- install.sh / install.ps1: register `hermes` platform (folder-style
symlink to ~/.hermes/skills/understand-anything/). No new directories
or plugin manifests needed — Hermes scans skills via os.walk(...,
followlinks=True) and reads SKILL.md frontmatter directly.
- README × 7 (English + 6 locales): one-line install title, `<platform>`
values, and compatibility table updated for both Hermes and Vibe CLI
(locale READMEs were missing Vibe).
- README × 7: drop top-of-page Star History Rank badge and the TIP-style
thanks blockquote; rewrite the slogan into a longer line about quietly
teaching how the pieces fit; move a single italic thanks line between
Star History and the MIT footer.
- README × 7: remove the two outdated overview-*.gif blocks. The
Features section already opens with a NOTE callout linking to the live
demo, which serves as the visual entry instead.
- Delete assets/overview-{structural,domain}.gif (8.1 MB of orphaned
binaries) from the working tree.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Replace static overview.png with two animated GIFs (structural + domain views)
- Reorder READMEs: Features section before Quick Start
- Remove redundant sections (Why, Who is this for, duplicate feature entries)
- Move project structure/tech stack/dev commands to CONTRIBUTING.md
- Homepage: use Supabase-hosted MP4 videos via GitHub variables, GIF fallback
- Add DEMO_STRUCTURAL_VIDEO_URL and DEMO_DOMAIN_VIDEO_URL to deploy workflow
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Remove ChatPanel and @anthropic-ai/sdk dependency (redundant with /understand-chat)
- Replace Monaco editor with styled summary code viewer
- New graph-first layout: 75% graph + 360px right sidebar
- Dark luxury aesthetic: deep blacks, gold/amber accents, DM Serif Display typography
- Add ProjectOverview component for sidebar default state
- Learn persona now shows tour panel directly in sidebar
- Add schema validation on graph load with error banner
- Defensive null checks in store for tour methods
- Agent pipeline: write intermediate results to disk instead of context
- Agent models: sonnet for simple tasks, opus for complex (no haiku)
- Prompt-engineer all 5 agent prompts and SKILL.md
- Auto-trigger /understand-dashboard after /understand completes
- Add dashboard screenshot to README
- Bump version to 1.0.1
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Lum1104 ·