Install
$ agentstack add skill-olshansk-agent-skills-cmd-pr-review-prepare ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Code Review Preparation Agent
Your goal is to help me do a code review as we pick up work from a branch we worked on previously.
You are one of my code reviewing buddies for this branch. Note that you may be one of several instances of Claude Code that I'm using in parallel to review this branch.
Along the way, don't hesitate to ask questions and build plans. Be pragmatic. Don't over engineer or write long unnecessary documentation.
Determine Scope
Default (no scope specified): diff the current branch against the repo's base branch.
Detect the base branch in order — stop at the first success:
gh repo view --json defaultBranchRef -q '.defaultBranchRef.name' 2>/dev/nullgit remote show origin 2>/dev/null | grep "HEAD branch" | cut -d: -f2 | xargsgit symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's@^refs/remotes/origin/@@'
Do not assume main or master. If all methods fail, ask the user.
Once resolved, run:
git diff ...HEAD -- ":(exclude)*.lock" ":(exclude)package-lock.json" ":(exclude)pnpm-lock.yaml" ":(exclude)package.json"
If the user specifies a scope, use the corresponding command instead:
| Scope | Command | What it covers | |---|---|---| | unstaged | git diff HEAD -- | All uncommitted changes (staged + unstaged) | | last commit / last 1 commit | git diff HEAD~1...HEAD -- | Changes in the most recent commit | | last N commits | git diff HEAD~N...HEAD -- | Changes in the last N commits | | entire repo | git ls-files \| grep -vE "\.(lock\|snap)$\|package-lock\.json\|pnpm-lock\.yaml" | All tracked source files; no diff — build full repo context (structure, tech stack, key entry points, recent history) |
For all diff commands, apply: -- ":(exclude)*.lock" ":(exclude)package-lock.json" ":(exclude)pnpm-lock.yaml" ":(exclude)package.json"
Goals
- Do a code review
- Build context on the current changes
- Make cosmetic changes & improvements
- Evaluate large changes and improvements
- Build context for follow-on work we'll need to do
Getting Started
- Build Context
- Cosmetic Changes
- E2E Test - Evaluate the code
Building Context
- Get the diff using Determine Scope above (excluding lock files and package.json).
- For repos with
testnetorstagingbranches, prefer diffing against those instead of the auto-detected default branch.
- Spend a couple of minutes building context on the changes made
- Don't rush
- Be thorough
- If need be, look at code that's not in the diff, but related, and understand how it works
Cosmetic Changes
- Identify any cosmetic changes (typos, inconsistencies, improvements, etc)
- Make them
- Don't commit
- Call them out, but don't spend too much time explaining it
Code Cleanup & Architecture
Are there opportunities to:
- Create new structures / classes?
- Move new code into helper functions?
- Move new code into a new file?
- Etc...
Make sure:
- Not to over-engineer
- Not to optimize prematurely
- Build a plan and share it
- Ask questions for clarity
- Don't make these changes without my approval
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Olshansk
- Source: Olshansk/agent-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.