Agent skill

Improve UI Audit and Plans

by ibelick in ibelick/ui-skills

Audits one product surface against its own design evidence and writes self-contained implementation plans for another agent, without touching product source.

MITAuto-check passedFrontend & Design

Install Improve UI Audit and Plans

skills CLI
$ npx skills add ibelick/ui-skills --skill improve-ui -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ibelick/ui-skills improve-ui --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ibelick/ui-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/improve-ui .claude/skills/improve-ui && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
improve-ui
GitHub stars
9.4k
Token cost
~2k tokens
SKILL.md length
950 words
Files
3 (incl. references)
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Audits one product surface against its own design evidence and writes self-contained implementation plans for another agent, without touching product source.

  • Works in 6 steps: Select the surface → Reconstruct the local system → Prove findings → …
  • Auditing an existing interface for verified UI problems without redesigning it
  • SKILL.md covers Boundaries, 1. Select the surface, 2. Reconstruct the local system and 3. Prove findings, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The skill audits one coherent surface against the system that actually governs it, preserving the product's identity, reusing existing owners and preferring no finding to an unsupported one. It is strictly read-only on product source: files are created or edited only under design-plans/, nothing is installed, formatted, committed or pushed, and design documentation is not updated. Rendered evidence is used only when you provide it or ask for visual inspection.

The agent first selects the surface, honoring your scope or, for a broad request, picking one deployable application and one surface family. It then traces the rendered path from routes and layouts through compositions, shared components, variants, resolved tokens and styles. A connection counts only when proven through rendering, imports, props, resolved configuration, CSS inheritance or a generated artifact. Next it reconstructs the local design system from DESIGN.md and similar sources, using one only after confirming it is current, and a missing design document is not itself a finding.

Plans are written only for the changes you select, and each must be self-contained because its executor has no context from the audit or the conversation. A plan template reference ships with the skill.

When your agent uses it

  • Auditing an existing interface for verified UI problems without redesigning it
  • Investigating design-system drift on a screen or surface family
  • Preparing a design handoff plan for another agent to implement

Example prompts

  • “Audit the checkout flow for design-system drift and write plans for the findings I pick.”
  • “Review the settings screens and tell me which UI problems you can prove from the code.”
  • “Prepare a self-contained plan for fixing the spacing and button variants on the dashboard.”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Select the surface
  2. Reconstruct the local system
  3. Prove findings
  4. Vet findings
  5. Report
  6. Specify selected changes

What it can do on your machine

Read from SKILL.md and the folder at commit 74da992. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Improve UI Audit and Plans loads about 2k tokens when it runs, and up to ~2.4k if it reads all its reference files. Until then it costs about 93 tokens; SKILL.md has 950 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~93
When it runs · the whole SKILL.md, loaded when a task matches
~2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ibelick/ui-skills at commit 74da992, republished under its MIT licence (© ibelick). 950 words, ~1,954 tokens.

Download SKILL.mdSave it as .claude/skills/improve-ui/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
improve-ui
description
Audit an existing product surface against its own design evidence, identify verified UI problems, and write self-contained implementation plans for another agent. Strictly read-only on product source. Use when asked to review, refine, improve, or clean up an interface without replacing its identity; investigate design-system drift; or prepare a design handoff.

Improve UI

Audit one coherent product surface against the system that actually governs it. Preserve the product's identity, reuse existing owners, and prefer no finding to an unsupported one. Write plans only for changes the user selects; another agent executes them.

Boundaries

  • Never modify product source. Create or edit files only under design-plans/.
  • Do not install dependencies, run formatters, commit, push, or otherwise mutate the working tree.
  • Do not update design documentation. Record accepted documentation changes in the plan for its executor.
  • Use rendered evidence only when the user provides it or explicitly requests visual inspection.
  • Make every plan self-contained; its executor has no context from the audit or conversation.

1. Select the surface

Honor the user's scope. If the request is broad, select one deployable application and one coherent surface family representing a primary product task. State the selection; do not synthesize the whole repository into one product.

