fe-rail

Plugin fe-rail from marketplace guardrail in sh5623/guardrail. Commands read from the repo's manifest — 9 days ago.

Skills (5)

• fe-build

  Implements frontend components and pages for React / Next.js / Vite SPA + TypeScript projects. Use when: starting implementation after feature.md or a spec is approved, writing components, building pages. Do NOT load for: writing specs, code review, bug analysis. - Read - Write - Edit - Bash - Task

• fe-doc-sync

  Comprehensively scans changes in code structure, tech stack, and workflow in the user project where this plugin is installed (e.g., Vibe App), and keeps that project's CLAUDE.md / README.md up to date. Covers new routes, components, dependencies, app/package additions, folder restructuring, framewor

• fe-review

  Reviews implemented frontend code from multiple angles. Use when: after implementation is done, before committing, before creating a PR, or when code quality needs checking. Do NOT load for: writing specs, implementing new features. - Read - Bash - Task - Agent

• fe-spec

  Converts requirements for a new frontend feature into a structured spec. Use when: before starting a new feature, when feature.md needs to be written, or when converting a planning doc into a dev spec. Do NOT load for: bug fixes, refactoring, simple style changes. - Read - Write - Edit - AskUserQues

• fe-start

  Takes a feature.md file and automatically runs spec confirmation → implementation → review → commit → PR. Use when: the user says "fe-start feature.md" or "start with feature.md". Do NOT load for: one-off bug hotfixes, 1-line changes, exploratory work, or tasks where pass/fail signals are ambiguous

Subagents (15)

• fe-a11y-auditor

  Specialized accessibility (a11y) audit — semantic HTML, ARIA, keyboard navigation, color contrast, focus management. More precise than fe-reviewer's a11y axis. READ-ONLY. With `--live`, also measures via Chrome DevTools MCP (Lighthouse a11y score, real accessibility tree, runtime console); falls bac

• fe-analyst

  Requirement gap analysis before/during the fe-spec stage. Systematically identifies unasked questions, undefined guardrails, scope creep, unverified assumptions, and edge cases. READ-ONLY.

• fe-architect

  React/TS architecture advisory — component boundaries, data flow, state management, routing, module dependencies. Supports both Next.js App Router and Vite SPA (TanStack Router / React Router 7·8). READ-ONLY analysis only.

• fe-build-fixer

  Build/type/compile error-fixing specialist. Resolves errors with minimal changes only, no architectural changes. Auto-fix step triggered after the quality-gate hook detects errors.

• fe-deck-reader

  Decomposes PPT/planning decks (multi-slide, converted to PDF/PNG) into [policy & rules / screen mockups / screen flow / data & fields]. Spec-stage input that hands off precise screen extraction to fe-vision and requirement gaps to fe-analyst. READ-ONLY.

• fe-explorer

  Dedicated codebase exploration. Delegate when a search needs 3+ queries. Returns only summaries so raw code doesn't flow into the parent context. READ-ONLY.

• fe-git-operator

  Dedicated git operations — splitting commits, safe staging that preserves the user's pre-existing index, writing Conventional Commits bodies (fix = symptom/cause/fix, feat = addition/core/impact), pushing the branch, and the pre-commit base sync (fe-start 6-0). fe-pr-author owns PRs; this agent owns

• fe-perf-auditor

  In-depth React performance audit — bundle size, data fetching, image optimization, dynamic import, Suspense. Supports both Next.js (RSC, next/image) and Vite SPA (bundle analysis, fetchpriority). More precise than fe-reviewer's performance axis. READ-ONLY. With `--live`, also measures via Chrome Dev

• fe-pr-author

  Synthesizes commits, diff, and spec to write the PR body (fix = symptom/cause/fix, feat = addition/core/impact blocks) and runs `gh pr create`. Delegate at the PR stage after fe-review passes — the main session only gets back the PR URL.

• fe-refactor-advisor

  Refactoring analysis specialist — evaluates 6 dimensions (complexity, duplication, naming, structure, patterns, type safety) with Before/After code and an impact × difficulty matrix. READ-ONLY.

• fe-researcher

  External docs/library research specialist — official Next.js/React/TS docs, GitHub Issues, Stack Overflow. Every piece of information must cite a source URL.

• fe-reviewer

  4-axis frontend code review — type safety, performance, a11y, code quality. READ-ONLY, no direct edits. Delegate after fe-build completes, before the PR stage.

• fe-test-author

  Generates frontend test code — derives BDD scenarios and supports TDD Red-Green-Refactor. Pairs with fe-test-runner (generation vs. execution).

• fe-test-runner

  Dedicated test execution. Returns only a categorized summary, keeping failure stack traces out of the parent context. Auto-detects jest/vitest/playwright.

• fe-vision

  Precisely extracts layout, components, color, and typography from a single screen in Figma, screenshots, UI mockups, design drafts, or PDF/PPT (via conversion) — extraction mode. Or compares an implementation screenshot against a reference and judges visual fidelity as JSON — comparison mode (visual

Hooks (11)

• SessionStart

  "${CLAUDE_PLUGIN_ROOT}/hooks/session-init.sh"

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/guard.sh"

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/write-guard.sh"

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/config-protection.sh"

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/read-guard.sh"

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/task-guard.sh"

• PostToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/lint-fix.sh"

• PostToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/nextjs-guard.sh"

• PostToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/design-nudge.sh"

• Stop

  "${CLAUDE_PLUGIN_ROOT}/hooks/quality-gate.sh"

• Stop

  "${CLAUDE_PLUGIN_ROOT}/hooks/doc-sync-check.sh"

Similar plugins