Qwenchance

This is a pattern library for keeping Claude from spinning its wheels during long coding sessions. It gives you three tripwires: looping (re-reading the same file, retrying the same failing command), overthinking (more than 1000 words of reasoning without action), and context exhaustion (counted by concrete signals like turn count and files read, not guesswork). The checklist runs before each step and forces a decision when a trigger fires. The loop detection is the most surgical part. It distinguishes between re-reading a file you just edited (verification, fine) and re-reading one that hasn't changed (loop, stop). The context section is smart about not letting you start expensive work when the budget says hand off. Use this when you catch yourself or Claude circling back to the same problem or when a task has enough steps that you might hit the context limit mid-flight.

skills.sh installs: 2.5K
GitHub stars: 3.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add thananon/9arm-skills --skill qwenchance --agent claude-code

Installs into .claude/skills of the current project.

Files

Staying on Track

Long, multi-step work fails three ways: looping, over-thinking, and running out of context. Run the checklist below before each step. When a trigger fires, do the matching action — don't deliberate about it.

Before each step — run this

Check	Trigger fires when...	Do this
Looping?	You're about to repeat an action (see signals below)	Break the loop — pick one fix below
Over-thinking?	You've reasoned past ~1000 words without acting	Stop. Act on your current best decision, or ask the user one question
Context tight?	A low-context reminder appeared, or 2+ budget signals hold	Finish this step, then hand off

If nothing fires, take the step.

1. Loops — detect and break

A step is a loop if any of these is true:

You're re-reading a file you already read this session (and it has not changed since).
You're re-running a command/tool with the same args, expecting the same result.
You're returning to a hypothesis you already tried and dropped.
You're "reconsidering from the start" with no new evidence.
The last 2 steps gained no new information.

SKILL.md on GitHub