Svn Code Review

v0.1.0

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

0· 130·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for zhouzy-creator/svn-code-review.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Svn Code Review" (zhouzy-creator/svn-code-review) from ClawHub.
Skill page: https://clawhub.ai/zhouzy-creator/svn-code-review
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install svn-code-review

ClawHub CLI

Package manager switcher

npx clawhub@latest install svn-code-review
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
The skill's name, description, and runtime instructions all align: it's meant to produce a code review of an SVN revision range. One minor mismatch: SKILL.md uses svn commands (svn info, svn diff) but the registry metadata lists no required binaries; the skill should declare the svn CLI as a dependency.
Instruction Scope
Instructions are focused on preparing and dispatching a code-review subagent and include commands to produce SVN diffs. They do not attempt to read unrelated files, environment variables, or call unknown external endpoints. Note: the review process will expose full diffs and code to the reviewer/subagent, which is expected for a code review but important from a confidentiality perspective.
Install Mechanism
There is no install spec (instruction-only), so nothing is downloaded or written to disk. This is the lowest-risk install posture and is coherent with the skill's design.
Credentials
The skill requests no environment variables or credentials, which is appropriate for a local code-review template. No unrelated secrets are requested. Reminder: diffs may contain secrets in code, so consider scanning/sanitizing diffs before sending to a reviewer if that is a concern.
Persistence & Privilege
always:false and default model invocation settings are used (normal). The skill does not request permanent presence or system-wide configuration changes.
Assessment
This skill is instruction-only and matches its stated purpose, but before installing or using it: (1) ensure the svn CLI is available on agents that will dispatch reviews (SKILL.md assumes svn commands); (2) be aware that requesting a review sends full diffs/code to the code-reviewer subagent—do not include secrets or proprietary code you don't want exposed; (3) verify where the subagent runs and whether review content could leave your environment (platform behavior, logs, or third-party integrations); (4) consider asking the skill author to add required-binaries metadata for svn and a homepage/source for provenance; and (5) if you need stricter controls, sanitize diffs or run reviews in a trusted environment.

Like a lobster shell, security has layers — review code before you run it.

latestvk97bb5bravjsvw9sv3f64qhf6x856as9
130downloads
0stars
1versions
Updated 1w ago
v0.1.0
MIT-0

Requesting Code Review

Dispatch code-reviewer subagent to catch issues before they cascade. The reviewer gets precisely crafted context for evaluation — never your session's history. This keeps the reviewer focused on the work product, not your thought process, and preserves your own context for continued work.

Core principle: Review early, review often.

When to Request Review

Mandatory:

  • After each task in subagent-driven development
  • After completing major feature
  • Before merge to main

Optional but valuable:

  • When stuck (fresh perspective)
  • Before refactoring (baseline check)
  • After fixing complex bug

How to Request

1. Get SVN revision numbers:

BASE_REV=$(svn info | grep 'Revision:' | awk '{print $2}')  # or previous revision
HEAD_REV=$(svn info | grep 'Revision:' | awk '{print $2}')  # current revision
# Example: BASE_REV=100, HEAD_REV=105

2. Dispatch code-reviewer subagent:

Use Task tool with superpowers:code-reviewer type, fill template at code-reviewer.md

Placeholders:

  • {WHAT_WAS_IMPLEMENTED} - What you just built
  • {PLAN_OR_REQUIREMENTS} - What it should do
  • {BASE_REV} - Starting revision
  • {HEAD_REV} - Ending revision
  • {DESCRIPTION} - Brief summary

3. Act on feedback:

  • Fix Critical issues immediately
  • Fix Important issues before proceeding
  • Note Minor issues for later
  • Push back if reviewer is wrong (with reasoning)

Example

[Just completed Task 2: Add verification function]

You: Let me request code review before proceeding.

BASE_REV=$(svn info | grep 'Revision:' | awk '{print $2}')  # Previous revision
HEAD_REV=$(svn info | grep 'Revision:' | awk '{print $2}')  # Current revision

[Dispatch superpowers:code-reviewer subagent]
  WHAT_WAS_IMPLEMENTED: Verification and repair functions for conversation index
  PLAN_OR_REQUIREMENTS: Task 2 from docs/superpowers/plans/deployment-plan.md
  BASE_REV: 100
  HEAD_REV: 105
  DESCRIPTION: Added verifyIndex() and repairIndex() with 4 issue types

[Subagent returns]:
  Strengths: Clean architecture, real tests
  Issues:
    Important: Missing progress indicators
    Minor: Magic number (100) for reporting interval
  Assessment: Ready to proceed

You: [Fix progress indicators]
[Continue to Task 3]

Integration with Workflows

Subagent-Driven Development:

  • Review after EACH task
  • Catch issues before they compound
  • Fix before moving to next task

Executing Plans:

  • Review after each batch (3 tasks)
  • Get feedback, apply, continue

Ad-Hoc Development:

  • Review before merge
  • Review when stuck

Red Flags

Never:

  • Skip review because "it's simple"
  • Ignore Critical issues
  • Proceed with unfixed Important issues
  • Argue with valid technical feedback

If reviewer wrong:

  • Push back with technical reasoning
  • Show code/tests that prove it works
  • Request clarification

See template at: code-reviewer.md

Comments

Loading comments...