Selemene orchestrator
Hub-and-spoke agent-skill clusters, one per stack (Astro·GSAP·Remotion, Tauri, …). Installable via skills.sh.
npx -y skills add Sheshiyer/skill-clusters --skill selemene-orchestratorAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Route Selemene Engine tasks to the right surface: deterministic reports (birth/compatibility/transit) via selemene-core and the @selemene/bridge CLI, or narrative witness readings via selemene-report. USE WHEN the user wants anything under the Selemene/Noesis umbrella but has not named the exact surface.
SKILL.md
1.4 KB, 241 tokens by cl100k_base, as published. Nobody here has run it
Selemene Orchestrator
Hub for the Selemene cluster. Use this when the user mentions Selemene, Noesis, birth chart, compatibility, transit, or witness reading without specifying a tool or surface.
Routing matrix
| User intent | Route to |
|---|---|
| Generate any Selemene report or reading | selemene-report |
| Understand which surface to use | selemene-core |
| Build/modify a Rust engine or report generator | rust-orchestrator |
| Build/modify the bridge CLI or its generators | createcli or direct repo work |
| Build/modify the web intake app | frontend-web-orchestrator or astro-orchestrator |
| Render PDF/DOCX from a generated report | documents-orchestrator |
Rules
- Prefer
selemene-reportfor end-user report requests. - Read
selemene-corebefore making cross-surface decisions. - Never route to a deferred cluster without first running
node ~/.agents/skill-clusters/scripts/tier.mjs --activate <cluster> --apply.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.