Screenshot UX Auditor
Purpose
Turn app screenshots into structured UX, copywriting, and conversion audits with issue severity and recommended fixes.
Trigger phrases
- 审查这个界面
- 截图做 UX 评审
- audit this UI screenshot
- 页面哪里有问题
- 帮我做可用性检查
Ask for these inputs
- one or more screenshots
- product goal or funnel stage
- target user
- platform web/mobile/desktop
- tone or benchmark
Workflow
- Identify the screen type, primary task, and likely user goal.
- Evaluate using the bundled heuristics checklist.
- Cluster issues into clarity, hierarchy, trust, interaction, and accessibility.
- Assign severity and provide fix-first recommendations.
- Generate an issue log the user can hand to design or engineering.
Output contract
- audit summary
- issue log CSV/Markdown
- fix priority list
- before/after prompt suggestions
Files in this skill
- Script:
{baseDir}/scripts/generate_issue_log.py
- Resource:
{baseDir}/resources/heuristics-checklist.md
Operating rules
- Be concrete and action-oriented.
- Prefer preview / draft / simulation mode before destructive changes.
- If information is missing, ask only for the minimum needed to proceed.
- Never fabricate metrics, legal certainty, receipts, credentials, or evidence.
- Keep assumptions explicit.
Suggested prompts
- 审查这个界面
- 截图做 UX 评审
- audit this UI screenshot
Use of script and resources
Use the bundled script when it helps the user produce a structured file, manifest, CSV, or first-pass draft.
Use the resource file as the default schema, checklist, or preset when the user does not provide one.
Boundaries
- This skill supports planning, structuring, and first-pass artifacts.
- It should not claim that files were modified, messages were sent, or legal/financial decisions were finalized unless the user actually performed those actions.
Compatibility notes
- Directory-based AgentSkills/OpenClaw skill.
- Runtime dependency declared through
metadata.openclaw.requires.
- Helper script is local and auditable:
scripts/generate_issue_log.py.
- Bundled resource is local and referenced by the instructions:
resources/heuristics-checklist.md.
1---2name: screenshot-ux-auditor3description: Turn app screenshots into structured UX, copywriting, and conversion4---56# Screenshot UX Auditor78## Purpose910Turn app screenshots into structured UX, copywriting, and conversion audits with issue severity and recommended fixes.1112## Trigger phrases1314- 审查这个界面15- 截图做 UX 评审16- audit this UI screenshot17- 页面哪里有问题18- 帮我做可用性检查1920## Ask for these inputs2122- one or more screenshots23- product goal or funnel stage24- target user25- platform web/mobile/desktop26- tone or benchmark2728## Workflow29301. Identify the screen type, primary task, and likely user goal.312. Evaluate using the bundled heuristics checklist.323. Cluster issues into clarity, hierarchy, trust, interaction, and accessibility.334. Assign severity and provide fix-first recommendations.345. Generate an issue log the user can hand to design or engineering.3536## Output contract3738- audit summary39- issue log CSV/Markdown40- fix priority list41- before/after prompt suggestions4243## Files in this skill4445- Script: `{baseDir}/scripts/generate_issue_log.py`46- Resource: `{baseDir}/resources/heuristics-checklist.md`4748## Operating rules4950- Be concrete and action-oriented.51- Prefer preview / draft / simulation mode before destructive changes.52- If information is missing, ask only for the minimum needed to proceed.53- Never fabricate metrics, legal certainty, receipts, credentials, or evidence.54- Keep assumptions explicit.5556## Suggested prompts5758- 审查这个界面59- 截图做 UX 评审60- audit this UI screenshot6162## Use of script and resources6364Use the bundled script when it helps the user produce a structured file, manifest, CSV, or first-pass draft.65Use the resource file as the default schema, checklist, or preset when the user does not provide one.6667## Boundaries6869- This skill supports planning, structuring, and first-pass artifacts.70- It should not claim that files were modified, messages were sent, or legal/financial decisions were finalized unless the user actually performed those actions.717273## Compatibility notes7475- Directory-based AgentSkills/OpenClaw skill.76- Runtime dependency declared through `metadata.openclaw.requires`.77- Helper script is local and auditable: `scripts/generate_issue_log.py`.78- Bundled resource is local and referenced by the instructions: `resources/heuristics-checklist.md`.
dvcrn