Loading...
Loading...
Found 60 Skills
Interroge l'utilisateur sans relâche sur un plan ou un design jusqu'à atteindre une compréhension partagée, en résolvant chaque branche de l'arbre de décision. À utiliser quand l'utilisateur veut stress-tester un plan, se faire challenger sur son design, ou mentionne « grill me » / « interroge-moi » / « challenge-moi » / « questionne-moi ».
Run a 5-dimension expert design review on any HTML artifact in the project — Philosophy / Visual hierarchy / Detail / Functionality / Innovation, each scored 0–10. Outputs a single self-contained HTML report with a radar chart, evidence-backed scores, and three lists: Keep / Fix / Quick-wins. Use when the brief asks for a "design review", "design critique", "5 维度评审", "design audit", or "what's wrong with my design".
Convene 11 role-specialized Claude agents to debate technical decisions in parallel, with the invoking Claude acting as CEO
Three-phase design review. Chain architect → refiner → critique subagents. Triggers on: 'design review', 'architecture review', '/arc', system design proposals, significant refactoring decisions, new service or module design.
Surfaces and assesses hidden assumptions behind decisions, designs, or recurring patterns — use when reviewing a design before committing, reflecting on recurring problems, or questioning why the same kinds of issues keep appearing
Audit design documents for missing decisions, compatibility risks, rollout gaps, and observability omissions. Use whenever the user asks to review a design doc, architecture proposal, implementation-facing design, plan, or design-adjacent markdown file for completeness, migration strategy, rollback, data handling, or suggested additions without directly editing the document. Also trigger on short requests such as `review <file>.md` or `audit <file>.md` when the target looks like a design, plan, architecture, proposal, or decision document.
Audit a design against Dieter Rams' ten "Good design is..." principles, then hand off a /make-plan prompt for one of three outcomes — new design, refine design, or redesign. Use when the user says "audit this design", "design review", "check this UI against Rams", "is this UI good", "critique this design", "design audit", or asks for a critique that should lead to a plan.
Review healthcare and EHR software interfaces against a comprehensive design style guide grounded in NIST, FDA, IEC 62366, ISO 9241, ISO 14971, WCAG 2.1, ONC SAFER, and HL7 FHIR standards. Produces a report-only assessment without modifying code or designs. Use when an agent needs to evaluate clinical UI screens, data display, forms, alerts, or workflows for patient-safety, usability, accessibility, and data-clarity compliance.
Stress-test a plan or design through structured interviewing. Use when the user wants to pressure-test a plan, resolve design decisions, or mentions "grill me".
Validates a UX spec, HUD design, or interaction pattern library for completeness, accessibility compliance, GDD alignment, and implementation readiness. Produces APPROVED / NEEDS REVISION / MAJOR REVISION NEEDED verdict with specific gaps.
Implement reviewer feedback on a Canva design. Reads all comment threads, synthesises what reviewers want, makes the clear-cut changes directly, and flags anything that needs a human decision. Use when the user asks to "implement feedback on my deck", "address comments on a design", "apply review feedback", "fix the comments on my presentation", or "implement the feedback".
Use vision models to self-review screenshots against design intent. Catches spacing issues, alignment problems, color inconsistencies, responsive bugs, and accessibility gaps. Use when reviewing designs, comparing implementations to mockups, or doing pre-ship QA.