# Peer Review

> This skill should be used when the user asks to "review portfolio proposals", "rank strategies with Borda voting", "filter IPS violations", or test a candidate portfolio against an adversarial diversifier.

- **Type:** Skill
- **Install:** `agentstack add skill-nutdnuy-self-driving-portfolio-skill-peer-review`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [nutdnuy](https://agentstack.voostack.com/s/nutdnuy)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [nutdnuy](https://github.com/nutdnuy)
- **Source:** https://github.com/nutdnuy/self-driving-portfolio-skill/tree/main/skills/peer-review

## Install

```sh
agentstack add skill-nutdnuy-self-driving-portfolio-skill-peer-review
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# peer-review

Implements the multi-agent strategy review protocol from
Ang/Azimbayev/Kim (2026) §3.1 step 5.

## Steps

1. **Hard-constraint filter** (drop infeasible proposals).
2. **Risk filter** (drop proposals with vol > IPS hard cap).
3. **Three-axis review**: a deterministic rubric rates every surviving
   proposal 1–5 on
   *risk-adjusted return*, *diversification*, *robustness*.
4. **Borda count**: per-axis rankings are converted to tie-aware Borda points;
   points are summed across the three axes.
5. **Adversarial diversifier**: if the Borda winner has effective N  50%, generate an IPS-projected equal-weight challenger. Mark
   it as winning the concentration challenge only when effective N improves by
   more than 20%.
6. Output the top-K (default 5) survivors plus the breakdown.

## CLI

```bash
python skills/peer-review/scripts/peer_review.py \
       --proposals outputs/demo01/pc_proposals.json \
       --ips ips/ips_template.md \
       --top-k 5 \
       --vol-cap 0.18 \
       --out outputs/demo01/peer_review.json
```

Run through `pipeline/orchestrator.py` for schema gating and governed output.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [nutdnuy](https://github.com/nutdnuy)
- **Source:** [nutdnuy/self-driving-portfolio-skill](https://github.com/nutdnuy/self-driving-portfolio-skill)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-nutdnuy-self-driving-portfolio-skill-peer-review
- Seller: https://agentstack.voostack.com/s/nutdnuy
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.