plan

Scan Python/ML codebases to generate program.md run specs with metric and guard configurations.

24|3|Updated Feb 22, 2026

Search Tags:#research #profiling #plan #ml #experiments #program-md

Ready to run

npx skills add https://github.com/Borda/AI-Rig --skill plan-borda

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: plan
Source: https://github.com/Borda/AI-Rig/tree/main/plugins/research/skills/plan
Command: npx skills add https://github.com/Borda/AI-Rig --skill plan-borda

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides an interactive wizard that scans a codebase to propose a metric, guard, and agent configuration, then writes a program.md run spec and optionally profiles the target with cProfile to surface bottlenecks before optimization goals.

Core Features & Use Cases

Scans codebases to surface measurable goals and configuration for experiments.
Generates a deterministic program.md plan that captures the planned run, including metrics and guards.
Profiles a target file to surface bottlenecks and informs goal selection.

Quick Start

Run /research:plan with a goal or target file to generate a program.md plan and begin profiling.

Frequently Asked Questions about plan

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I generate a run spec for ML experiments?▼

ML experiment profiling uses cProfile to scan a target Python file and surface bottlenecks before execution, informing your optimization goals and metric selection. It helps identify performance constraints prior to running experiments.

What is a program.md run spec for research planning?▼

A program.md run spec is a frontmatter-driven plan that captures your ML experiment's configuration blocks, including metrics, guards, and scope, ensuring a deterministic execution plan for your research project.

Can I profile a Python file before planning optimization goals?▼

Yes, you can profile a target Python file with cProfile before planning optimization goals. This optional step surfaces bottlenecks and informs measurable goal selection for your ML experiments.

Does this research planning tool work with any Python ML project?▼

This research planning tool is applicable to Python and ML open-source software projects. It scans the codebase to propose structured configuration blocks and generate a run spec tailored to your project.

What's the best way to define metrics and guards for ML experiments?▼

The best way to define metrics and guards for ML experiments is scanning your codebase to propose a deterministic configuration. This Skill surfaces measurable goals and generates structured metric, guard, and scope blocks in a program.md plan.