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.

Quality

97%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, well-structured meta-skill: actionable numeric thresholds, a clear checklist workflow with feedback loops, and appropriate single-file organization. The only minor gap is a few trimmable reinforcing adages affecting conciseness.

Suggestions

Remove well-known adages like 'Never repeat a failed action hoping for a different result' that restate the adjacent retry-cap rule, to tighten conciseness toward the top anchor.

Reduce overlap between the summary table's action column and the Section 1-3 elaborations — either let the sections carry the detail or have the table point to them, not both.

Dimension	Reasoning	Score
Conciseness	Largely lean — table, bullets, and checkboxes carry the load with operational definitions rather than padding — but a few reinforcing adages ('Never repeat a failed action hoping for a different result') and slight overlap between the summary table and the section elaborations could be trimmed, sitting just below the top anchor.	4 / 5
Actionability	Though code-free, the guidance is concrete and directly executable: '~1000 words per step', 'never run the same failing command a 3rd time', the checkbox count→action map, and 'save the file, commit, write the result' — specific thresholds covering the common cases per the instruction-only exception.	5 / 5
Workflow Clarity	A clear pre-step checklist workflow with explicit checkpoints ('finish this step, then hand off', 'One edit → one check') and feedback loops (3-retry cap, 'looped 2+ times → declare unsolved-for-now and move on'), matching the checklist-plus-feedback-loops top anchor.	5 / 5
Progressive Disclosure	A single self-contained, well-organized file with clear headers, a table, and numbered sections; no external references are needed and none are nested, so the simple-skill exception places it at the top anchor.	5 / 5
	Total	19 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An excellent description: third-person, concrete in its actions, and explicit on both what it does and when to use it, with a rich set of natural trigger synonyms. No weaknesses against the rubric anchors.

Dimension	Reasoning	Score
Specificity	Names four concrete actions — 'breaks out of looping/circular thinking, watches the context budget, bounds internal reasoning, and triggers a clean handoff before the window fills' — comprehensively covering the three failure modes it identifies, matching the top anchor.	5 / 5
Completeness	Explicitly answers both what (keeps a long task on-track via the four actions) and when (two 'Use when…' clauses with concrete trigger phrases), matching the top anchor; third-person voice throughout.	5 / 5
Trigger Term Quality	Includes natural user phrasings with synonyms — 'looping', 'going in circles', 'stuck', 'repeating itself', 'spinning', and 'asks for a handoff before running out of context' — exactly what a user would say, matching comprehensive synonym coverage.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — meta-cognitive loop-breaking and context-budget handoff for long tasks — with distinct triggers unlikely to fire for unrelated skills, matching the minimal-conflict top anchor.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: thananon/9arm-skills
Path: skills/productivity/qwenchance/SKILL.md
Commit: a1fc303

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.