Home / Skills / agent-reproduce-align
agent-reproduce-align
QwenLM/qwen-codeSkill
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.
Why this score
This repo hosts 10 skills, so its 28,586 stars are split between them (about 2,859 each) for scoring.
Popularity score: 85/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank
Security
Scanned Oct 20, 2026 at commit 5936225e43f9, with Cisco's open-source skill-scanner.
None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.
A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan
Alternatives
Other makers' add-ons that do the same job, next to this one.
| Name | Score | Stars | Context | Updated |
|---|---|---|---|---|
| This oneagent-reproduce-align QwenLM/qwen-code · Skill | 85 | ★ 29k | ≈80 always | 16d ago |
| llm-align Calibre-Labs/reforge-ai-evals · Skill Both about align | 54 | ★ 76 | ≈22 always | 16d ago |
| reproduce-bug googleapis/mcp-toolbox · Skill Both about reproduce | 85 | ★ 17k | ≈22 always | 16d ago |
| reproduce cloudflare/agents · Skill Both about reproduce | 83 | ★ 5.9k | ≈48 always | 16d ago |
| align-recipe-pyproject google/adk-recipes · Skill Both about align | 82 | ★ 10k | ≈24 always | 16d ago |
| lov-align-wechat-uiux lovstudio/skills · Skill Both about align and behavior | 54 | ★ 72 | ≈35 always | 21d ago |