Guides

Choose a Resource type

Choose the Resource type by what should happen next, not by the filename you already have.

Resource types

Match the type to the behavior.

Do not make every file generated output. Use a Document for normal knowledge, a Topic for reusable AI guidance, and specialized types only when Playbook should render a role, command, workflow, or lifecycle behavior.

✓

Document

Use it for normal Markdown knowledge that should stay readable before it needs generated output.

✓

Topic

name + title + description

Use it when concise guidance should become AI Channel output.

✓

Reference

category: reference

Use it for same-folder supporting detail such as checklists, examples, tables, and edge cases.

✓

Team member

category: team-member

Use it for a delegated specialist role that can render as each AI Channel's native profile.

✓

Command

category: command

Use it for a user-invoked procedure such as triage, planning, review, or release handoff.

✓

Workflow

category: workflow

Use it for a multi-agent orchestration script that each AI Channel adapts to its native orchestration surface.

✓

Lifecycle

category: lifecycle

Use it for automatic behavior such as hooks, guards, and post-edit checks.

Guide map

Choose the decision you are making.

Source model

Place guidance in the Project, group reusable knowledge in Catalogs, and keep Resources reviewable before they become AI Channel output.

Portable intent

Declare model tier, effort, access, and tools once so each AI Channel can map the Resource into its native format.

Agent instructions

Extract durable rules with agents-md markers instead of hand-editing generated Codex, Claude, or Cursor files.

Channels and sync

Enable AI Channels in sumr.yaml, validate source docs, preview generated files, then write outputs.