Skip to content
Back to skills

Conduct Review

ASecurity

Second-opinion review of the branch by a worker LLM; the controller triages findings

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 11, 2026
ai-agentsbashgit

Security analysis

A100/100

Scanned November 11, 2026

npx -y skills add KevalParikh22/conductor-ai --skill conduct-review --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Conduct Review?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Conduct Review
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/kevalparikh22-conduct-review/badge)](https://www.skillsdirectory.com/skills/kevalparikh22-conduct-review)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: conduct-review
description: "Second-opinion review of the branch by a worker LLM; the controller triages findings"
argument-hint: "[--plan <file>] [--base <ref>] [focus text]"
disable-model-invocation: true
allowed-tools: "Read, Bash(conductor run review:*), Bash(git diff:*), Bash(git log:*)"
---

Run in the background: `conductor run review the arguments the user gave`

Then read the report and triage every finding: open the cited lines and mark each one **real**, **false positive** or **unsure**. Don't pass on unchecked claims. Show the user only the real and unsure findings (severity, `file:line`, one-line problem), plus the reviewer's verdict and yours. Offer to fix them: small ones yourself, larger ones with `conductor run fix`.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.