~ / leaderboard / skill / debug-loop
Skill · #4312
debug-loop
Run a capped hypothesize-test-narrow loop on a failing test or reproducible bug to find root cause, not patch it. Use when the user has a failing test, stack trace, or reproducible crash.
4rigs use it
0%of all rigs
6.7kavg rig context tax
Get it
$ npx degit protoLabsAI/protoAgent/plugins/engineer/skills/debug-loop .claude/skills/debug-loop From the most-starred rig that ships it: protoLabsAI/protoAgent. Same-named skills in different rigs may differ — review before use.
Often used together with
code-review · 2grilling · 2simplify · 1systematic-debugging · 1test-driven-development · 1performance · 1verification-before-completion · 1design-ui · 1triage · 1deploy · 1
Rigs using debug-loop (4)
protoLabsAI/protoAgent
Local-first agent that drives Claude Code and Codex over ACP. Desktop app, git-URL plugins, A2A 1.0. MIT.
Skill Collector 2.8k tok · · Q0
ychampion/ystack
The power-user stack for AI coding agents: mods, skills, subagents and setup for Claude Code, Codex and OpenCode. Your rules enforced as code, not hoped for in a prompt; long sessions that stay fast and cheap. One-line install, growing ever
Skill Collector 1.6k tok · · Q0
milosCvetkovicDev/claude-code-monorepo
The real Claude Code configuration behind a 13-service TypeScript platform — 71 skills, 34 hooks, 31 agents, 172 memories, one full epic walkthrough — sanitized and organized as a 13-chapter book. A worked example of loop engineering: maker
Orchestrator 15.5k tok · · Q69
jthiruveedula/agentkit
Portable, vendor-neutral agent foundation for Claude Code, Copilot, Cursor, and Antigravity — one command restores your skills/agents/commands on any machine.
Orchestrator 7.1k tok · · Q0