research-brand

Researches a company from its URL and produces a Brand DNA file covering positioning, audience, competitors, voice, and messaging. Use when starting work with a new brand or customer.

Quality

96%

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

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, concisely written research workflow with clear sequencing and accuracy guardrails. The main gap is progressive disclosure: the large inline output template could be split into a referenced file so SKILL.md reads as an overview.

Suggestions

Move the brand_dna.md output template into a references/ file (e.g. references/brand_dna_template.md) and link to it from step 4 so SKILL.md serves as a lean overview.

Consider extracting the web-search query block (step 2) into references/search-queries.md, leaving the five-step process as the navigable spine.

Add a one-line pointer near the top (e.g. "See references/brand_dna_template.md for the exact file structure") so the file split is clearly signaled rather than implicit.

Dimension	Reasoning	Score
Conciseness	The body is lean throughout — it assumes Claude's competence, explains no basic concepts, and every section (crawl list, search queries, output template, rules) earns its tokens.	3 / 3
Actionability	Copy-paste search queries (e.g. "[company name]" site:crunchbase.com OR site:ycombinator.com), an exact page list, and a complete output template give concrete, executable guidance.	3 / 3
Workflow Clarity	Five clearly numbered steps with extraction checklists and an accuracy guardrail ("No fabrication ... Never guess") plus 404 handling; this is a research/synthesis task, not a destructive or batch operation, so the validation cap does not apply.	3 / 3
Progressive Disclosure	Well-organized into sections but effectively monolithic: a roughly 60-line output template is kept fully inline with no references or file-splitting, where moving it to a referenced file would let SKILL.md act as a leaner overview.	2 / 3
	Total	11 / 12 Passed

Description

100%

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 strong, concrete description that states both capability and explicit trigger conditions in third person, matching the quality of the rubric's good examples. No changes needed.

Dimension	Reasoning	Score
Specificity	"Researches a company from its URL and produces a Brand DNA file covering positioning, audience, competitors, voice, and messaging" names concrete actions (research, produce) and a specific deliverable with five named coverage areas, well above the vague anchor language.	3 / 3
Completeness	It explicitly states what it does (research a company from its URL → Brand DNA file) and when to use it ("Use when starting work with a new brand or customer"), satisfying both halves.	3 / 3
Trigger Term Quality	Natural terms a user would actually say ("brand," "customer," "company," "URL") appear alongside an explicit trigger clause, comparable to the rubric's good examples.	3 / 3
Distinctiveness Conflict Risk	It carves a clear niche (brand research from a URL into a Brand DNA file) with a distinct trigger unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: onvoyage-ai/gtm-engineer-skills
Path: research-brand/SKILL.md
Commit: 3777930

Reviewed: about 17 hours 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.