recipe-diagnose

Coordinate agent-driven diagnosis to identify failure points in complex workflows.

Updated Jun 8, 2026
One-click install
npx skills add https://github.com/darsoohoo/intake-bot --skill recipe-diagnose
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: recipe-diagnose
Source: https://github.com/darsoohoo/intake-bot/tree/main/.agents/skills/recipe-diagnose
Command: npx skills add https://github.com/darsoohoo/intake-bot --skill recipe-diagnose

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinates an agent-driven diagnosis workflow to identify concrete failure points in complex AI-driven processes, delivering structured insights and recommended remedies.

Core Features & Use Cases

  • Orchestrated investigation: Spawns investigator, verifier, and solver agents to collect evidence and derive robust conclusions.
  • Evidence-driven resolution: Builds an evidence matrix, maps failure points, and outputs actionable remediation steps.
  • Use Case: Rapidly triage and diagnose intermittent system issues in AI-powered platforms, then present a ready-to-implement plan.

Quick Start

Provide a problem statement and trigger the orchestrated diagnosis workflow to begin investigation, verification, and solution steps.

Frequently Asked Questions about recipe-diagnose

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I diagnose failure points in complex AI workflows?

To diagnose failure points in complex AI workflows, you can trigger an agent-driven diagnosis that coordinates investigator, verifier, and solver agents to collect evidence and determine a structured resolution path.

What is an agent-driven diagnosis workflow for system investigation?

An agent-driven diagnosis workflow is a structured process that spawns investigator, verifier, and solver agents to map execution flows, collect evidence, and identify concrete failure points for final solution reporting.

How do I start an orchestrated investigation for intermittent system issues?

You start an orchestrated investigation by providing a problem statement, which triggers the workflow to register tasks, collect evidence, verify findings, and output actionable remediation steps.

Does the diagnosis workflow include guardrails for design gaps?

Yes, the diagnosis workflow enforces structured task registration and evidence collection with built-in guardrails specifically designed to identify and handle design gaps and coverage issues.

What is the best way to triage and resolve intermittent issues in AI platforms?

The best way to triage intermittent AI platform issues is using an orchestrated agent workflow that builds an evidence matrix, maps failure points, and generates a ready-to-implement remediation plan.

When should I not use an agent-based diagnosis solver?

You should avoid an agent-based diagnosis solver for simple, single-point failures that require no evidence matrix or cross-flow verification, as the structured task registration overhead is designed for complex workflows.