无公网服务时,聚焦缺陷的本地代码审查
Scanned 9/2/2026
Install to Claude Code
npx -y skills add wangzhe04/ruyi-workbench-oss --skill code-review-offline --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Code Review Offline?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/wangzhe04-code-review-offline)More formats (shields.io, HTML) on the badges page.
---
name: 离线代码审查
description: 无公网服务时,聚焦缺陷的本地代码审查
---
# Code Review Offline
Use this skill for bug-focused code review when public services are unavailable.
Workflow:
1. Run `git_status`, then `git_diff` for the change content, when reviewing uncommitted changes.
2. Run `code_review_scan` to collect lightweight security and quality signals.
3. Read the exact files and lines behind any finding before reporting it.
4. Prioritize behavioral bugs, data loss, security exposure, regressions, and missing tests.
5. Present findings first, ordered by severity, with file paths and line numbers.
6. If no issues are found, say that clearly and mention residual risk or unrun tests.
Do not:
- Report style-only comments unless they hide a real defect.
- Assume external CI, GitHub, or cloud scanners exist.
- Copy large diffs into the answer; summarize the relevant lines.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...