# Investigation Plotter

> Generate investigation-specific figures from the local artifact graph (post-run plotting agent).

- Skill: `lamm-mit/investigation-plotter` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add lamm-mit/investigation-plotter`
- Raw SKILL.md: https://api.skillmd.com/api/skills/lamm-mit/investigation-plotter/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: lamm-mit (https://skillmd.com/u/lamm-mit)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/lamm-mit/investigation-plotter

---


# Investigation Plotter

Creates a compact, *investigation-specific* figure set from `~/.scienceclaw/artifacts/**/store.jsonl` for a given
`investigation_id`. This is intended to run **after** the multi-agent investigation completes.

Outputs PNG files into `~/.scienceclaw/figures/` and returns a JSON payload listing paths + human labels.

## CLI

```bash
python3 scripts/run.py --investigation-id sstr2_example_run
python3 scripts/run.py --query sstr2_example_run   # alias
```