agentleFS
Sign inStart free
Dragoon0xDragoon0x/10x-interface/skills/interface-review/SKILL.md

interface-review

Skill0 starsChanged 2 months agoMITView on GitHub

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.

We split this skill into the rules it gives an agent

8 rules. 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 13 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

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

    line 22
  2. Distinctive:

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

    line 49
  3. Distinctive:

    Do not manufacture findings to fill a quota.

    line 62
  4. Very specific:

    Use the reference artifact belonging to the discipline under review: ../interface-architecture/references/architecture-review.md, …

    line 74
  5. Very specific:

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

    line 78
  6. Distinctive:

    BLOCK: when a release-critical finding remains.

    line 86
  7. Distinctive:

    NEEDS CHANGES: when actionable non-blocking findings remain.

    line 87
  8. Distinctive:

    APPROVE: when no actionable finding remains and claimed coverage is credible.

    line 88

“Common” is measured: kept by at least 6 in 10 of the 13 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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.

Download now (ZIP)

  • Other versions13 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 13

    1. jakubkrehel/skills★ 9.7ksame name
    2. talebook/talebook★ 5.9ksame name
    3. Atharvsinh-codez/ObsidianUI★ 562same name
    4. boraoztunc/skills★ 337same name
    5. 0xPasho/agentcut★ 21same name
    6. hsynozdamar-byte/claude-skills-edited★ 4same name
    7. sanmidable/skills★ 2same name
    8. AnasX7/skills★ 1same name
    9. cill-i-am/skills★ 1same name
    10. ElyzeSolutions/skills★ 1same name

    3 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use apple-design, emil-design-eng and 3 more.

    Other files people use alongside this one.

    Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
    • ozgureyilmazSkill

      apple-design

      Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading), reduced-motion, or the design foundations (feedback, spatial consistency, restraint) behind Apple-style interfaces.

      Also in 3 projects that use this

    • VercelSkill

      emil-design-eng

      This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.

      Also in 3 projects that use this

    • VercelSkill

      web-design-guidelines

      Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

      Also in 4 projects that use this

    • MicrosoftSkill

      impeccable

      Use when the user wants to design, redesign, shape, critique, audit, polish, simplify, harden, animate, or otherwise improve a frontend interface: websites, landing pages, dashboards, product UI, components, forms, settings, onboarding, empty states, and native iOS or Android screens. Handles UX review, hierarchy, layout, typography, color, motion, UX copy, accessibility, responsive behavior, edge cases, and capturing or documenting design systems (DESIGN.md, tokens). Also for making bland UI bolder, loud UI quieter, or ambitious visual effects. Not for backend-only or non-UI tasks.

      Also in 3 projects that use this

    • BlockSkill

      frontend-design

      Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

      Also in 4 projects that use this

  • In this repository10 other files it gives its agents.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free