aif-warmup

Loads AI Factory project context files and returns a compact session handoff summary.

1.1k|96|Updated Feb 6, 2026
One-click install
npx skills add https://github.com/lee-to/ai-factory --skill aif-warmup
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: aif-warmup
Source: https://github.com/lee-to/ai-factory/tree/main/skills/aif-warmup
Command: npx skills add https://github.com/lee-to/ai-factory --skill aif-warmup

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Starting a new AI session or recovering from context loss usually means re-reading project documentation manually. This Skill reads the configured AI Factory artifacts (DESCRIPTION, ARCHITECTURE, ROADMAP, RESEARCH, RULES, and applicable AGENTS.md files) and produces a compact, self-contained handoff so work can continue or fork cleanly.

Core Features & Use Cases

  • Config-driven context resolution: Reads .ai-factory/config.yaml to resolve custom artifact paths, language, git, and workflow preferences, falling back to documented defaults.
  • Ordered artifact loading: Reads core artifacts and nested AGENTS.md files from broadest to most specific, with more specific rules overriding broader ones.
  • Structured handoff output: Returns sections covering configuration, project state, architecture, direction, rules, gaps, loaded paths, and readiness.
  • Use Case: After a long session hits the context limit, invoke the warmup command at the start of a new session to reload project purpose, active roadmap priorities, and non-negotiable rules without touching any files.

Quick Start

Run the aif-warmup skill at the start of a new session to load the project context and receive a compact handoff summary.

Frequently Asked Questions about aif-warmup

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

FAQPage Schema
How do I restore AI project context after losing a session?

Invoke the aif-warmup skill at the start of a new session. It reads the configured DESCRIPTION, ARCHITECTURE, ROADMAP, RESEARCH, and RULES artifacts plus applicable AGENTS.md files, then returns a compact handoff summary so work can continue or fork.

What files does AI Factory warmup read?

It reads .ai-factory/config.yaml first, then DESCRIPTION, ARCHITECTURE, ROADMAP, RESEARCH, and RULES artifacts, plus AGENTS.md files from the repository root down to the current working directory. Extra paths can be added via the warmup.paths config key.

Does aif-warmup modify any project files?

No. The skill is strictly read-only and never creates or modifies files, code, branches, plans, or config. It stops after producing the handoff so the session remains a clean fork point.

What happens if AI Factory config or artifacts are missing?

Missing artifacts are recorded as gaps and skipped, and missing config values fall back to documented defaults such as .ai-factory/DESCRIPTION.md. If the config cannot be parsed, the skill reports that and continues with defaults.

When should I not use the warmup skill?

Do not use it to scan application code, git history, or external sources, since warmup deliberately skips those. It is meant only for loading project context at session start, not for task-specific investigation or implementation.