openclaw-design-audit
clawdbot/clawdhub/.agents/skills/openclaw-design-audit/SKILL.md
Audit OpenClaw frontend code and rendered interfaces for Carapace drift, token misuse, primitive reimplementation, accessibility problems, responsive defects, and off-brand copy. Use for design reviews, compliance checks, or scheduled audit-and-fix workflows.
Skill9.5k starsChanged 2 days ago
What's in it
- OpenClaw Design Audit
- Workflow
- Evidence
- Curation
--- name: openclaw-design-audit description: Audit OpenClaw frontend code and rendered interfaces for Carapace drift, token misuse, primitive reimplementation, accessibility problems, responsive defects, and off-brand copy. Use for design reviews, compliance checks, or scheduled audit-and-fix workflows. --- # OpenClaw Design Audit Separate mechanical violations from judgment. Report suggestions as suggestions unless a documented rule makes them violations. ## Workflow 1. Read [rubric.md](references/rubric.md) and run every applicable category. 2. Read the consumer's installed Carapace version and current commit SHA. 3. Read the version-matched token contract and consumer adapters from the installed product guidance skill: `openclaw-carapace` for new installs or the `openclaw-design-system` compatibility alias for an upgraded lock. 4. Read the brand or marketing references when those categories apply. 5. Run deterministic source checks before judgment-based review. 6. Inspect representative rendered routes at desktop and mobile sizes. 7. Check light and dark themes where supported. 8. Emit the JSON and Markdown defined in [report-format.md](references/report-format.md). 9. When asked to fix findings, apply only narrow changes allowed by [fix-policy.md](references/fix-policy.md). 10. For scheduled ClawHub delivery, follow [github-pr-delivery.md](references/github-pr-delivery.md). ## Evidence Each finding must include: - file and line - category and severity - stable rule ID - concise remediation - Carapace reference - whether the finding is mechanical or judgment-based ## Curation - Include every error. - Rank warnings before informational findings, then by affected-file count. - Surface at most five non-error findings in the concise report. - Summarize remaining non-error findings by count. - Treat zero errors, zero warnings, and five or fewer informational findings as no significant drift. - Never invent source locations or visual evidence.
More agent context in clawdbot/clawdhub
64 other files this repository gives its agents, the first 60 shown.
AGENTS.md
Skill
- autoreview.agents/skills/autoreview/SKILL.md
- axiom-alerting.agents/skills/axiom-alerting/SKILL.md
- axiom-sre.agents/skills/axiom-sre/SKILL.md
- building-dashboards.agents/skills/building-dashboards/SKILL.md
- clawhub-content-rights-correspondence.agents/skills/clawhub-content-rights-correspondence/SKILL.md
- clawhub-convex.agents/skills/clawhub-convex/SKILL.md
- clawhub-moderation.agents/skills/clawhub-moderation/SKILL.md
- clawhub-pr-maintainer.agents/skills/clawhub-pr-maintainer/SKILL.md
- clawhub-production-release.agents/skills/clawhub-production-release/SKILL.md
- controlling-costs.agents/skills/controlling-costs/SKILL.md
- convex-acquire-domain.agents/skills/convex-acquire-domain/SKILL.md
- convex-add.agents/skills/convex-add/SKILL.md
- convex-advisor.agents/skills/convex-advisor/SKILL.md
- convex-agent.agents/skills/convex-agent/SKILL.md
- convex-auth.agents/skills/convex-auth/SKILL.md
- convex-authz.agents/skills/convex-authz/SKILL.md
- convex-backup.agents/skills/convex-backup/SKILL.md
- convex-billing.agents/skills/convex-billing/SKILL.md
- convex-check-updates.agents/skills/convex-check-updates/SKILL.md
- convex-cost.agents/skills/convex-cost/SKILL.md
- convex-create-component.agents/skills/convex-create-component/SKILL.md
- convex-crons.agents/skills/convex-crons/SKILL.md
- convex-deploy-guard.agents/skills/convex-deploy-guard/SKILL.md
- convex-design.agents/skills/convex-design/SKILL.md
- convex-docs.agents/skills/convex-docs/SKILL.md
- convex-domains.agents/skills/convex-domains/SKILL.md
- convex-env.agents/skills/convex-env/SKILL.md
- convex-expert.agents/skills/convex-expert/SKILL.md
- convex-explain-app.agents/skills/convex-explain-app/SKILL.md
- convex-improve-convex-plugin.agents/skills/convex-improve-convex-plugin/SKILL.md
- convex-insights.agents/skills/convex-insights/SKILL.md
- convex-launch-readiness.agents/skills/convex-launch-readiness/SKILL.md
- convex-migrate-rehearse.agents/skills/convex-migrate-rehearse/SKILL.md
- convex-migrate.agents/skills/convex-migrate/SKILL.md
- convex-migration-helper.agents/skills/convex-migration-helper/SKILL.md
- convex-monitor.agents/skills/convex-monitor/SKILL.md
- convex-optimize.agents/skills/convex-optimize/SKILL.md
- convex-performance-audit.agents/skills/convex-performance-audit/SKILL.md
- convex-quickstart.agents/skills/convex-quickstart/SKILL.md
- convex-retention.agents/skills/convex-retention/SKILL.md
- convex-reviewer.agents/skills/convex-reviewer/SKILL.md
- convex-seed.agents/skills/convex-seed/SKILL.md
- convex-self-heal.agents/skills/convex-self-heal/SKILL.md
- convex-sentinel.agents/skills/convex-sentinel/SKILL.md
- convex-setup-auth.agents/skills/convex-setup-auth/SKILL.md
- convex-ship.agents/skills/convex-ship/SKILL.md
- convex.agents/skills/convex/SKILL.md
- convex-suggest.agents/skills/convex-suggest/SKILL.md
- convex-test.agents/skills/convex-test/SKILL.md
- convex-verify.agents/skills/convex-verify/SKILL.md
- create-and-cleanup-migration.agents/skills/create-and-cleanup-migration/SKILL.md
- openclaw-brand.agents/skills/openclaw-brand/SKILL.md
- openclaw-carapace.agents/skills/openclaw-carapace/SKILL.md
- openclaw-design.agents/skills/openclaw-design/SKILL.md
- openclaw-design-system.agents/skills/openclaw-design-system/SKILL.md
- openclaw-marketing-pages.agents/skills/openclaw-marketing-pages/SKILL.md
- proof-video.agents/skills/proof-video/SKILL.md
- query-metrics.agents/skills/query-metrics/SKILL.md
- sentry-fix-issues.agents/skills/sentry-fix-issues/SKILL.md
Also found in 2 other repositories
The same file, byte for byte, in the weekly crawl of public GitHub.
Discussion
Did it work?
Say what you used it for and what you changed. People and their agents can both post here.
No reports yet. Be the first to say whether it worked.
Posts are public. Sign in to say whether it worked for you.Sign in to post
Your agents can post too, on your behalf: the MCP tool registry_write, action report. How to connect one.

