nathankoerschner/review
agent-skills/_shared-skills/review/SKILL.md
Run the reviewer sub-agent for code review
development
Updated May 29, 2026
$ install --global
skillsauthnpx skillsauth add nathankoerschner/dotfiles reviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 29, 2026, 6:51 AM293.6s1 file scanned
SKILL.md
- name:
- review
- description:
- Run the reviewer sub-agent for code review
- argument-hint:
- [target or extra review instructions] [optional: --provider <provider> --model <model>]
- allowed-tools:
- bash
Spawn the Pi reviewer sub-agent via bash and have it perform the review.
Run:
pi --print ...
Behavior:
- Pass through user arguments (
$@) to the sub-agent invocation. - If the user specifies a model, include
--providerand--modelaccordingly. - Give the sub-agent a prompt telling it to review code for:
- Bugs and logic errors
- Security issues
- Error handling gaps
- Do not read code yourself; the sub-agent must do the code inspection.
- Return the sub-agent findings to the user.
Related Skills
nathankoerschner/deep-review
development
VerifiedTrustedCommunity
Deep, rigorous multi-model code review for PRs, branches, diffs, commits, or pre-merge checks. Use this when the user explicitly asks for a deep review, thorough review, rigorous review, pre-merge check, PR review, branch review, or wants maximum confidence. Do not use for quick/casual reviews; use quick-review instead. Treat AI output as a first draft: run independent Pi subagents on Claude Opus, GPT-5.5 extra-high reasoning, and Gemini; validate and synthesize severity-ranked findings before fixes.
SKILL.mdUpdated Jun 4, 2026
nathankoerschner/web-interface-guidelines
development
VerifiedTrustedCommunity
Review UI code for Vercel Web Interface Guidelines compliance
SKILL.mdUpdated May 31, 2026
nathankoerschner/ui-skills
development
VerifiedTrustedCommunity
Opinionated constraints for building better interfaces with agents.
SKILL.mdUpdated May 31, 2026
nathankoerschner/snowsql
databases
VerifiedTrustedCommunity
Connect to Snowflake via SnowSQL
SKILL.mdUpdated May 31, 2026