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
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.
About
Use cases: design, frontend
Reviews
Write a reviewNo 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
- 0.414score
low-altitude-interviewer
gclm
Screen resumes and prepare interviews for low-altitude aviation roles such as drone inspection, facade cleaning, and related operational backends.
SkillDFreshness: DClaude Code +9 - 0.414score
pdf
gclm
Read, create, or review PDF files.
SkillDFreshness: DClaude Code +9 - 0.414score
doc
gclm
Read, create, or edit `.docx` documents.
SkillDFreshness: DClaude Code +9 - 0.411score
frontend-design
gclm
Design or reshape frontend UI with an explicit visual direction, stronger aesthetic judgment, and browser-verifiable outcomes instead of generic AI-looking…
SkillDFreshness: DClaude Code +9 - 0.411score
repo-bootstrap
gclm
Inspect a repository and decide whether to initialize the generated-project scaffold before task-level harness work begins.
SkillDFreshness: DClaude Code +9 - 0.411score
brainstorm
gclm
Explore 2-3 credible implementation approaches, compare trade-offs, and converge on a recommendation before detailed planning.
SkillDFreshness: DClaude Code +9 - 0.411score
closed-loop-testing
gclm
Collect fresh evidence into a task-local evidence pack and turn implemented work into a structured verdict before calling it done.
SkillDFreshness: DClaude Code +9 - 0.411score
codex-record-retrospective
gclm
Review Codex local records for a specific project path, reconstruct what happened, and generate reusable retrospective or skill-evolution recommendations for…
SkillDFreshness: DClaude Code +9 - 0.411score
architecture-guardrails
gclm
Keep long-running work inside agreed boundaries by tracking scope drift, upgrade conditions, and design decisions before implementation silently expands.
SkillDFreshness: DClaude Code +9 - 0.411score
harness-marathon
gclm
Run long tasks with checkpoints, resume discipline, and human escalation gates so work can continue across turns without losing context.
SkillDFreshness: DClaude Code +9 - 0.411score
task-harness
gclm
Initialize a durable task pack under harness/tasks so long-running work has stable brief, progress, decisions, evidence, and verdict artifacts.
SkillDFreshness: DClaude Code +9 - 0.411score
database-design
gclm
Design or review database schemas, indexes, constraints, and data access trade-offs before implementation hardens around weak persistence choices.
SkillDFreshness: DClaude Code +9
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
- Repository
- github.com/gclm/super-stack
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from gclm
- 0.414score
low-altitude-interviewer
gclm
Screen resumes and prepare interviews for low-altitude aviation roles such as drone inspection, facade cleaning, and related operational backends.
SkillDFreshness: DClaude Code +9 - 0.414score
pdf
gclm
Read, create, or review PDF files.
SkillDFreshness: DClaude Code +9 - 0.414score
doc
gclm
Read, create, or edit `.docx` documents.
SkillDFreshness: DClaude Code +9 - 0.411score
repo-bootstrap
gclm
Inspect a repository and decide whether to initialize the generated-project scaffold before task-level harness work begins.
SkillDFreshness: DClaude Code +9 - 0.411score
frontend-design
gclm
Design or reshape frontend UI with an explicit visual direction, stronger aesthetic judgment, and browser-verifiable outcomes instead of generic AI-looking…
SkillDFreshness: DClaude Code +9 - 0.411score
architecture-guardrails
gclm
Keep long-running work inside agreed boundaries by tracking scope drift, upgrade conditions, and design decisions before implementation silently expands.
SkillDFreshness: DClaude Code +9
Cite this page
frontend-refactor skill. Agent Mart. https://agentmart.dev/skills/gclm-frontend-refactor (last updated 2026-10-24)