brand-dna-extractor

This skill should be used when users want to scrape multiple websites (Firecrawl, Parallel, or hybrid), extract brand guideline signals (including CSS variables + computed styles via browser probing), generate per-site prompt packs, and blend sources into a composite brand direction with exactly three outputs: brand_guidelines.md, prompt_library.json, design_tokens.json.

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

78%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 well-structured, actionable body for a complex multi-step skill, with real referenced bundle files and explicit validation steps. Main improvements would be tightening redundant prose and making the quality-check fix-retry loop explicit.

Suggestions

Make the step-10 quality-check feedback loop explicit (e.g. 'if a check fails, fix the offending artefact and re-run validate_outputs.py until it passes').

Trim the 'Why three prongs?' section and consolidate the repeated 'Recommended receipts' path patterns into one canonical block to reduce redundancy.

Align the inline bash example paths with the bundle layout (scripts/...) or note that the .agents/skills path is the installed location.

Dimension	Reasoning	Score
Conciseness	Mostly dense and useful with little concept-explanation padding, but sections like 'Why three prongs?' and repeated 'Recommended receipts' path patterns restate earlier content and could be trimmed.	4 / 5
Actionability	Provides concrete executable commands (the node firecrawl_branding_v2.ts invocation and `python3 .../validate_outputs.py`), named scripts (probe_css.js, blend_signals.py, normalise_tokens.py), and explicit schemas for PageArtefact and evidence objects, with only minor gaps where steps rely on prose rather than code.	4 / 5
Workflow Clarity	A clearly sequenced 10-step pipeline with explicit validation checkpoints (step 1 'Validate inputs', step 10 'Quality checks' plus validate_outputs.py) for this batch operation; the fix-and-retry feedback loop is implied but not stated as explicitly as the 5-anchor.	4 / 5
Progressive Disclosure	Well-organized overview that signals one-level-deep references to real bundle files (references/brand_guidelines_template.md, prompt_library.schema.json, design_tokens.schema.json, brand_dna_run.schema.json, scripts/*, assets/sample_config.json — all verified present), with content appropriately split and easy to navigate.	5 / 5
	Total	17 / 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.

A strong, specific description that clearly states capabilities and explicit trigger guidance with named outputs and tooling. It could be marginally improved by adding common synonyms (design tokens, brand identity) as trigger terms.

Suggestions

Add common user synonyms like 'design tokens', 'brand identity', or 'design system' to broaden natural trigger coverage.

Consider trimming the inline output-file list to keep the description tighter, since the body already documents outputs.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'scrape multiple websites (Firecrawl, Parallel, or hybrid)', 'extract brand guideline signals (including CSS variables + computed styles via browser probing)', 'generate per-site prompt packs', 'blend sources into a composite brand direction' — with comprehensive coverage and named outputs.	5 / 5
Completeness	Explicitly answers both 'what' (scrape, extract, generate prompt packs, blend) and 'when' via the 'This skill should be used when users want to...' clause with concrete trigger tasks.	5 / 5
Trigger Term Quality	Good natural-keyword coverage ('scrape multiple websites', 'brand guideline signals', 'CSS variables', 'computed styles', 'brand direction', 'prompt packs') and named output files, but misses common synonyms a user might say such as 'design system', 'brand identity', or 'design tokens' as a trigger.	4 / 5
Distinctiveness Conflict Risk	Clear niche — multi-site brand-DNA extraction with named tooling (Firecrawl, Parallel, browser probe) and three specific named outputs — giving minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 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: marchatton/agent-skills
Path: .agents/skills/00-utilities/brand-dna-extractor/SKILL.md
Commit: a0eadb2

Reviewed: 5 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.