feat(hub): fan out to Biolearn (North-Star toolset) — /longevity-loop auto-grows to 2 toolsets#13
Merged
Merged
Conversation
… /longevity-loop The recommended next step: the one fan-out that's actually needed now. Biolearn is the leaderboard + challenge-data/clock loader that E6 (run Turn 01) and E7 (submit) depend on. Grounded in bio-learn.github.io docs at HEAD 0d714f5a0c0a (no fabrication): - hub/biolearn/knowledge-graph.json — 19 nodes/edges (DataLibrary/GeoData/ModelGallery, real API, real example titles → Turn 01 / leaderboard / clockbench) - hub/biolearn/SKILL.md — biolearn-leaderboard: real API + the two shipped examples that ARE E6/E7, handing the clock panel to clockbench → PROOF.md → submit - hub/biolearn/manifest.json — SHA-stamped (FRESH), provenance Proves fan-out AND auto-wiring: skill_gen re-discovered it → /longevity-loop now discloses 2 toolsets with zero hand-editing. Geneformer/scGPT deliberately left JIT (not needed yet). E26. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The recommended next step, shipped: fan the hub out to the one repo needed now — Biolearn, the leaderboard + challenge-data/clock loader that E6 (run Turn 01) and E7 (first submission) depend on.
Grounded in
bio-learn.github.iodocs at HEAD0d714f5a(no fabrication — exact dataset IDs deferred to the cited example files):hub/biolearn/knowledge-graph.json— 19 nodes/edges:DataLibrary/GeoData/ModelGallery, the real API, and the real example titles ("Exploring the Challenge Data", "Building a competition submission") that map straight to E6/E7 → clockbench.hub/biolearn/SKILL.md—biolearn-leaderboard: the documented API + those two shipped examples, handing the clock panel toclockbench.py --input→PROOF.md→ submit.hub/biolearn/manifest.json— SHA-stamped;--refreshsays FRESH.Proves two things: fan-out works for a 2nd repo, and auto-wiring works —
skill_genre-discovered it, so/longevity-loopnow discloses 2 toolsets with zero hand-editing. Geneformer/scGPT deliberately stay JIT (not needed yet — the architecture's rule). E26; audit 100/100, 15/26 executions.🤖 Generated with Claude Code