docs: fix first-time experience — remove fictional kindling, add recommended schema (#3)

* docs: add recommended brain schema

Full LLM-maintained knowledge base architecture: MECE directory structure,
compiled truth + timeline pages, enrichment pipeline, resolver decision
tree, skill architecture, and cron job recommendations.

* docs: fix first-time experience — remove fictional kindling, add GitHub URL

- Remove all references to data/kindling/ (never existed)
- OpenClaw paste now references https://github.com/garrytan/gbrain
- "Try it" section rewritten as three-act story with user's own data
- Agent picks dynamic query based on imported content
- Step 5 links to recommended schema doc for brain restructuring
- Includes bun install fallback in paste step 1

* chore: bump version and changelog (v0.2.0.1)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

CHANGELOG.md

@@ -2,6 +2,17 @@
 
 All notable changes to GBrain will be documented in this file.
 
+## [0.2.0.1] - 2026-04-07
+
+### Added
+
+- Recommended brain schema doc (`docs/GBRAIN_RECOMMENDED_SCHEMA.md`): full MECE directory structure, compiled truth + timeline pages, enrichment pipeline, resolver decision tree, skill architecture, and cron job recommendations. The OpenClaw paste now links to this as step 5.
+
+### Changed
+
+- First-time experience rewritten. "Try it" section shows your own data, not fictional PG essays. OpenClaw paste references the GitHub repo, includes bun install fallback, and has the agent pick a dynamic query based on what it imported.
+- Removed all references to `data/kindling/` (a demo corpus directory that never existed).
+
 ## [0.2.0] - 2026-04-05
 
 ### Added