github.com/QwenLM/qwen-code
| Skill | Added | Review |
|---|---|---|
desktop-pet .qwen/skills/desktop-pet/SKILL.md Create pixel-art desktop pet companions for Qwen Code. Generates a customized chibi spritesheet (1536×1872, 8×9 grid) for any character the user names — F1 drivers, anime characters, celebrities, fictional characters, animals, etc. Use when the user says "desktop pet", "桌宠", "桌面宠物", "想要XXX当桌宠", "换个宠物", or similar. | — | |
deflake .qwen/skills/deflake/SKILL.md Stabilize a flaky test with a minimal, assertion-preserving fix — never by weakening or deleting the check. | 69 69 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Reviewed: Version: 8878264 | |
create-issue .qwen/skills/create-issue/SKILL.md Draft and submit a GitHub issue from a user idea or bug description, with bilingual body and correct labels. | 68 68 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Reviewed: Version: 8878264 | |
ci-flaky-patrol .qwen/skills/ci-flaky-patrol/SKILL.md Classify a bounded batch of stale PR CI failures and choose the safest response. | 61 61 Impact — No eval scenarios have been run Securityby High Do not use without reviewing Reviewed: Version: 8878264 | |
bugfix .qwen/skills/bugfix/SKILL.md Fix a bug from a GitHub issue, following the reproduce-first workflow. Use when the user asks to fix a bug, investigate a GitHub issue, or debug a user-reported problem. Takes a GitHub issue URL or number as input. | 76 76 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Reviewed: Version: 8878264 | |
autofix .qwen/skills/autofix/SKILL.md Use when Qwen Code Autofix runs from GitHub Actions or an operator dry-run to choose an approved issue, implement it, or address review feedback on an existing autofix PR. | 72 72 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Reviewed: Version: 62e009a | |
agent-reproduce-feature .qwen/skills/agent-reproduce-feature/SKILL.md Use when reproducing an existing Codex or Claude Code feature in Qwen Code or another agent CLI by choosing a reference agent, capturing HTTP request bodies, prompts, tool/function schemas, terminal output, and then implementing the matching behavior in the target repo. | 71 71 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Reviewed: Version: 62e009a | |
agent-reproduce-align .qwen/skills/agent-reproduce-align/SKILL.md Use after a Codex or Claude Code feature has been implemented in Qwen Code to run the selected reference agent and Qwen Code under the same scenario, capture HTTP and terminal traces, compare request bodies, tool/function schemas, outputs, and iterate until the reproduced behavior is close enough. | 75 75 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Reviewed: Version: 62e009a |