investigate-autophysicist-run Skill
Investigates an Autophysicist workspace run. Use to understand what went wrong and could be improved in the single-agent iterative research process. Published by huggingface in physics-intern.
What is investigate-autophysicist-run Skill?
Investigates an Autophysicist workspace run. Use to understand what went wrong and could be improved in the single-agent iterative research process. Published by huggingface in physics-intern. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.
Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement.
Key capabilities
- Includes SKILL.md support
- Reusable instructions support
- Data analysis
- Design and media
- Research
- Data analysis use cases
- Design and media use cases
Technical details
- Install or run with Copy skill directory
When to use investigate-autophysicist-run Skill
- Use it for data analysis.
- Use it for design and media.
- Use it for research.
Built with
Editorial notes
Source
- Creator: huggingface
- Repository: huggingface/physics-intern
- Skill file: .claude/skills/investigate-autophysicist-run/SKILL.md
What it does
Investigates an Autophysicist workspace run. Use to understand what went wrong and could be improved in the single-agent iterative research process.
Skill instructions
Analyze an Autophysicist Run Read README.md to understand how the Autophysicist research mode works (single-agent iterative loop with ephemeral sub-agents). Given a workspace directory (under workspaces/ in the PhysicsIntern project — autophysicist runs end in autophysicist; legacy runs may live under workspaces/autophysicist/), perform a systematic post-mortem analysis of the run. The user may provide a folder name or path; if ambiguous, list available workspaces and ask. Check references/ in the project root for a reference document matching the problem. These files describe what a correct answer looks like and what a typical successful run looks like for known problems. The reference is written for the vanilla multi-agent pipeline, but the correct answer and key pitfalls still apply. Key deliverables: - A list of specific failures and inefficiencies: what went wrong, in which iteration, and why. - Assessment of the Manager's strategic quality: decomposition, sub-agent design, verifi
Explore related resources
Frequently asked questions
What is investigate-autophysicist-run?
investigate-autophysicist-run is a open-source AI agent skill with Copy skill directory. Investigates an Autophysicist workspace run. Use to understand what went wrong and could be improved in the single-agent iterative research process.
Who is investigate-autophysicist-run best for?
investigate-autophysicist-run is best for reusing agent instructions, scripts, and references, data analysis workflows, design and media workflows, research workflows.
How do I install investigate-autophysicist-run?
Install or run investigate-autophysicist-run using Copy skill directory. Check investigate-autophysicist-run for the latest setup command.
Is investigate-autophysicist-run actively maintained?
investigate-autophysicist-run may need a closer maintenance check before production use.
Auto-fetched from GitHub.
