~ / leaderboard / skill / gauntlet-loop
Skill · #2642
gauntlet-loop
Run a Gauntlet Loop (Matt Shumer's method), driving work toward a concrete reference standard with paired builder and critic agents that loop until the output matches the bar. Use when the user says "
6rigs use it
0%of all rigs
13.6kavg rig context tax
Get it
$ npx degit mintuz/skills/src/core/skills/gauntlet-loop .claude/skills/gauntlet-loop From the most-starred rig that ships it: mintuz/skills. Same-named skills in different rigs may differ — review before use.
Often used together with
review · 3debug · 3audit · 2handoff · 2code-reviewer · 2graphify · 2plan · 2pr · 2implement · 2teach · 2
Rigs using gauntlet-loop (6)
mintuz/skills
My collection of Claude Code, Codex and OMP Agent Skills for web and iOS Development
Skill Collector 24.8k tok · · Q0
SkyWalker2506/claude-config
Multi-Agent OS for Claude Code — 134 agents, 15 categories, local-first routing, 14 plugins, cost-aware orchestration
Orchestrator 9.9k tok · · Q14
zorahrel/jarvis
Personal AI setup in the open: Claude Code, Codex, jcode and an OpenClaw assistant. Public half here, private half in an encrypted git submodule — a pattern you can copy.
Skill Collector 1.3k tok · · Q5
zznabil/lean-agent-skill-collection
Twenty-four compact, vendor-neutral agent skills for engineering, research, communication, documents, experiments, and quality work, plus optional review-only standards packs.
Skill Collector 6.2k tok · · Q8
Mariano215/tack
Run a different Claude Code and Codex setup in every terminal. One profile drives both agents, with per-terminal config isolation.
Skill Collector 3.9k tok · · Q5
damilola-elegbede-org/claude-config
Configurations Files for Claude
YOLO Cowboy 35.3k tok · · Q0