← Back to Skills Marketplace
Review Tui
by
Kevin Anderson
· GitHub ↗
· v1.0.1
· MIT-0
115
Downloads
0
Stars
1
Active Installs
2
Versions
Install in OpenClaw
/install review-tui
Description
Comprehensive BubbleTea TUI code review for terminal applications
Usage Guidance
This skill appears to be a structured code-review orchestrator for BubbleTea/TUI code and is instruction-only (no install/download). Before installing or using it: 1) Note that the SKILL.md runs shell commands (git, grep) but the skill metadata lists no required binaries — ensure git and grep are available in the execution environment or ask the author to declare them. 2) The skill loads other skills (beagle-go:*) and will spawn subagents; only use it if those downstream skills are trusted, because they will execute review logic on your repository. 3) It reads repository files/diffs—do not run it against repositories containing secrets you do not want reviewed. 4) The review policy enforces an exhaustive single-pass reporting requirement and assumes a 'main' branch; confirm these operational assumptions match your workflow. If you need higher assurance, ask the skill author to: (a) update metadata to list required binaries, (b) document expected availability/trust of the beagle-go skills, and (c) clarify behavior when repository layout differs (no main branch).
Capability Tags
Capability Assessment
Purpose & Capability
The SKILL.md is coherent with the named purpose (orchestrating a BubbleTea TUI code review and delegating to specialized 'beagle-go' skills). However, the runtime commands in the instructions (git, grep) are required to operate but the skill metadata declares no required binaries. The skill also expects other skills (beagle-go:*) to be present and loadable; that dependency is reasonable for an orchestrator but is not reflected in the metadata.
Instruction Scope
Instructions explicitly run shell commands (git diff, grep) and instruct the agent to read repository files and diffs; they do not attempt to read unrelated system files or environment variables. The SKILL.md also instructs loading and spawning subagents for other skills, increasing the review surface. It assumes repository layout (e.g., main branch) and demands a single-pass exhaustive report, which is an aggressive review policy but not inherently malicious. Missing declaration of required binaries (git/grep) and the aggressive 'report ALL issues in single pass' rule are notable.
Install Mechanism
Instruction-only skill with no install spec and no code files. This is low-risk from an install perspective because nothing is downloaded or written by the skill itself.
Credentials
The skill requests no environment variables, credentials, or config paths. The SKILL.md also does not reference secrets or external endpoints beyond loading other local skills. This is proportionate to a code-review orchestrator.
Persistence & Privilege
The skill does not request persistent presence (always is false) and declares disable-model-invocation true, so it cannot be autonomously invoked by the model. It does load other skills during its run but does not modify system or other skills' configurations. This reduces blast radius.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install review-tui - After installation, invoke the skill by name or use
/review-tui - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
- Introduced explicit gate checks ("Gates" section) to enforce review sequence and output quality before publishing findings.
- Clarified scope control: reviewers must confirm file targets and loaded skills before starting analysis.
- Added requirements that all Critical/Major findings must cite precise file and line (or code quote) from source.
- Enhanced hygiene: all findings must be checked against the verification protocol and review rules before output.
- No breaking changes to CLI, review format, or output structure; all changes are procedural and workflow-oriented.
v1.0.0
Initial release: Comprehensive code review skill for BubbleTea TUI apps
- Automated tech detection (BubbleTea, Lipgloss, Bubbles, Wish SSH, and test files) via codebase scans
- Layered review process covers Go quality, BubbleTea architecture, styling, composition, SSH integration, and test coverage
- Clear multi-level issue categorization (Critical, Major, Minor, Informational) with strict formatting
- Smart skill loading for relevant areas: always loads core review skills, conditionally loads extra protocols
- Enforces "single-pass" review: all relevant issues must be surfaced at once; follow strict iteration and fix policy
- Ready-to-use output template and explicit post-fix verification instructions
Metadata
Frequently Asked Questions
What is Review Tui?
Comprehensive BubbleTea TUI code review for terminal applications. It is an AI Agent Skill for Claude Code / OpenClaw, with 115 downloads so far.
How do I install Review Tui?
Run "/install review-tui" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Review Tui free?
Yes, Review Tui is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Review Tui support?
Review Tui is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Review Tui?
It is built and maintained by Kevin Anderson (@anderskev); the current version is v1.0.1.
More Skills