Start from the surface's routes and layouts. Trace the rendered path through compositions, shared components, variants, resolved tokens, and styles. Do not begin with a repository-wide search for inconsistencies.

A connection exists only when it is proven through rendering, imports, props, resolved configuration, CSS inheritance, or a generated artifact loaded by the surface. Shared names, similar tokens, repository proximity, and conceptual relationships do not establish a connection. Exclude other applications, previews, configurators, generated registries, legacy systems, and enterprise variants unless they participate in the traced path.

2. Reconstruct the local system

Check for DESIGN.md, repository guidance, and surface-local design documentation. Use a source only after proving it is current and governs the selected surface; drafts, proposals, migrations, and task lists describe future intent unless explicitly accepted and current. Absence of design documentation is not a finding.

Inspect only the tokens, variables, themes, primitives, variants, and compositions relevant to the traced path. Resolve aliases and variants to their definitions. Classify an implementation as local or legacy only when the repository says so.

Record:

markdown
## Design language
- Audited surface:
- Design sources:
- Documented decisions:
- Governing owners and consumers:
- Explicit exceptions:

Write None documented under Explicit exceptions unless a cited source explicitly identifies the exception.

3. Prove findings

Before applying the proof gate, inspect every traced surface's user-facing labels, active-state presentation, responsive branches, and sibling variants for internal contradictions. Treat the results only as candidates.

A finding is in scope only when its correction primarily changes visual presentation, interface copy, layout, component styling, or conformance to a documented design rule. If the correction primarily changes whether product behavior works, reject it.

Search results, repetition, and implementation differences produce candidates, not findings. Keep a candidate only when all three proofs exist:

  1. Contract — Cite a binding design decision for this property and scope, or a direct contradiction in user-facing presentation or content within the same task. “Prefer,” “generally,” names, omissions, repetition, and absence of an exception do not establish a contract.
  2. Runtime — Prove that the cited owner, value, or behavior reaches the affected surface through the traced runtime path. Do not compare separate ownership layers or lifecycle states.
  3. Correction — State one change required by the evidence. If it depends on an existing token, variant, primitive, or exemplar, name it exactly. If the evidence cannot determine the correct choice, the intended condition is ambiguous, the proposal contains alternatives, or the correction requires inventing product intent, reject the candidate.

Source can prove token, typography, color, spacing, layout, copy, component-variant, responsive-presentation, and explicit design-contract violations. It cannot turn functional behavior, state management, or interaction correctness into design findings. Hierarchy, prominence, density, clarity, discoverability, usability, and perceived coherence require rendered or user evidence.

Discard accessibility and HTML/ARIA semantic findings unless the user explicitly requests them. Discard broken routes, redirects, data wiring, action failures, metadata, package API, performance, architecture, and code-quality findings unless the user requested them or a product-specific design contract governs them.

Assign confidence only after all proofs pass. Reuse an existing owner when the evidence supports it; do not create a shared primitive from repetition alone.

Show full SKILL.md (305 more words)Show less

4. Vet findings

Before reporting, re-open every cited source and try to falsify each candidate. Delete it when:

  • The problem does not exactly match the cited implementation.
  • The rule does not govern that property and surface.
  • Counterevidence shows the difference is valid or deliberate.
  • The evidence supports multiple corrections.
  • The correction invents product intent.
  • Another finding describes the same root problem.

Only findings that survive this pass may enter the table.

5. Report

Order surviving findings by confidence, user impact, reach, and correction cost. Stop at three.

Use this structure:

markdown
## Design language
- Audited surface:
- Design sources:
- Documented decisions:
- Governing owners and consumers:
- Explicit exceptions:

## Findings
| # | Problem | Evidence | Proposed change | Scope | Confidence |
| --- | --- | --- | --- | --- | --- |

## Improve first
<Highest-leverage finding and why, or no supported recommendation.>

Evidence must establish the contract, runtime relationship, and deterministic interface consequence. Proposed change must contain one correction. Delete unsupported or overlapping rows before returning.

