Skip to content
Agentmart
Submit a tool

frontend-refactor

Refactor frontend code by separating structural cleanup, UI consistency, state flow, and verification instead of mixing visual edits with risky behavior…

Skill by gclm

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/gclm-frontend-refactor

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Refactor frontend code by separating structural cleanup, UI consistency, state flow, and verification instead of mixing visual edits with risky behavior changes.

Use cases: design, frontend

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/frontend-refactor

What's inside

Skill name
frontend-refactor
Description
Refactor frontend code by separating structural cleanup, UI consistency, state flow, and verification instead of mixing visual edits with risky behavior changes.
License
MIT
Instructions
50 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • refactor-slices.md · references/

SKILL.md (first lines)

# Frontend Refactor

Use this skill when a frontend change is larger than a simple bugfix and the real goal is to improve maintainability, consistency, or interaction quality without losing existing behavior.

## Read First

- `docs/overview/roadmap.md` and `harness/state.md` if they exist
- `harness/history.md` if it exists
- `docs/reference/conventions.md` if it exists
- the closest layout, state, and routing files involved
- any existing design or product notes that constrain the refactor
- `references/refactor-slices.md` when the work needs safer slicing

## Goals

- separate structural refactor from incidental redesign
- keep behavior changes explicit
- improve consistency across layout, state, styles, and reusable components
- leave behind clearer UI patterns instead of one-off edits
- preserve the difference between reusing a reference project's structure and copying its implementation
- avoid generic AI-looking visual output when the task includes meaningful UI polish or visual cleanup

## Steps

1. Define the refactor target.
2. Identify what must stay behaviorally stable.
3. Decide whether the task is reusing information architecture, interaction structure, implementation details, or some combination.
4. Split the work into safe slices instead of rewriting everything at once.
5. Refactor shared patterns first when multiple screens repeat them.
6. When visual polish matters, choose an explicit visual direction instead of defaulting to generic app UI.
7. Make typography, spacing, color, hierarchy, and background treatment intentional rather than leaving them as framework defaults.
8. Keep motion sparse but meaningful; avoid filler animation.
9. For validation samples, prefer maintainable skeletons and debug-friendly structure over premature visual fidelity, but do not accept obviously bland or placeholder-looking UI when presentation is part of the task.
10. Verify both UI structure and the most important user flows after each slice.

Read `references/refactor-slices.md` when you need a more explicit slicing strategy.

## Output

Report:

- refactor scope
- stable behavior constraints
- reference reuse boundary chosen
- visual direction chosen when relevant
- shared patterns extracted
- risky areas
- verification evidence

From gclm/super-stack, MIT.

More from gclm/super-stack

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Mar 29, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from gclm

Cite this page

frontend-refactor skill. Agent Mart. https://agentmart.dev/skills/gclm-frontend-refactor (last updated 2026-10-24)