brand-intel-branddev

Brand intelligence - logos, colors, fonts, styleguides, and company data from any domain

Quality

67%

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/brand/capabilities/brand-intel-branddev/SKILL.md

Quality

Content

60%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.

A strongly actionable, executable API reference with good setup error-handling, undermined by systematic parameter repetition and a monolithic structure: the entire endpoint catalog lives inline in SKILL.md with no bundle files or references to offload it. One broken curl example and no response-error guidance keep it from the top band.

Suggestions

Move the per-endpoint parameter details into a references/ file (e.g., references/endpoints.md), keeping SKILL.md as a short overview with capability summaries and one or two canonical examples, linked one level deep.

Factor shared parameters (timeoutMS, force_language, maxSpeed) into a single documented table instead of repeating them verbatim under every endpoint, cutting substantial tokens.

Fix the malformed 'Query website data using AI' curl (missing `-d '{` before the JSON body) and add brief guidance on handling common error responses (408, 422) as explicit retry/fallback steps.

Dimension	Reasoning	Score
Conciseness	The body is dense API data with no padding prose, but it repeats the identical timeoutMS parameter 12 times verbatim, plus maxSpeed (5x), force_language (7x), and re-states every capability description from the Capabilities list again under Usage. This matches anchor 3 (mostly efficient but could be tightened); it does not reach anchor 4 because the redundancy is systematic, and it avoids anchor 2 since there is no conceptual over-explanation.	3 / 5
Actionability	Nearly every endpoint ships a copy-paste-ready curl with auth headers and a populated example payload, matching anchor 4/5. It falls short of 5 because the 'Query website data using AI' curl is malformed — the JSON body ("domain": "anthropic.com", "data_to_extract"...) is broken out of the -d string with a missing opening quote — so one example is not executable as written.	4 / 5
Workflow Clarity	Setup is a clear, ordered sequence with an explicit error checkpoint (credentials missing → tell the user to run `npx gooseworks login`), and the email endpoint documents the 422 failure mode. It is below anchor 5 because there is no guidance for handling other API error responses (e.g., 408 on timeoutMS is documented only as a parameter fact, not as a retry step), and above anchor 3 because the sequence that exists is coherent with a real checkpoint.	4 / 5
Progressive Disclosure	No references/, scripts/, or assets/ directories exist, and ~260 lines of per-endpoint API reference are inlined directly in SKILL.md — exactly anchor 2's case of content that clearly belongs in separate files being inlined. The 'Discover More' section provides dynamic endpoint lookup but not structured file navigation, so it does not reach anchor 3's partial organization.	2 / 5
	Total	13 / 20 Passed

Description

61%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.

A concrete, keyword-rich description that clearly communicates the domain (brand assets from domains) without fluff. Its main gaps are the absence of any 'when to use' trigger clause and the lack of explicit action verbs, leaving it solidly mid-range rather than exemplary.

Suggestions

Add a 'Use when...' clause, e.g., 'Use when the user mentions a brand, company branding, logos, brand colors, fonts, or needs company info from a domain, email, or ticker.'

Lead with action verbs to sharpen specificity: 'Extract brand logos, colors, fonts, and styleguides, and look up company data by domain, email, company name, stock ticker, or ISIN.'

Include natural synonyms users would say — 'branding', 'brand guidelines', 'design system', 'screenshot' — to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	The description lists concrete deliverables ("logos, colors, fonts, styleguides, and company data from any domain") but uses no action verbs — the extraction/retrieval actions are only implied. It matches anchor 3 (clear domain and concrete items, but not comprehensive actions); it is below anchor 4, whose examples list several explicit actions ("Extracts text... fills forms..."), and above anchor 2, which names a domain with only generic content.	3 / 5
Completeness	The "what" is clear (brand assets and company data from a domain) but there is no "Use when..." clause or equivalent trigger guidance, capping completeness at 3 per the rubric guideline. It is not anchor 4 because the "when" is entirely absent rather than merely implicit, and it exceeds anchor 2 because the "what" is concrete, not vague.	3 / 5
Trigger Term Quality	Multiple natural keywords users would say are present ("logos", "colors", "fonts", "styleguides", "brand", "company data"), comparable to anchor 4's "PDF files, forms, document extraction". It falls short of anchor 5 because common synonyms and variations like "branding", "brand guidelines", "design system", or "screenshot" are missing, but it exceeds anchor 3's single-keyword example.	4 / 5
Distinctiveness Conflict Risk	"Brand intelligence" with logos/fonts/styleguides-from-a-domain occupies a fairly distinct niche with minimal conflict risk. It is below anchor 5 only because "company data from any domain" is broad enough to overlap with lead-enrichment or web-scraping skills; it is above anchor 3, whose examples are generically worded domain references.	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: gooseworks-ai/goose-skills
Path: skills/brand/capabilities/brand-intel-branddev/SKILL.md
Commit: cc3e518

Reviewed: 7 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.