by bydtesla1609
Supervising whether AI really promotes cross-platform skills in research programs
# Add to your Claude Code skills
git clone https://github.com/bydtesla1609/research-solution-supervisorGuides for using ai agents skills like research-solution-supervisor.
See how research-solution-supervisor compares with popular alternatives.
research-solution-supervisor is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by bydtesla1609. Supervising whether AI really promotes cross-platform skills in research programs. It has 52 GitHub stars.
research-solution-supervisor's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/bydtesla1609/research-solution-supervisor" and add it to your Claude Code skills directory (see the Installation section above).
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh research-solution-supervisor against similar tools.
No comments yet. Be the first to share your thoughts!
Unlocks once the catalog security scan passes (runs nightly).
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
research-solution-supervisor vs everything claude code
See comparison
Research Solution Supervisor 是一个面向研究型工作的 AI 监督 skill。它不负责把研究重新做一遍，而是判断 AI 的回答、研究 pass 或方案建议是否真正推进了用户的研究目标，并把结论转成下一步可执行动作。
它适合用在这样的时刻：
这个 skill 借鉴了 Intent Debugger 的思路：先把目标和判断标准说清楚，再评估当前输出是否满足这些标准。不同点在于，Intent Debugger 更偏“把模糊意图变成可确认需求”，Research Solution Supervisor 更偏“监督 AI 是否让研究方案真的向前走”。
一次典型监督会输出四块内容：
research-solution-supervisor/
|-- README.md
|-- skill/
| `-- research-solution-supervisor/
| |-- SKILL.md
| `-- agents/
| `-- openai.yaml
`-- adapters/
|-- codex/
|-- claude-code/
`-- deepseek/
把 skill/research-solution-supervisor 复制到 Codex 可发现的 skills 目录中：
mkdir -p "$HOME/.agents/skills"
cp -R skill/research-solution-supervisor "$HOME/.agents/skills/"
在部分本地 Codex Desktop 环境里，skills 目录可能是 $CODEX_HOME/skills 或 $HOME/.codex/skills。如果你的 Codex 已经在这些目录发现个人 skill，也可以复制到对应目录。
更多说明见 adapters/codex。
Claude Code 支持从用户级或项目级 skills 目录加载 skill。把同一个 skill 文件夹复制到 .claude/skills 或用户级 skills 目录即可：
mkdir -p .claude/skills
cp -R skill/research-solution-supervisor .claude/skills/
更多说明见 adapters/claude-code。
DeepSeek API 本身不会自动读取本地 SKILL.md 目录。适配方式是把 SKILL.md 的说明作为 system/developer prompt 的一部分注入到对话里，再把用户的研究方案和 AI 输出作为待监督材料传入。
更多说明见 adapters/deepseek。
使用 research-solution-supervisor。
我的研究目标是：比较几种数学建模思路，找出最适合比赛论文的方案。
当前 AI 给出的方案如下：
...
请判断它是否真正推进了我的研究流程，指出关键缺口，并给出下一步最有效动作。
适用：
不适用：