 4. Run) or removing the step labels.

Add one worked end-to-end example (e.g. fetch a logo for example.com: connection ensure, action list --intent, action run with a concrete --input) to make the placeholder-only commands fully copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Mostly efficient command-focused content, but it includes unnecessary padding: the marketing-style intro ('It allows marketing teams and designers to easily access and share their brand assets... It helps maintain brand consistency') and internal-mechanics explanation ('The URL is normalized to a domain and matched against known apps...') that Claude does not need. This matches 'mostly efficient but includes some unnecessary explanation'.	3 / 5
Actionability	Concrete, executable commands appear throughout (install, login, connection ensure, action list/run, request with a flag table), covering the common cases with clear state-machine handling. It falls short of anchor 5 only because commands rely on unfilled placeholders (CONNECTION_ID, QUERY, actionId) with no worked end-to-end example showing real values.	4 / 5
Workflow Clarity	The connect -> wait/verify -> discover -> run -> proxy-fallback sequence is clear, with explicit state-based checkpoints (READY, CLIENT_ACTION_REQUIRED, CONFIGURATION_ERROR) and a re-poll feedback loop after user action. Minor gap: the text says 'skip to Step 2' but no step is ever labeled 'Step 2', leaving the numbered flow slightly incoherent.	4 / 5
Progressive Disclosure	A single SKILL.md (~140 lines) with well-organized, clearly headed sections and no nested references to nonexistent files. Minor gaps: content like the proxy flag table and clientAction details could live in separate reference files to slim the overview, and there is no navigation to further detail at all. Good structure, matching anchor 4.	4 / 5
	Total	15 / 20 Passed

Description

57%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 has a clear trigger clause and a distinctive brand name, but its capability statement is template boilerplate that says nothing concrete about what Brandfetch actually offers. It would benefit from naming the real assets and operations (logos, colors, fonts, brand assets) that users would naturally mention.

Suggestions

Replace 'Manage data, records, and automate workflows' with Brandfetch-concrete capabilities, e.g. 'Fetch brand assets like logos, colors, fonts, and screenshots for any company domain.'

Add natural trigger terms and synonyms to the 'Use when' clause, such as 'logos', 'brand colors', 'fonts', 'brand assets', or 'company branding'.

Mention the primary input pattern (a company domain/URL) in the description so users asking about a specific brand know the skill applies.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Brandfetch integration') but its actions are generic boilerplate ('Manage data, records, and automate workflows') with no Brandfetch-concrete capabilities such as logos, colors, fonts, or brand assets. It does not reach anchor 3 because no action is concrete or specific to Brandfetch.	2 / 5
Completeness	It has both 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 of 3. It falls short of anchor 5 because the 'what' remains vague and the 'when' lacks concrete trigger phrases beyond the brand name.	4 / 5
Trigger Term Quality	'Brandfetch' and 'Brandfetch data' are natural terms a user would say, but common variations and synonyms ('brand assets', 'logos', 'colors', 'fonts', 'brand guidelines') are absent. This matches 'some relevant keywords but missing common variations or synonyms' rather than anchor 4's good coverage.	3 / 5
Distinctiveness Conflict Risk	'Brandfetch' gives it a clear niche trigger with minimal wrong-skill risk, but the generic middle sentence ('Manage data, records, and automate workflows') could overlap with sibling integration skills that share the same boilerplate template. Mostly distinct with minor overlap risk, matching anchor 4 rather than the minimal-conflict anchor 5.	4 / 5
	Total	13 / 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
Revision: f484c82

Reviewed: 16 days ago

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.

brandfetch

Table of Contents

Is this your skill?