kentoshimizu/sw-agent-skills/design-review
Claude Code and agent skill by kentoshimizu/sw-agent-skills
- community
Checking that the SKILL.md file is still in the repository.
Run structured design reviews that produce actionable findings and clear approval decisions. Use when a design artifact needs formal review for usability, accessibility, consistency, and implementation readiness before handoff or approval; do not use for backend data-model or deployment pipeline decisions.
Install
npx vskill@latest install kentoshimizu/sw-agent-skills/design-reviewSKILL.md
The same SKILL.md was published earlier as kentoshimizu/sw-agent-skills/design-review.
Design Review
Overview
Use this skill to convert subjective design feedback into prioritized, evidence-based decisions that unblock implementation.
Scope Boundaries
- Use this skill when the task matches the trigger condition described in
description. - Do not use this skill when the primary task falls outside this skill's domain.
Shared References
- Severity calibration guidance:
references/design-review-severity-guidance.md
Templates And Assets
- Findings template:
assets/design-review-findings-template.md- Approval decision log:
assets/design-review-decision-log-template.md
Inputs To Gather
- Review target (screens, flows, interaction states) and intended users.
- Acceptance criteria and non-negotiable constraints.
- Accessibility and localization expectations for in-scope surfaces.
- Delivery timeline and risk tolerance for unresolved issues.
Deliverables
- Findings list with severity, user impact, engineering impact, and owner.
- Explicit approval decision: approved, conditional approval, or rejected.
- Remediation plan with due dates and verification method.
- Residual risk statement for any deferred non-blocker issues.
Quick Example
- Blocker: keyboard focus order breaks checkout completion.
- Major: ambiguous copy causes wrong destructive action selection.
- Minor: visual rhythm inconsistency without measurable task impact.
- Decision: reject due to blocker; re-review only affected flow after fix.
Quality Standard
- Findings are reproducible and linked to concrete evidence.
- Severity reflects impact, not reviewer preference.
- Blockers are separated from improvements and tracked independently.
- Approval decision is auditable and tied to explicit criteria.
Workflow
- Confirm review scope, criteria, and decision authority.
- Evaluate critical user journeys before secondary surfaces.
- Log findings with impact, severity, and remediation guidance in
assets/design-review-findings-template.md. - Resolve or defer issues using explicit risk acceptance rules and
references/design-review-severity-guidance.md. - Publish final decision and follow-up actions in
assets/design-review-decision-log-template.md.
Failure Conditions
- Stop when review scope or acceptance criteria are ambiguous.
- Stop when critical flows cannot be validated end-to-end.
- Escalate when blocker findings remain open near implementation handoff.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/design-review/SKILL.md
Popularity
- Repository stars
- 4
- 7-day trend score
- 8
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 29 Mar 2026, 7 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/kentoshimizu/sw-agent-skills/design-review)