polish

A review and refinement pass for an application's visual interface before release. It checks the running app for issues with layout, text, spacing, motion, responsiveness, visibility, and contrast.

In plain words
What is it for?
Use it to inspect and refine a frontend after implementation and quality checks, before deployment. It helps fix inconsistent spacing, missing hover states, typography issues, contrast problems, and responsive layout defects.
Why use it?
It helps turn an app that works but looks unfinished into a more consistent interface. It catches visual problems that functional tests may miss.

Skill for Claude CodeCodex

Part of the transmuter plugin — 23 skills, 1 command, 7 agents shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/voxtechnologies/transmute-framework/polish
Any agent
npx skills add VoxTechnologies/transmute-framework --skill polish
Clone the repo
git clone --depth 1 https://github.com/VoxTechnologies/transmute-framework

Made for: Claude Code, Codex.

Or install transmuter, the plugin that ships this one along with the rest of its 23 skills, 1 command, 7 agents.

Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,888 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00099 $0.03888
Opus 5 $0.00049 $0.01944
Sonnet 5 $0.00020 $0.00778
Haiku 4.5 $0.00010 $0.00389

Measured 3d ago against content hash 55e42cf68b3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

polish scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/polish/SKILL.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stage 6P: Visual Polish & UI Refinement

Why This Stage Exists

After Stage 5 implementation and Stage 6 quality passes, the product is functionally complete but often looks "functional rather than polished." Components work correctly but lack the visual refinement that distinguishes a production product from a prototype — inconsistent spacing, missing hover states, contrast issues, and generic typography. This stage transforms a functionally correct app into a visually distinctive product. It runs AFTER 6R (all mechanical issues fixed) and BEFORE deployment.

Analyze the RUNNING application's visual quality, identify UI issues (visibility, layout, typography, spacing, motion, responsiveness), and automatically refine the frontend to production-grade aesthetic quality. Lead a multi-agent visual polish project using Claude Code Agent Teams.

Mutual Exclusivity: This stage (6P) and Stage 6P-R (Frontend Design Elevation) are alternatives — run exactly ONE, not both. If 6P has already been run and you want to switch to 6P-R, revert 6P changes first (git revert the 6P commit). See CLAUDE.md for details.

Relationship to frontend-design skill: If available, the frontend-design skill provides aesthetic guidance and design direction. Polish uses it for enhancement decisions but never replaces the project's existing design system. The lead invokes the skill and saves output; teammates read the saved output -- they do NOT invoke the skill themselves.

Category System Note: This stage uses DIFFERENT categories than 6V/6R. 6P categories: O (objective defects), E (enhancements), D (design elevation). 6V/6R categories: A/B (agent-fixable), C (human judgment). Do NOT confuse the two systems when reading 6V/6R reports.

Read the detailed guide at ${CLAUDE_SKILL_ROOT}/references/polish-detailed-guide.md for full refinement categories, teammate prompts, design system integration, and report templates.

Prerequisites

  1. Check if 6P-R was run instead: If ./plancasting/_audits/visual-polish/design-plan.md exists, check 6P-R completion status:
    • If progress.md in the same directory shows all phases completed -- 6P-R is done. Skip this stage (6P).
    • If progress.md is missing or shows incomplete phases -- 6P-R failed mid-execution. Do NOT proceed -- request operator approval before continuing.
    • If design-plan.md does not exist -- 6P-R was not run. Proceed with 6P.

Read the full file on GitHub · 203 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 203 lines · 99 tokens per session scan A 55e42cf68b3a

Subscribe to this mod's changes

polish is a skill published in the GitHub repository VoxTechnologies/transmute-framework (4 stars, last pushed 1mo ago), licensed MIT. It adds 99 tokens to every session and 3,888 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

coss-ui

Set up or extend a Next.js web app with Coss/UI — the official Cal.com design system, built on Base UI + Tailwind CSS v4 and installed through the shadcn CLI via the namespaced @coss/ registry. Two modes: Init (shadcn init @coss/style on a new project) and Add (pull @coss/ui primitives, single @coss/ components, or…

lukedj78/dev-flow · 244 tokens

frontend-design

This skill should be used when creating distinctive, production-grade frontend interfaces with high design quality. It applies when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

originalrashmi/rc-engine-product-framework · 48 tokens

creating-styled-wrappers

Creates styled wrapper components that compose headless/base compound components. Use when refactoring styled components to use base primitives, implementing opinionated design systems on top of headless components, or when the user mentions "use base components", "compose primitives", "styled wrapper", or "refactor…

Sri-Krishna-V/Derived-WMD · 68 tokens

design-guide

Paperclip UI design system guide for building consistent, reusable frontend components. Use when creating new UI components, modifying existing ones, adding pages or features to the frontend, styling UI elements, or when you need to understand the design language and conventions. Covers: component creation, design…

paperclipai/paperclip · 105 tokens

material-ui-tailwind

Integrates Material UI with Tailwind CSS v4 using cascade layers (enableCssLayer, @layer order) and documents Tailwind v3 interoperability (preflight, important, injectFirst, portals). Use when combining MUI with Tailwind utilities, slotProps className, or theme token bridges.

mui/material-ui · 67 tokens

author-component

Create or review Blazor components (.razor files) with correct architecture. USE FOR: writing new Blazor components that do NOT involve JavaScript interop, implementing parameters and EventCallback, RenderFragment slots, component lifecycle (OnInitializedAsync, OnParametersSet), async patterns, IAsyncDisposable…

dotnet/skills · 148 tokens