# Frontend Reviewer

> Review frontend code, UI changes, generated implementations, and pull requests with severity-based findings and checklist-driven analysis. Use when auditing React/TypeScript/CSS code, validating AI-generated frontend output, performing acceptance review before merge, or checking whether a frontend change is safe to ship.

- **Type:** Skill
- **Install:** `agentstack add skill-ceilf6-frontagent-frontend-reviewer`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [ceilf6](https://agentstack.voostack.com/s/ceilf6)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [ceilf6](https://github.com/ceilf6)
- **Source:** https://github.com/ceilf6/FrontAgent/tree/develop/skills/frontend-reviewer
- **Website:** https://marketplace.visualstudio.com/items?itemName=ceilf6.frontagent

## Install

```sh
agentstack add skill-ceilf6-frontagent-frontend-reviewer
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Frontend Reviewer

Review relevant frontend files and produce concrete findings ordered by severity. Keep the review evidence-based, concise, and actionable.

## Workflow

1. Read `references/severity-rubric.md`.
2. Read `references/review-checklist.md`.
3. Read `references/frontend-quality-rules.md` when architecture, layering, or maintainability questions matter.
4. Inspect only the files relevant to the request, the diff, or the changed surfaces implied by the task.
5. Report findings grouped by severity, highest risk first.
6. If no findings exist, state that explicitly and mention residual risks or testing gaps.

## Output Contract

- Start with findings. Do not lead with a summary.
- For each finding include:
  - affected file path
  - optional line number when known
  - severity
  - why it matters
  - shortest viable fix direction
- Prefer one issue per finding. Split unrelated problems.
- Use exact evidence. Avoid generic advice.

## Guardrails

- Do not invent files, line numbers, or user intent.
- Do not upgrade style nits into blocking issues.
- Do not hide uncertainty. Mark assumptions when evidence is incomplete.
- Do not spend space on praise unless the user explicitly asks for it.
- Prefer behavioral regressions, data-flow bugs, accessibility issues, and missing tests over cosmetic commentary.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [ceilf6](https://github.com/ceilf6)
- **Source:** [ceilf6/FrontAgent](https://github.com/ceilf6/FrontAgent)
- **License:** MIT
- **Homepage:** https://marketplace.visualstudio.com/items?itemName=ceilf6.frontagent

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-ceilf6-frontagent-frontend-reviewer
- Seller: https://agentstack.voostack.com/s/ceilf6
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.