frontend-code-review — Claude Code skill: review and install
The frontend-code-review skill checks frontend files against a checklist and formats findings in a fixed review structure. Use it for pending changes or specific files you name.
MIT ★ 880 updated 2026-09-03
npx skills add sangrokjung/claude-forge --skill frontend-code-review -a claude-codeWhat frontend-code-review does
The skill reviews frontend code, especially .tsx, .ts, and .js files. It can inspect changes in the working tree that are headed for a commit, or focus on files you specify. Each applicable checklist violation receives an urgency label.
The checklist is split into code quality, performance, and business logic, with rules in references/code-quality.md, references/performance.md, and references/business-logic.md. Findings are grouped by urgency and category, with a file path, line number, and suggested fix. When the review finds nothing, it uses a separate concise template. The checklist governs the results, so make sure its rules fit your project.
Install it with npx skills add sangrokjung/claude-forge --skill frontend-code-review -a claude-code. The skill file is located at ~/.claude/skills/frontend-code-review/SKILL.md.
What it helps with
- review frontend changes before committing
- check a selected
.tsxfile against the checklist - separate urgent findings from improvement suggestions
- get findings with file and line references
Example prompts for the agent
- Review the pending frontend changes before I commit them.
- Check
src/App.tsxand report checklist violations with line numbers. - Review
src/components/Button.tsxfor code quality and performance issues.
How to install frontend-code-review
1Skills CLI (Vercel)
npx skills add sangrokjung/claude-forge --skill frontend-code-review -a claude-code2Manually: put the files in place
~/.claude/skills/frontend-code-review/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/frontend-code-review/
1Skills CLI (Vercel)
npx skills add sangrokjung/claude-forge --skill frontend-code-review -a codex2Manually: put the files in place
.agents/skills/frontend-code-review/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add sangrokjung/claude-forge --skill frontend-code-review -a cursor2Manually: put the files in place
.cursor/skills/frontend-code-review/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install sangrokjung/claude-forge skills/frontend-code-review2Manually: put the files in place
.github/skills/frontend-code-review/SKILL.md1Skills CLI (Vercel)
npx skills add sangrokjung/claude-forge --skill frontend-code-review -a gemini-cli2Platform CLI
gemini skills install https://github.com/sangrokjung/claude-forge --path skills/frontend-code-reviewManually: put the files in place
.devin/skills/frontend-code-review/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about frontend-code-review
How do I install frontend-code-review in Claude Code?
Run npx skills add sangrokjung/claude-forge --skill frontend-code-review -a claude-code. The skill file is at ~/.claude/skills/frontend-code-review/SKILL.md.
What does frontend-code-review do?
It reviews selected frontend files or changes prepared for a commit. Findings and suggestions include file and line references, along with a proposed fix.
Which rules does the skill use to review code?
It follows checklists for code quality, performance, and business logic stored in files under references/. Each violation gets an urgency label.
Source text
SKILL.md · MIT
--- name: frontend-code-review description: "Trigger when the user requests a review of frontend files (e.g., `.tsx`, `.ts`, `.js`). Support both pending-change reviews and focused file reviews while applying the checklist rules." --- # Frontend Code Review ## Intent Use this skill whenever the user asks to review frontend code (especially `.tsx`, `.ts`, or `.js` files). Support two review modes: 1. **Pending-change review** – inspect staged/working-tree files slated for commit and flag checklist violations before submission. 2. **File-targeted review** – review the specific file(s) the user names and report the relevant checklist findings. Stick to the checklist below for every applicable file and mode. ## Checklist See [references/code-quality.md](references/code-quality.md), [references/performance.md](references/performance.md), [references/business-logic.md](references/business-logic.md) for the living checklist split by category—treat it as the canonical set of rules to follow. Flag each rule violation with urgency metadata so future reviewers can prioritize fixes. ## Review Process 1. Open the relevant component/module. Gather lines that relate to class names, React Flow hooks, prop memoization, and styling. 2. For each rule in the review point, note where the code deviates and capture a representative snippet. 3. Compose the review section per the template below. Group violations first by **Urgent** flag, then by category order (Code Quality, Performance, Business Logic). ## Required output When invoked, the response must exactly follow one of the two templates: ### Template A (any findings) ``` # Code review Found <N> urgent issues need to be fixed: ## 1 <brief description of bug> FilePath: <path> line <line> <relevant code snippet or pointer> ### Suggested fix <brief description of suggested fix> --- ... (repeat for each urgent issue) ... Found <M> suggestions for improvement: ## 1 <brief description of suggestion> FilePath: <path> line <line> <relevant code snippet or pointer> ### Suggested fix <brief description of suggested fix> --- ... (repeat for each suggestion) ... ``` If there are no urgent issues, omit that section. If there are no suggestions, omit that section. If the issue number is more than 10, summarize as "10+ urgent issues" or "10+ suggestions" and just output the first 10 issues. Don't compress the blank lines between sections; keep them as-is for readability. If you use Template A (i.e., there are issues to fix) and at least one issue requires code changes, append a brief follow-up question after the structured output asking whether the user wants you to apply the suggested fix(es). For example: "Would you like me to use the Suggested fix section to address these issues?" ### Template B (no issues) ``` ## Code review No issues found. ```
© sangrokjung · MIT · sangrokjung/claude-forge