← ClaudeAtlas

product-auditlisted

Audit an existing product interface for evidence-backed UI, UX, accessibility, and copy findings at low, medium, or high depth. Use only when the user explicitly invokes $product-audit for a read-only review of a screen, flow, feature, live product, design artifact, or implementation. Not for implementing fixes, redesigning the product, writing back to design tools, or changing code.
martonpaulo/skills · ★ 1 · AI & Automation · score 71
Install: claude install-skill martonpaulo/skills
# Product Audit Assess the product as one user experience and return a prioritized report in the conversation. Never mutate the product, repository, design file, issue tracker, or audit inputs. ## Depth router Treat the first argument as the depth and the remaining arguments as the scope. Default to `medium` when the depth is omitted. | Depth | Required sources | Coverage | Finding cap | | --- | --- | --- | --- | | `low` | [`core-review.md`](references/core-review.md) | Breadth-first UI, UX, accessibility, and copy pass over the primary path | 5; `HIGH` and `MEDIUM` only | | `medium` | Core + [`ux-writing.md`](references/ux-writing.md) | Low plus a dedicated microcopy and content-usability pass across key states | 10 | | `high` | Core + writing + [`deep-critique.md`](references/deep-critique.md) | Medium plus flow completeness, stage-aware critique, counteranalysis, and systemic synthesis | 15 findings plus up to 5 grounded gaps | Load only the references required by the selected depth. A lower depth narrows coverage; it never relaxes evidence, safety, or confidence requirements. The routing preserves the requested source split: the core pass adapts `jakubkrehel/skills`, the writing pass adapts `content-designer/ux-writing-skill`, and the deep pass adapts `Thecsiz/ux-critique`. If the requested scope is too large to inspect credibly, select the highest-risk complete user flow, state the boundary before judging it, and list the unreviewed surfaces. Never imply full-prod