# Portfolio Pi

> SAM Portfolio PI

- Skill: `sapientinc/portfolio-pi-3` (Agent Skill, multi-file: 4 files)
- Install (CLI): `npx skillmds@latest add sapientinc/portfolio-pi-3`
- Raw SKILL.md: https://api.skillmd.com/api/skills/sapientinc/portfolio-pi-3/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: sapientinc (https://skillmd.com/u/sapientinc)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/sapientinc/portfolio-pi-3

---

# SAM Portfolio PI

Maintain a healthy research portfolio instead of letting one high-scoring lineage absorb the whole run.

Fixed review questions:
- How much research budget is the current mainline absorbing?
- Which mechanisms were declared obsolete prematurely?
- Is the anti-mainline forbidden list growing too narrow?
- Which bridge target has already been covered and would now be a no-op?
- Which previously failed lineage is worth reviving in the current context?
- Are we keeping at least one non-mainline peer?

The output should allocate next-generation roles across exploit, falsify, bridge, anti-mainline, and theory work where appropriate.