← Back to Skills Marketplace
Review Frontend
by
Kevin Anderson
· GitHub ↗
· v1.0.1
· MIT-0
123
Downloads
0
Stars
1
Active Installs
2
Versions
Install in OpenClaw
/install review-frontend
Description
Comprehensive React/TypeScript frontend code review with optional parallel agents
Usage Guidance
Before installing, check that your execution environment provides the local tools the skill uses (git, grep, head, and npm if you plan to run post-fix checks). Review the manifests of any beagle-react:* skills this skill will load — those secondary skills may request credentials or install steps not declared here. Because this skill can spawn subagents and load other skills, treat it as a coordinator: verify the transitive behavior of every skill it loads. If you have strict least-privilege requirements, demand that the author declare required binaries and explicitly list transitive environment/permission needs before use.
Capability Analysis
Type: OpenClaw Skill
Name: review-frontend
Version: 1.0.1
The skill is a frontend code review coordinator that uses standard git and grep commands to identify changes and detect technologies (React, Zustand, Tailwind). It follows a structured workflow to load specialized sub-skills and provides clear guidelines for reporting issues. While it executes 'npm' scripts for verification, this is a standard practice for the stated purpose of validating code fixes and does not indicate malicious intent.
Capability Assessment
Purpose & Capability
The skill claims to perform repo-focused React/TypeScript reviews, which fits its name. However the SKILL.md explicitly runs shell commands (git, grep, head) and suggests running npm scripts; the registry metadata lists no required binaries. This mismatch (declaring no required binaries while the runtime relies on git/grep/npm) is an incoherence that could lead to unexpected failures or hidden capabilities if the environment differs from the author’s assumptions.
Instruction Scope
Instructions are largely limited to scanning the repo diff, grepping for patterns, and running checks — all appropriate for a code-review skill. Two items to note: (1) the skill instructs loading an external 'review-verification-protocol' gate and many other beagle-react skills before making judgments; loading those skills delegates additional behavior to them and may expand scope unexpectedly, and (2) the skill supports spawning parallel subagents (via a Task tool) which may further load other skills. The SKILL.md does not list the transitive actions or requirements of those external skills, so the effective runtime behavior depends on external manifests.
Install Mechanism
This is instruction-only with no install spec or external downloads, which is the lowest install risk. Nothing is written to disk by an installer step in the registry metadata.
Credentials
The skill declares no required environment variables or credentials, which is appropriate for a local code review. However, because it loads other skills and can spawn subagents, those secondary skills may request environment variables/credentials transitively. Also it fails to declare required local tooling (git, grep, npm) in the manifest, which is a proportionality/accuracy problem rather than direct credential overreach, but still important to surface.
Persistence & Privilege
The skill does not request always:true or persistent presence and does not attempt to modify system/other-skill configs. One unusual flag: disable-model-invocation is set to true in the skill header — yet the runtime expects to call platform tools (Skill, Task) to load other skills and spawn agents. This is not necessarily malicious, but it's an uncommon configuration and may indicate misunderstanding of platform semantics or an assumption about available orchestration tools. Combine this with the transitive loading of other skills and you get a wider effective privilege surface.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install review-frontend - After installation, invoke the skill by name or use
/review-frontend - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
- Clarified the requirement to load the review verification protocol skill before making any substantive judgment or assigning severity to findings.
- Added explicit PASS conditions and review "gates" for each stage of the review, specifying required artifacts or confirmations to proceed.
- Tightened the evidence requirement for Critical/Major findings: each must cite a real FILE:LINE and, where applicable, concrete proof beyond diff context.
- Prohibited advancing through steps or restating informal checks without satisfying all listed gates.
- No structural changes to review logic, but increased enforcement and clarity on process sequencing and evidentiary standards.
v1.0.0
- Initial release of review-frontend: a comprehensive React/TypeScript frontend code review skill.
- Supports detection of React Flow, Zustand, Tailwind v4, and test files for targeted reviews.
- Optionally spawns parallel agents with --parallel for specialized domain reviews.
- Applies beagle-react skill set, loading relevant skills per detected technologies.
- Enforces single-pass, comprehensive review with strict output and severity conventions.
- Provides clear guidelines for reporting, issue severity, and post-fix verification.
Metadata
Frequently Asked Questions
What is Review Frontend?
Comprehensive React/TypeScript frontend code review with optional parallel agents. It is an AI Agent Skill for Claude Code / OpenClaw, with 123 downloads so far.
How do I install Review Frontend?
Run "/install review-frontend" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Review Frontend free?
Yes, Review Frontend is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Review Frontend support?
Review Frontend is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Review Frontend?
It is built and maintained by Kevin Anderson (@anderskev); the current version is v1.0.1.
More Skills