brand-research

Research a company or brand from its website and produce a reusable Brand Core covering products, audience, competitors, positioning, offers, messaging evidence, voice, and visual identity. Use before growth, ad, content, creator, or product work when reliable brand context is missing.

Quality

85%

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

77%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 well-sequenced, actionable research workflow with validation checkpoints and a concrete output contract. Its main weakness is progressive disclosure: bundle files exist but are not referenced from SKILL.md and their structure is inconsistent with the inline spec.

Suggestions

Link the bundle files from the body — e.g., under 'Brand Core output' add 'See references/output-contract.md for the normative file/manifest shape' and reference scripts/verify_pack.py in the Quality checks step.

Reconcile the inline output tree with references/output-contract.md so filenames match (summary.md vs brand-summary.md, sources.md vs asset-urls.md) to avoid contradicting the normative contract.

Tighten the repeated 'optional/paid extensions are not prerequisites' messaging so it appears once, reducing token redundancy across the intro and steps 8–9.

Dimension	Reasoning	Score
Conciseness	The body is lean and directive with no over-explanation of known concepts, but the 'optional/paid extensions are not prerequisites' point is restated across the intro and steps 8–9, leaving minor trimmable repetition; fits the 'efficient, minor instances that could be trimmed' anchor rather than a fully lean 5.	4 / 5
Actionability	Provides concrete per-file content specs, a copy-paste-ready JSON schema, named companion skills, and a quality checklist; as an instruction-only research skill this is actionable, but there are no runnable commands for the research itself and minor gaps in execution detail, matching the 'mostly executable guidance with minor gaps' anchor.	4 / 5
Workflow Clarity	A clearly sequenced 9-step workflow with explicit checkpoints: step 1 ambiguity guard, step 7 confirmation summary with low-confidence marking, and a closing Quality checks checklist; this matches the 'clear sequence with explicit validation steps and checklists' anchor.	5 / 5
Progressive Disclosure	The body is well-sectioned but never links or signals the provided bundle files (references/output-contract.md and scripts/*.py), and the body's output tree diverges from output-contract.md (e.g., summary.md vs brand-summary.md), fitting the 'references present but not clearly signaled' anchor rather than 4.	3 / 5
	Total	16 / 20 Passed

Description

92%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 specific, third-person, and explicitly pairs a concrete 'what' with a trigger-rich 'when' clause, yielding strong completeness and distinctiveness. The only minor gap is trigger-term breadth, where a few common synonyms could be added.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Research a company or brand from its website and produce a reusable Brand Core') with comprehensive coverage of eight named areas (products, audience, competitors, positioning, offers, messaging evidence, voice, visual identity), matching the comprehensive-coverage anchor; not below 5 because no concrete actions are missing.	5 / 5
Completeness	Explicitly answers both 'what' (research + produce a Brand Core covering eight areas) and 'when' ('Use before growth, ad, content, creator, or product work when reliable brand context is missing') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural user phrases ('growth, ad, content, creator, or product work', 'brand context is missing') with good coverage, but stops short of comprehensive synonyms (e.g., marketing, campaign, competitive analysis), fitting the 'good coverage, a few natural terms missing' anchor rather than 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (brand research producing a reusable Brand Core artifact) with distinct triggers tied to missing brand context, giving minimal overlap with other skills; fits the 'clear niche with distinct triggers' anchor.	5 / 5
	Total	19 / 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/ads/composites/brand-research/SKILL.md
Commit: 2523432

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.