From factoria
Use when the factory is known but its policies, ADRs, and technology stack have not yet been loaded into context — typically at session start or after factory selection
How this skill is triggered — by the user, by Claude, or both
Slash command
/factoria:loading-factory-contextThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
For the active factory (replace `<factory>` with `net`, `ang`, `nest`, `pyt`, `pytml`, `dataeng`, `kot`, `swf`, or `wps`):
For the active factory (replace <factory> with net, ang, nest, pyt, pytml, dataeng, kot, swf, or wps):
Read: references/<factory>/CLAUDE.md
This establishes the technology stack, golden rules, and architecture overview.
Read all: references/<factory>/policies/*.md
Net/Ang/Pyt typically have 6 policies (security, testing, coding-standards + qa, performance, security-testing). DataEng has 6 specialized policies. Kot/Swf/Wps have 3–4. Read them all.
Read: references/<factory>/adrs/ADR-001-*.md
Read: references/<factory>/adrs/ADR-002-*.md
Read: references/<factory>/adrs/ADR-003-*.md
Read: references/<factory>/adrs/ADR-004-*.md
Read: references/<factory>/adrs/ADR-005-*.md
For tasks touching infrastructure, security, testing, or CI/CD: read all ADRs (count varies 10–15 by factory).
Confirm to the user (or yourself if running autonomously):
"Factoria context loaded for factory:
<factory>. 3 policies and N ADRs active."
Then proceed with the original user task.
| Thought | Reality |
|---|---|
| "I already know this factory's rules" | Context windows are fresh each session. Read them. |
| "Loading all ADRs is too many tokens" | ADRs are the contract. Skipping them means violations. |
| "I'll load later if needed" | Load NOW, before any code generation. |
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub juankmvanegas/factoria-powers --plugin factoria