← 返回 Skills 市场
aibenyclaude-coder

Tetra Scar Code Review

作者 aibenyclaude-coder · GitHub ↗ · v0.1.0 · MIT-0
cross-platform ⚠ suspicious
120
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install tetra-scar-code-review
功能描述
Code review that learns from failures. Reflex arc blocks repeat mistakes without LLM calls. Combines systematic checklist review (security, performance, corr...
安全使用建议
This skill appears to do what it says: local, regex/heuristic code review plus a local scar database. Before installing or running it: (1) review the scar JSONL contents or configure the scar file location to a safe directory you control (to avoid unexpected blocks), (2) avoid importing or trusting scars from untrusted sources because regex patterns can trigger false blocks or cause heavy CPU (ReDoS) on large diffs, (3) run the tool in a sandbox or on non-production copy first to confirm behavior, and (4) note it writes review_scars.jsonl in your working directory by default, so back up any existing file you care about.
功能分析
Type: OpenClaw Skill Name: tetra-scar-code-review Version: 0.1.0 The tetra-scar-code-review skill bundle is a legitimate static analysis tool designed to perform security, performance, and maintainability checks on source code. The core logic in scar_code_review.py uses regex-based heuristics to identify common vulnerabilities such as SQL injection, hardcoded secrets, and unsafe eval usage. It includes a 'reflex arc' feature that matches code against a local database of past misses (review_scars.jsonl). The code is well-documented, includes comprehensive tests (test_scar_code_review.py), and contains no evidence of data exfiltration, malicious execution, or harmful instructions.
能力评估
Purpose & Capability
Name/description (learning code-review via scars) matches the shipped files and declared requirements: Python 3 only, local CLI/API, local JSONL storage. No unrelated credentials, binaries, or installs are requested.
Instruction Scope
Runtime instructions operate on local files and diffs and instruct storing scars to a local review_scars.jsonl — which is consistent. One operational note: scars include user-supplied regex patterns and keyword text which the reflex_check runs against diffs; overly broad or malicious regexes could cause false positives or heavy CPU (ReDoS) when scanning large diffs. The skill also reads/writes files in the current working directory (expected behavior).
Install Mechanism
Instruction-only with bundled Python source files and no install spec — lowest risk. Nothing is downloaded or executed from remote URLs.
Credentials
No environment variables, credentials, or external config paths are required; requested resources are proportional to a local static analysis tool.
Persistence & Privilege
always:false and no code to modify other skills or system-wide agent settings. The only persistent effect is writing/reading a local review_scars.jsonl file (configurable via scar_file parameter), which is reasonable for this tool.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install tetra-scar-code-review
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /tetra-scar-code-review 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v0.1.0
- Initial release of scar-code-review (version 0.1.0) - Provides checklist code reviews across security, performance, correctness, and maintainability - Introduces a scar reflex arc: when a bug slips through review, a "scar" is recorded to block similar mistakes in the future - No external dependencies; Python 3.9+ only - Includes CLI for reviewing files, checking diffs against scars, and recording missed findings - Offers importable Python API for integration with existing workflows
元数据
Slug tetra-scar-code-review
版本 0.1.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Tetra Scar Code Review 是什么?

Code review that learns from failures. Reflex arc blocks repeat mistakes without LLM calls. Combines systematic checklist review (security, performance, corr... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 120 次。

如何安装 Tetra Scar Code Review?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install tetra-scar-code-review」即可一键安装,无需额外配置。

Tetra Scar Code Review 是免费的吗?

是的,Tetra Scar Code Review 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Tetra Scar Code Review 支持哪些平台?

Tetra Scar Code Review 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Tetra Scar Code Review?

由 aibenyclaude-coder(@aibenyclaude-coder)开发并维护,当前版本 v0.1.0。

💬 留言讨论