🏗️ Extract tome from spire into standalone plugin
Tome is opt-in per project — each project declares its own knowledge management approach. Spire retains a small knowledge-awareness skill that explains what tome does and provides a fallback strategy for projects without it. - New plugins/tome/ with own manifests, README, all 5 sub-skills - Spire keeps skills/knowledge/SKILL.md as awareness stub - Updated all READMEs and marketplace JSONs - tome: namespace refs now correct (tome is its own plugin)
This commit is contained in:
@@ -0,0 +1,54 @@
|
||||
---
|
||||
name: knowledge
|
||||
description: >
|
||||
Knowledge management awareness — explains how a project's knowledge base works,
|
||||
how to navigate it, and what to do when the tome plugin isn't installed. Each
|
||||
project declares its own approach in project.md.
|
||||
---
|
||||
|
||||
# Knowledge Management
|
||||
|
||||
Spire agents (Igor, adepts, athanor) need to orient themselves in a project's knowledge base. How that knowledge is structured varies per project.
|
||||
|
||||
## How projects declare their knowledge approach
|
||||
|
||||
The project's `project.md` (loaded by Igor's skill and by athanor) should describe:
|
||||
|
||||
- Where authoritative docs live (CLAUDE.md files, topic docs, wiki/)
|
||||
- How to navigate them (tome plugin, direct file reads, AGENTS.md routing tables)
|
||||
- What the entry point is (root CLAUDE.md, boot.md, AGENTS.md)
|
||||
|
||||
## When the tome plugin is installed
|
||||
|
||||
If the project has `tome@reliquary` enabled:
|
||||
|
||||
- Use `/tome:navigate` before substantial work in an unfamiliar area
|
||||
- Use `/tome:check` to verify knowledge-layer health after structural changes
|
||||
- Use `/tome:curate` for knowledge maintenance
|
||||
- Use `/tome:handoff` when transitioning between sessions or agents
|
||||
|
||||
Tome provides structured navigation (wiki/, NAV files, boot.md) and automated curation methods. It's the full-featured path.
|
||||
|
||||
## When tome is not installed (fallback)
|
||||
|
||||
Most projects work fine without tome. The fallback strategy:
|
||||
|
||||
1. **Read the root CLAUDE.md / AGENTS.md** — this is always the entry point
|
||||
2. **Follow @-includes and links** — CLAUDE.md files reference each other; follow the chain relevant to your task
|
||||
3. **Check for module-level CLAUDE.md** — many projects have per-module docs (`src/foo/CLAUDE.md`)
|
||||
4. **Use `find` or `glob`** for `**/CLAUDE.md` to discover what documentation exists
|
||||
5. **Read topic docs** if they exist (`docs/topics/`, `docs/`, or similar)
|
||||
|
||||
The fallback is manual but sufficient. Tome automates what fallback does by hand.
|
||||
|
||||
## Installing tome
|
||||
|
||||
To add tome to a project:
|
||||
|
||||
```json
|
||||
{
|
||||
"enabledPlugins": ["tome@reliquary"]
|
||||
}
|
||||
```
|
||||
|
||||
Then run `/tome:init` to scaffold the knowledge structure. This is a one-time setup that creates the wiki/, boot.md, and folder navigation. See the tome plugin's README for details.
|
||||
Reference in New Issue
Block a user