investigate-run Skill
Investigates PhysicsIntern workspace run. Use to understand what went wrong and could be improved in the multi-agent research process. Published by huggingface in physics-intern.
Decision snapshot
Is this a fit?
Data analysis, Design and media, Writing, Research
Compatibility not yet detected.
Read-only mode detected, Read-only mode, Filesystem access
Copy skill directory
3 months ago
Access note: Local files.
What is investigate-run Skill?
Investigates PhysicsIntern workspace run. Use to understand what went wrong and could be improved in the multi-agent 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. See how SkillIndex evaluates profiles.
Key capabilities
- Includes SKILL.md support
- Reusable instructions support
- Data analysis
- Design and media
- Writing
- Research
- Data analysis use cases
Declared skill metadata
- Source file: .claude/skills/investigate-run/SKILL.md
Allowed tools declared by source
These fields retain source and confidence evidence from the indexed SKILL.md.
Compatibility and setup
- Install or run with Copy skill directory
- Local files
Requirements and access
Security and permissions
Review permissions before connecting any MCP server to an agent. Pay special attention to whether it can read local files, write data, call external services, or perform destructive actions.
When to use investigate-run Skill
- Use it for data analysis.
- Use it for design and media.
- Use it for writing.
- Use it for research.
Built with
Editorial notes
Source
- Creator: huggingface
- Repository: huggingface/physics-intern
- Skill file: .claude/skills/investigate-run/SKILL.md
What it does
Investigates PhysicsIntern workspace run. Use to understand what went wrong and could be improved in the multi-agent research process.
Skill instructions
Analyze a PhysicsIntern Run Read README.md to understand how the multi-agent research process works. Given a workspace directory (under workspaces/ in the PhysicsIntern project), perform a systematic post-mortem analysis of the run and its failure modes and inefficiencies. 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. Key deliverables: - A list of specific failures, which agent or part of the framework didn't work, when, and why. - A list of insights for improvements in the process design, improved agents (prompt, tools), and scaffold adjustments. Tools For any python code you need to write to analyze the file, use the /tmp folder to write and run temporary files. Do not run directly in the command line. Instead, write a python script that
Verified compatibility and discovery
Frequently asked questions
What is investigate-run?
investigate-run is a open-source AI agent skill with Copy skill directory. Investigates PhysicsIntern workspace run. Use to understand what went wrong and could be improved in the multi-agent research process.
Who is investigate-run best for?
investigate-run is best for reusing agent instructions, scripts, and references, data analysis workflows, design and media workflows, writing workflows.
How do I install investigate-run?
Install or run investigate-run using Copy skill directory. Check investigate-run for the latest setup command.
Is investigate-run actively maintained?
investigate-run may need a closer maintenance check before production use.
Project health auto-fetched from the source repository.
Maintain this resource?
Review this source-backed profile, send a correction with evidence, or link to it from your documentation. Claims verify your relationship to the project; profile facts still require source evidence and editorial review.