Delete any finding that does not include every required column, including Confidence.

Under Improve first, select one surviving finding with the strongest evidence and highest leverage. Never combine findings.

If no candidate survives, write No supported findings were found. under ## Findings and No supported recommendation. under ## Improve first.

If findings survive, stop and ask which to turn into plans. If the user already selected a finding or explicitly requested a plan for a described improvement, continue with that scope. If asked to fix or improve directly, offer a plan; never implement it.

6. Specify selected changes

Read references/plan-template.md. Write one plan per selected change, never one per symptom.

Before writing, re-open every cited source, record the current commit when available, identify exact reusable primitives and exemplars, and trace affected surfaces. Reconcile an existing plan instead of duplicating it.

Do not invent values when the repository provides a token or component contract. Introduce a primitive only after proving why the existing system cannot express the decision and which consumers should share it.

If asked to reconcile, recheck existing plans against current source and documented decisions; update stale evidence, affected surfaces, and status.

© ibelick, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in skills/improve-ui of ibelick/ui-skills.

  • SKILL.md
  • agents/openai.yaml
  • references/plan-template.md

Open the folder on GitHubat commit 74da992

Compare with similar skills

Improve UI Audit and Plans next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Improve UI Audit and Plans compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Improve UI Audit and Plans this skillibelick/ui-skills9.4k—~2kAutomated safety check: PassMIT
Spec WorkflowLeoYeAI/openclaw-master-skills2.2k1 repos~1.4kAutomated safety check: PassMIT
UI StylingOhh-889/skyroc79513 repos~2.5kAutomated safety check: PassMIT
Stitch Prompt Enhancergoogle-labs-code/stitch-skills8.4k6 repos~1.7kAutomated safety check: PassApache-2.0
Design Dnazanwei/design-dna1.9k1 repos~2.1kAutomated safety check: PassMIT
Creative Tim UI Blockscreativetimofficial/ui12k—~2.1kAutomated safety check: NotesMIT

Similar skills

  • Spec Workflow

    LeoYeAI/openclaw-master-skills

    Standard software engineering workflow for requirement analysis, technical design, and task planning.

    2.2k GitHub starsUsed in 1 repo~1.4k tokens
    Frontend & DesignAuto-check passed
  • UI Styling

    Ohh-889/skyroc

    Create beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs.

    795 GitHub starsUsed in 13 repos~2.5k tokens
    Frontend & DesignAuto-check passed
  • Stitch Prompt Enhancer

    google-labs-code/stitch-skills

    Official

    Rewrites a vague UI generation idea into a structured, keyword-rich prompt for Stitch, pulling in an existing DESIGN.md design system when the project has one.

    8.4k GitHub starsUsed in 6 repos~1.7k tokens
    Frontend & DesignAuto-check passed
  • Design Dna

    zanwei/design-dna

    Extract, define, and apply design DNA across three dimensions: design system (tokens), design style (qualitative feel), and visual effects (Canvas, WebGL, 3D, particles, shaders, scroll effects…

    1.9k GitHub starsUsed in 1 repo~2.1k tokens
    Frontend & DesignAuto-check passed
  • Creative Tim UI Blocks

    creativetimofficial/ui

    Helps install, generate and review Creative Tim UI blocks: shadcn/ui-based React and Tailwind sections that follow a restrained, production-minded design philosophy.

    12k GitHub stars~2.1k tokensUpdated 6 mo ago
    Frontend & DesignAuto-check: notes
  • Official daisyUI skill for Tailwind CSS projects, routing to install, usage, configuration, color and per-component guides before writing any HTML or JSX with its classes.

    43k GitHub stars~1.3k tokensUpdated 7 days ago
    Frontend & DesignAuto-check passed

More from ibelick/ui-skills

  • Fixing Motion Performance

    ibelick/ui-skills

    Audits and fixes web animation performance: layout thrashing, work that belongs on the compositor, scroll-linked motion and costly blur effects.

