audit

Audit or critique a product flow, journey, workflow, funnel, onboarding path, checkout path, settings path, screen, or multi-step product experience by capturing screenshots first, then reporting UX, design, and accessibility findings inline from that evidence. Use Figma only when the user explicitly asks for a board. Use when the user asks to audit, review, critique, inspect, assess, analyze, evaluate, or give feedback on a product experience.

Quality

86%

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

Quality

Content

81%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, highly actionable audit workflow with strong sequencing and validation. Its main weakness is moderate redundancy in the screenshot-acceptance rules and a dense main body that could push more Figma/browser detail into references.

Suggestions

Consolidate the screenshot accept/reject guidance into one place; it is currently repeated across capture rules, screenshot source rules, and steps 5, 6, and 11.

Move the detailed Figma placement specs (200px/15-per-row/600px) and browser capture order into a reference file so the SKILL.md body stays a lean overview.

Tighten the Evidence rules and Capture rules sections, which overlap on 'use only current-run evidence' and 'do not audit until product/flow/tool are known'.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept padding, but the screenshot accept/reject rule is restated across capture rules, screenshot source rules, and steps 5/6/11, which could be consolidated.	3 / 5
Actionability	Highly concrete guidance — numbered file names like '01-start.png', explicit Figma layout values (200px spacing, new row every 15 screenshots, 600px row separation), and named checks (spinners, login walls, cookie dialogs); absence of code is acceptable for an instruction-only skill.	5 / 5
Workflow Clarity	Clear 13-step per-step sequence with explicit validation checkpoints (wait for stability, inspect before accepting, reject if blank/loading) and feedback loops (reject and recapture), plus acceptance-checks and blockers checklists.	5 / 5
Progressive Disclosure	The 'what to inspect' detail is appropriately offloaded to a real one-level reference (references/design-audit-framework.md) with clear section headers, though the body is fairly long with inlined Figma/browser detail that could be split out.	4 / 5
	Total	17 / 20 Passed

Description

91%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, third-person description that clearly conveys both capability and trigger conditions with rich natural synonyms. It is highly actionable and largely distinct, with only minor overlap risk from generic verbs.

Dimension	Reasoning	Score
Specificity	Names the product-flow domain and several concrete actions — 'capturing screenshots first, then reporting UX, design, and accessibility findings inline from that evidence' and Figma board creation — but stops short of exhaustive coverage of audit actions.	4 / 5
Completeness	Explicitly states both what ('Audit or critique a product flow... by capturing screenshots first, then reporting UX, design, and accessibility findings inline') and when ('Use when the user asks to audit, review, critique...').	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms including synonyms — 'audit, review, critique, inspect, assess, analyze, evaluate, or give feedback' — alongside concrete domain nouns (onboarding path, checkout path, funnel).	5 / 5
Distinctiveness Conflict Risk	Clear product/UX-audit niche with screenshot-based evidence and Figma boundary guidance, but broad verbs like 'review' and 'analyze' create minor overlap risk with general review skills.	4 / 5
	Total	18 / 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
relative_links	Relative link issues: 4 suspicious	Warning

	Total	15 / 16 Passed

Repository: XiaomiMiMo/MiMo-Code
Path: packages/opencode/src/skill/builtin/.bundle/product-design/workflows/audit/SKILL.md
Commit: df9f3c9

Reviewed: 1 day 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.