General

critique - Claude MCP Skill

Council critique mode - agents find bugs and flaws in each other's answers

SEO Guide: Enhance your AI agent with the critique tool. This Model Context Protocol (MCP) server allows Claude Desktop and other LLMs to council critique mode - agents find bugs and flaws in each other's answers... Download and configure this skill to unlock new capabilities for your AI workflow.

🌟11 stars • 6 forks
📥0 downloads

Documentation

SKILL.md
# Council Critique Mode

Start an owlex council in **critique mode** - agents actively find bugs, security issues, and flaws.

## Instructions

1. Take the user's question or code from: $ARGUMENTS
2. If no argument provided, ask what they want critiqued
3. Call `mcp__owlex__council_ask` with:
   - `prompt`: The user's question/code to critique
   - `working_directory`: Current working directory
   - `deliberate`: true
   - `critique`: true (enables adversarial mode)
4. Return immediately with the task_id
5. Tell the user:
   - "Critique started (task: <task_id>)"
   - "This typically takes 2-5 minutes"
   - "Check results with: `/council-result <task_id>`"

**Do NOT call wait_for_task. Return immediately.**

## Usage

- `/critique Review this auth for security holes`
- `/critique Find bugs in this payment code`

Signals

Avg rating0.0
Reviews0
Favorites0

Information

Repository
agentic-mcp-tools/owlex
Author
agentic-mcp-tools
Last Sync
3/12/2026
Repo Updated
3/11/2026
Created
1/24/2026

Reviews (0)

No reviews yet. Be the first to review this skill!