    9.4k GitHub starsUsed in 5 repos~1.4k tokens
    Auto-check passed
  • Accessibility Fixer

    ibelick/ui-skills

    Audits and fixes HTML accessibility problems such as ARIA labels, keyboard navigation, focus management, contrast and form errors with minimal changes.

    9.4k GitHub starsUsed in 4 repos~1.2k tokens
    Auto-check passed
  • Baseline UI

    ibelick/ui-skills

    Applies a fixed set of UI rules for stack, components, interaction, animation, typography and layout, or reviews a file against them with concrete fixes.

    9.4k GitHub starsUsed in 8 repos~855 tokens
    Auto-check passed
  • HTML Metadata Fixer

    ibelick/ui-skills

    Audits and fixes page titles, meta descriptions, canonical URLs, Open Graph and Twitter cards, favicons, JSON-LD and robots directives.

    9.4k GitHub starsUsed in 2 repos~1.1k tokens
    Auto-check passed
  • DESIGN.md Creator

    ibelick/ui-skills

    Writes or updates a DESIGN.md for one product from its repository or a public URL, recording the design language and tokens that the evidence supports.

    9.4k GitHub stars~4k tokensUpdated today
    Auto-check passed
  • UI Skills Router

    ibelick/ui-skills

    Routes UI tasks to the smallest useful set of UI Skills through the ui-skills CLI, picking a category and loading at most three skills before implementing.

    9.4k GitHub starsUsed in 2 repos~362 tokens
    Auto-check passed

Questions about Improve UI Audit and Plans

What does Improve UI Audit and Plans do?

Audits one product surface against its own design evidence and writes self-contained implementation plans for another agent, without touching product source. The skill audits one coherent surface against the system that actually governs it, preserving the product's identity, reusing existing owners and preferring no finding to an unsupported one. It is strictly read-only on product source: files are created or edited only under design-plans/, nothing is installed, formatted, committed or pushed, and design documentation is not updated.

When should I use Improve UI Audit and Plans?

Improve UI Audit and Plans fits situations like: auditing an existing interface for verified UI problems without redesigning it; investigating design-system drift on a screen or surface family; preparing a design handoff plan for another agent to implement.

How do I install Improve UI Audit and Plans in Claude Code?

Run `npx skills add ibelick/ui-skills --skill improve-ui -a claude-code`. Or copy the skill folder (skills/improve-ui in ibelick/ui-skills) into .claude/skills/improve-ui in your project. Claude Code loads it when a task matches its description.

How do I install Improve UI Audit and Plans in Codex?

Run `npx skills add ibelick/ui-skills --skill improve-ui -a codex`. Or copy the skill folder (skills/improve-ui in ibelick/ui-skills) into .agents/skills/improve-ui in your project. Codex loads it when a task matches its description.

Can I use Improve UI Audit and Plans in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ibelick/ui-skills --skill improve-ui -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/improve-ui, .gemini/skills/improve-ui, .github/skills/improve-ui and .opencode/skills/improve-ui in your project.

What does Improve UI Audit and Plans need to run?

SKILL.md names no scripts, command-line tools or credentials: Improve UI Audit and Plans is instructions for the agent only.

Does Improve UI Audit and Plans access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Improve UI Audit and Plans safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Improve UI Audit and Plans use?

Improve UI Audit and Plans is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Improve UI Audit and Plans use?

About 2k tokens (SKILL.md is roughly 7.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 398 tokens, read only when the agent opens those files.

What are the alternatives to Improve UI Audit and Plans?

Skills that share tags, products or a category with Improve UI Audit and Plans: Spec Workflow (LeoYeAI/openclaw-master-skills, 2.2k stars), UI Styling (Ohh-889/skyroc, 795 stars), Stitch Prompt Enhancer (google-labs-code/stitch-skills, 8.4k stars) and Design Dna (zanwei/design-dna, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Improve UI Audit and Plans?

ibelick (a GitHub user) maintains it in ibelick/ui-skills, which has 9,437 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 6, 2026.

Source: ibelick/ui-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.