skills.rest
heyu-ai
heyu-aiOFFICIAL
Explore all skills by this author →
WebsiteGitHub

harness-eval-focus

Inspect and troubleshoot a single harness-eval dimension in Claude Code.

Updated May 15, 2026
Search Tags:#tooling#Claude Code#code audit#issue debugging#workflow inspection
One-click install
npx skills add https://github.com/heyu-ai/yibi-stack --skill harness-eval-focus
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: harness-eval-focus
Source: https://github.com/heyu-ai/yibi-stack/tree/main/skills/harness-eval-focus
Command: npx skills add https://github.com/heyu-ai/yibi-stack --skill harness-eval-focus

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill allows for deep, targeted inspection of a specific harness-eval dimension, facilitating precise identification and resolution of issues.

Core Features & Use Cases

  • Single Dimension Analysis: Perform in-depth audits and troubleshooting on a single harness-eval dimension, such as D1, D2, D3, etc.
  • Issue Resolution: Utilize this skill after running a comprehensive harness-eval to pinpoint issues like warnings or failures.
  • Use Case: If a harness-eval report shows a problem in the 'D2 hook' area, use this skill to deeply investigate and resolve the issue.

Quick Start

Execute the '/harness-eval-focus D2' command to focus on deep inspection for D2 hooks.

Frequently Asked Questions about harness-eval-focus

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

FAQPage Schema
How do I debug a specific harness-eval failure in my Claude Code workflow?▼

To debug a specific harness-eval failure, execute the '/harness-eval-focus' command with the target dimension like D2. This conducts a deep inspection on that single dimension to pinpoint and resolve the issue.

When should I use single dimension analysis for Claude Code issue debugging?▼

Use single dimension analysis after running a comprehensive harness-eval report shows warnings or failures. It allows targeted inspection of specific areas like D2 hooks to isolate problems rather than re-auditing the entire workflow.

Can I run a focused code audit without a full harness-eval report?▼

No, a running harness-eval is required first to identify specific areas of concern. You need the comprehensive report results to know which dimension requires this targeted troubleshooting and deep inspection.

What is the best way to inspect D2 hook issues in a Claude Code harness?▼

The best way to inspect D2 hook issues is running the '/harness-eval-focus D2' command. It deep dives into that single dimension, facilitating precise identification and resolution of the hook problem.

Does targeted workflow inspection work for any harness-eval dimension?▼

Yes, targeted workflow inspection works for any single harness-eval dimension such as D1, D2, or D3. You specify the dimension to focus the deep audit and troubleshooting exactly where needed.

Related Skills

Explore More Software Engineering Skills→
xu-xiangxu-xiang
1.8k

eval-harness

Define, execute, and report capability and regression evals for Claude Code sessions.

Community
Intermediate
loopyardloopyard
21

fix-bug

Reproduce bugs in Elixir/Mix projects using a test-first workflow.

Official
Intermediate
Angriff36Angriff36

Task Orchestrator Hooks Builder

Generate bash hook scripts for Task Orchestrator cascade events.

Community
Advanced
nobelknobelk

security-scan

Identify security vulnerabilities in codebases via manual review and automated pattern detection.

Community
Advanced