# Interface Review

> Run a unified evidence-driven review of an interface, change, flow, or product surface by coordinating the 10X Interface disciplines and producing one consolidated decision.

- Skill: `dragoon0x/interface-review` (Agent Skill)
- Install (CLI): `npx skillmds@latest add dragoon0x/interface-review`
- Raw SKILL.md: https://api.skillmd.com/api/skills/dragoon0x/interface-review/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: dragoon0x (https://skillmd.com/u/dragoon0x)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/dragoon0x/interface-review

---


# Interface Review

## Mission

Review the interface as one system rather than producing disconnected specialist reports.

The result should reveal what is strong, what is weak, what causes the weakness, what evidence supports it, and whether the work is ready to proceed.

## Modes

### Focused
Inspect the primary task and highest-risk states. Report meaningful findings only.

### Full
Inspect the complete requested scope across architecture, craft, interaction, adaptation, states, accessibility, and implementation evidence.

If the requested scope is too large to inspect credibly, narrow it and state the boundary.

## Review order

1. Resolve scope and intent.
2. Inspect existing architecture and conventions.
3. Evaluate information and structure.
4. Evaluate visual craft.
5. Evaluate interaction behavior.
6. Evaluate adaptation.
7. Stress reachable states.
8. Inspect implementation evidence.
9. Consolidate systemic findings.
10. Verify.
11. Issue a verdict.

## Evidence rule

A finding needs evidence appropriate to its claim.

- Source claim: cite source location.
- Visual claim: inspect rendered UI.
- Interaction claim: exercise the interaction.
- State claim: reach or deliberately reproduce the state.
- Accessibility claim: perform the relevant check.
- Performance claim: measure or label unverified.

Never infer runtime behavior from source alone when runtime behavior determines the result.

## Consolidation

One root cause is one finding. If one system decision creates symptoms in several places, consolidate them and list affected locations.

## Severity

- **BLOCKER**: release-critical, unsafe, inaccessible, or core-task failure.
- **HIGH**: materially damages a core workflow or systemic behavior.
- **MEDIUM**: meaningful comprehension, efficiency, adaptability, accessibility, or consistency issue.
- **LOW**: isolated polish.

Do not manufacture findings to fill a quota.

## Alternatives

Record credible changes considered and rejected because they were unnecessary, unsupported by evidence, inconsistent with the system, or more complex than their benefit.

## Coverage

State scope, surfaces, states, contexts, domains, evidence, and unverified areas. Never imply an uninspected surface was reviewed.

## Reference artifacts

Use the reference artifact belonging to the discipline under review: `../interface-architecture/references/architecture-review.md`, `../interface-craft/references/craft-review.md`, `../interaction-engine/references/interaction-review.md`, `../adaptive-interface/references/adaptation-matrix.md`, or `../state-forge/references/state-report.md`.

## Output

Use `../interface-critic/references/review-output.md` as the consolidated report shape.

## Review safety

A review is read-only unless implementation is explicitly requested. Do not alter the working tree simply to inspect a change.

## Verdict

- **BLOCK** when a release-critical finding remains.
- **NEEDS CHANGES** when actionable non-blocking findings remain.
- **APPROVE** when no actionable finding remains and claimed coverage is credible.

## Completion criteria

The review is complete when the interface has one coherent evidence-backed diagnosis rather than disconnected specialist opinions.