qwenchance
Keeps a long Claude Code task on-track — breaks out of looping/circular thinking, watches the context budget, bounds internal reasoning, and triggers a clean handoff before the window fills. Use when the model is repeating steps, re-reading the same files, second-guessing in circles, stuck or spinning, or running a long multi-step task at risk of exhausting context. Also use when the user says it is "looping", "going in circles", "stuck", "repeating itself", or asks for a handoff before running out of context.
- Installs
- 2.4K
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/thananon/9arm-skills --skill qwenchance- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads qwenchance automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
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.
Re-reading a file you just edited is NOT a loop — that's verifying.
When a loop fires, stop and do exactly one:
- State the blocker in one sentence and ask the user a specific question.
- Write what you know vs. don't know, then take a different action than last time.
- Looped 2+ times on the same sub-problem? Declare it unsolved-for-now; move on or hand off.
Never repeat a failed action hoping for a different result.
Retry cap: never run the same failing command a 3rd time. Can't get something working (a command, a test runner, an import) after ~3 attempts — even varied ones — STOP and ask the user; don't grind through more variations.
Don't edit blind — it's the top loop source. Read enough to know the change is correct before editing. After each edit, verify it (read the diff / run it / run the test) before the next step. One edit → one check.
2. Thinking — keep it bounded
Cap reasoning at ~1000 words per step. Past that, you're deliberating instead of acting.
- Decide → act → observe. Don't re-derive a decision you already made.
- Can't decide in ~1000 words? The task is underspecified — ask the user one sharp question.
- Don't restate the whole problem to yourself. Reference what you concluded; don't rebuild it.
3. Context budget — count signals, don't estimate
Authoritative: A <system-reminder> about low context / approaching auto-compaction. → Hand off now (section 4). Don't start new work.
Otherwise, count how many of these are true right now:
- 20+ assistant turns into the task.
- Read 5+ files, or any one huge file/log/dump.
- Long tool outputs you keep scrolling back to.
- 3+ plan steps still left.
Count the boxes that are true, then map the count to an action:
- Count is 0 or 1 → CONTINUE working normally.
- Count is 2, 3, or 4 → HAND OFF — finish the current step, then go to section 4.
Count first, then decide — don't judge by feel. A higher count means more context pressure, not less. Being on the last step or "almost done" does not lower the count or cancel a HAND OFF.
Before any expensive step (large read, new subtask, long generation), ask: "Room to finish this AND hand off after?" If the count says HAND OFF, finish the current atomic unit, then hand off — don't start the next.
4. Hand off cleanly
When context is tight or the user asks:
- Land durable artifacts first — save the file, commit, write the result. Nothing lost.
- Invoke the
handoffskill to compact the conversation. Don't hand-write the handoff. - Tell the user plainly: "Context is getting tight — handing off now; start a fresh session (
/clear)."
FAQ
What does the qwenchance skill do?
Keeps a long Claude Code task on-track — breaks out of looping/circular thinking, watches the context budget, bounds internal reasoning, and triggers a clean handoff before the window fills. Use when the model is repeating steps, re-reading the same files, second-guessing in circles, stuck or spinning, or running a long multi-step task at risk of exhausting context. Also use when the user says it is "looping", "going in circles", "stuck", "repeating itself", or asks for a handoff before running out of context.
How do I install qwenchance?
Run npx skills add https://github.com/thananon/9arm-skills --skill qwenchance in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/qwenchance/ (personal) or .claude/skills/qwenchance/ (project).
Which AI agents can use qwenchance?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is qwenchance safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains qwenchance?
It is published by thananon in thananon/9arm-skills. It has 2,448 recorded installs.
More from thananon/9arm-skills
scrutinize
thananon/9arm-skills
Outsider-perspective end-to-end review of a plan, PR, or code change. First questions intent and whether a simpler/more elegant approach would achieve the same goal, then traces the actual code path (not just the diff) to verify the change does what it claims. Output is concise, actionable, and every call carries its rationale. Trigger on /scrutinize and proactively whenever the user asks to review, audit, sanity-check, or get a second opinion on a plan, PR, diff, design doc, or proposed code change.
debug-mantra
thananon/9arm-skills
Four-mantra debugging discipline — reproduce, trace the fail path, falsify the hypothesis, cross-reference every breadcrumb. Recite the mantra block verbatim at the start of any debugging session, then apply the four steps in order before proposing any fix. Trigger on /debug-mantra and proactively whenever debugging starts — user reports a bug, says something is broken/throwing/failing, asks to debug/diagnose/investigate an issue, or pastes a stack trace or error log.
post-mortem
thananon/9arm-skills
Write the canonical engineering record of a fixed bug — root cause, mechanism, fix, validation, and how it slipped through. Engineer-audience, code identifiers welcome. Use after a debug session lands a fix, before closing the ticket. Trigger on /post-mortem, when the user says "write the post-mortem / postmortem / RCA / root cause analysis", "document this fix", "write up the root cause", "close out this bug with a writeup", or hands you a fixed-and-validated bug and asks for the writeup.
management-talk
thananon/9arm-skills
Rewrite engineer-to-engineer content for engineering-org leadership (VPs, directors, PMs, release managers, execs in an engineering-savvy company) and shape it for the channel it is going to — JIRA comment, Slack post, async standup line, email, or meeting talking-points. Trigger when the user asks to write/rewrite for management / exec / VP / director / PM / release manager, asks for an "executive summary / leadership update / status update", says "make this less technical / less jargony", or asks for a slack / email / standup / meeting version of work originally written engineer-to-engineer.
qwen-agent
thananon/9arm-skills
Delegate menial, well-scoped coding tasks to a cheap Qwen-backed subagent via the claude-9arm command instead of burning Claude tokens/quota. Use when the work is mechanical and low-risk — bulk renames, formatting, boilerplate, find-replace, grep-style search & summarization, reading/condensing logs or files, test/docstring/comment scaffolding, or running builds/linters/tests and reporting pass-fail. Also use when the user says "use qwen", "delegate this", "send it to 9arm/qwen", or "do this cheaply". Do NOT use for architecture, design, debugging judgment, security-sensitive edits, or anything needing this conversation's context.
Popular code quality & workflow skills
grill-me
mattpocock/skills
A relentless interview to sharpen a plan or design.
improve-codebase-architecture
mattpocock/skills
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
handoff
mattpocock/skills
Compact the current conversation into a handoff document for another agent to pick up.
domain-modeling
mattpocock/skills
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.
codebase-design
mattpocock/skills
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
diagnosing-bugs
mattpocock/skills
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.