agentleFS
austin-starksaustin-starks/Public-Portfolio-Challenge/skills/walk-forward-oos/AGENTS.md

Public-Portfolio-Challenge / walk-forward-oos

AGENTS.md82 starsChanged 3 months agoMITView on GitHub

Run and read a NexusTrade walk-forward out-of-sample study — the certification engine behind the Public Portfolio Challenge. Use when certifying a fixed portfolio (backtest_only) or re-optimizing one (sweep), when setting fold_count / anchored / validation / embargo params, when monitoring a run_walk_forward_study to completion, when reading per-fold OOS returns/Sortino/drawdown, or when a variant's fold calendar needs calendar-alignment against a base control. Invoke with the NexusTrade MCP connected. Invoke with /walk-forward-oos, or let it auto-activate when a task matches the description…

The file

Files
AGENTS.md

walk-forward-oos

Run and read a NexusTrade walk-forward out-of-sample study — the certification engine behind the Public Portfolio Challenge. Use when certifying a fixed portfolio (backtest_only) or re-optimizing one (sweep), when setting fold_count / anchored / validation / embargo params, when monitoring a run_walk_forward_study to completion, when reading per-fold OOS returns/Sortino/drawdown, or when a variant's fold calendar needs calendar-alignment against a base control. Invoke with the NexusTrade MCP connected.

Activation

Invoke with /walk-forward-oos, or let it auto-activate when a task matches the description above. This is a SKILL.md skill on the open Agent Skills standard — Claude Code, Codex CLI, Cursor, Gemini CLI, GitHub Copilot and ~15 other tools read it (natively or via the install.sh adapter).

Usage

See SKILL.md for the full workflow, triggers, hard constraints, and detail. Reference material (if any) lives in references/.

Requirements

The NexusTrade MCP server must be connected — this skill drives NexusTrade's deterministic backtest/certification/compute tools (deferred; load schemas via ToolSearch).

Part of

The Public Portfolio Challenge skills library — a functional decomposition of the Episode 10 certification runbooks. See the library index at ../README.md.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.