investigate-run Skill
Post-mortem analysis of a PhysicsIntern workspace run (Claude Code, Pi, Codex, or OpenCode host). Reconstructs the trajectory from the session record — JSONL file(s) for Claude/Pi/Codex, the SQLite store for OpenCode — audits methodology adherence against the workspace's own CLAUDE.md / AGENTS.md and skill/agent prompt Published by huggingface in physics-intern-skills.
What is investigate-run Skill?
Post-mortem analysis of a PhysicsIntern workspace run (Claude Code, Pi, Codex, or OpenCode host). Reconstructs the trajectory from the session record — JSONL file(s) for Claude/Pi/Codex, the SQLite store for OpenCode — audits methodology adherence against the workspace's own CLAUDE.md / AGENTS.md and skill/agent prompt Published by huggingface in physics-intern-skills. 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
- Database workflows
- Data analysis
- Database workflows use cases
- Data analysis use cases
Technical details
- Install or run with Copy skill directory
When to use investigate-run Skill
- Use it for database workflows.
- Use it for data analysis.
Built with
Editorial notes
Source
- Creator: huggingface
- Repository: huggingface/physics-intern-skills
- Skill file: .claude/skills/investigate-run/SKILL.md
What it does
Post-mortem analysis of a PhysicsIntern workspace run (Claude Code, Pi, Codex, or OpenCode host). Reconstructs the trajectory from the session record — JSONL file(s) for Claude/Pi/Codex, the SQLite store for OpenCode — audits methodology adherence against the workspace's own CLAUDE.md / AGENTS.md and skill/agent prompt
Skill instructions
Investigate PhysicsIntern Run You are auditing a PhysicsIntern workspace run. Three sources: 1. The workspace at $workspacepath — files, git history, and the actual skills/agents and methodology file the run was operating under (.claude/ + CLAUDE.md for Claude Code, .pi/ + AGENTS.md for Pi, .codex/ + AGENTS.md for Codex, .opencode/ + AGENTS.md for OpenCode). 2. The session record — every prompt, response, and tool call from the run. Single JSONL for Claude Code; main-agent JSONL plus per-skill sub-agent JSONLs for Pi; main-agent JSONL plus per-spawned-agent JSONLs for Codex; a single SQLite database (rows keyed by session, not files) for OpenCode (see Host detection and session locations below). 3. The methodology contract — the workspace's own methodology file and (.claude|.pi|.codex)/agents/ or .opencode/agents/, and (.claude/skills|skills|.agents/skills|.opencode/commands)/. These are the rules the run is being audited against. (Optional: the canonical templates in the parent common
Explore related resources
Frequently asked questions
What is investigate-run?
investigate-run is a open-source AI agent skill with Copy skill directory. Post-mortem analysis of a PhysicsIntern workspace run (Claude Code, Pi, Codex, or OpenCode host).
Who is investigate-run best for?
investigate-run is best for reusing agent instructions, scripts, and references, database workflows, data analysis 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.
Auto-fetched from GitHub.
