# Fpa Portfolio Learn

> Use when you run FP&A for several clients and want your practice to compound - mines patterns that generalize across your same-type clients, validates them by leave-one-out cross-client backtesting, and promotes ratified priors and skills into a local library that seeds every new client. All local; nothing leaves your machine.

- **Type:** Skill
- **Install:** `agentstack add skill-jeffbrines-openfpa-fpa-portfolio-learn`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [JeffBrines](https://agentstack.voostack.com/s/jeffbrines)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [JeffBrines](https://github.com/JeffBrines)
- **Source:** https://github.com/JeffBrines/openfpa/tree/main/skills/fpa-portfolio-learn
- **Website:** https://www.guiderail.io

## Install

```sh
agentstack add skill-jeffbrines-openfpa-fpa-portfolio-learn
```

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

## About

# Portfolio Learn (Loop B)

## Overview

Loop A makes the model better at one client. This makes your *practice* compound:
client #10 starts smarter than client #1 because your library carries what generalized
across #1–9. Everything is local - your own book, on your own machine.

**Core principle:** self-improving, never self-ratifying - propose, you accept. The
objective metric is cross-client: does a pattern learned on some clients fail to
degrade the *others*' backtest?

## Setup

A portfolio manifest `~/.fpa/portfolio.yaml` lists your clients + a business-type tag:

```yaml
library: ~/.fpa/library
clients:
  - { path: ~/clients/acme,  type: d2c-inventory }
  - { path: ~/clients/peak,  type: d2c-inventory }
  - { path: ~/clients/haul,  type: trucking }
```

## Workflow

1. **Load** the manifest (`pyfpa.load_portfolio`).
2. For each business-type with at least 3 clients:
   - **Priors:** let `type_clients = pyfpa.portfolio.clients_of_type(portfolio, type)`.
     `pyfpa.mine_priors(portfolio, type)` finds drivers that cluster tightly; validate each
     with `pyfpa.validate_prior(driver, type_clients)` (leave-one-out). Surface validated
     ones first (by cross-client delta), then unvalidated/judgment.
   - **Skills:** `pyfpa.find_recurring_skills(portfolio, type)` for recurring generated
     skills. Also weigh recurring **structural corrections** across clients (read each
     `.fpa/corrections/` for `type: structural`) - a human-authored pattern that repeats
     is strong signal.
3. **Present** candidates ranked by evidence (support count + cross-client delta).
4. **Ratify.** On your acceptance, `pyfpa.promote_prior` / `pyfpa.promote_skill` writes the
   `~/.fpa/library/` and `library-log.md`. Reversible.

## Guardrails

- Local-only; nothing phones home.
- At least 3 clients to propose; tight-cluster only; a prior must not degrade held-out clients.
- You ratify everything; priors are *seeds*, not mandates - each client's Loop A refines.

## The payoff

New clients inherit the library: **fpa-learn-business** seeds their starting model from
your promoted priors (`pyfpa.seed_from_library`) and offers the promoted skills.

## Next

Promoted → the next new client onboarded via **fpa-learn-business** starts smarter.

## Source & license

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

- **Author:** [JeffBrines](https://github.com/JeffBrines)
- **Source:** [JeffBrines/openfpa](https://github.com/JeffBrines/openfpa)
- **License:** MIT
- **Homepage:** https://www.guiderail.io

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-jeffbrines-openfpa-fpa-portfolio-learn
- Seller: https://agentstack.voostack.com/s/jeffbrines
- 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%.