Update to Biohub ESM

{
  "name": "biohub-esm",
  "description": "Route Biohub ESM requests to ESMC, ESMFold2, ESM Atlas, Modal, or private open weights. Use for explicitly ESM/Biohub work, ESM protein representations or mutation scoring, ESMFold2 folding, Atlas discovery, ESM binder design, or choosing an ESM compute route. Do not use for unrelated non-ESM models, generic sequence alignment, or standalone structure viewing unless the user explicitly asks to compare it with Biohub ESM.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 228
    },
    {
      "relative_path": "references/failures.md",
      "size_in_bytes": 3402
    },
    {
      "relative_path": "references/routing.md",
      "size_in_bytes": 5798
    }
  ],
  "skill_md_contents": "---\nname: biohub-esm\ndescription: Route Biohub ESM requests to ESMC, ESMFold2, ESM Atlas, Modal, or private open weights. Use for explicitly ESM/Biohub work, ESM protein representations or mutation scoring, ESMFold2 folding, Atlas discovery, ESM binder design, or choosing an ESM compute route. Do not use for unrelated non-ESM models, generic sequence alignment, or standalone structure viewing unless the user explicitly asks to compare it with Biohub ESM.\n---\n\n# Biohub ESM router\n\nUse this as the implicit entry point. Identify the scientific goal before choosing a model or provider; ESMC, ESMFold2, and Atlas are different artifacts.\n\n## Route first\n\n| User need | Default | Escalation |\n| --- | --- | --- |\n| Existing-protein discovery, functional neighborhoods, Atlas feature catalog, clusters | public Atlas alpha API | anonymous Atlas S3 for bulk data |\n| SAE activation extraction or interpretation for an input sequence | Biohub managed ESMC | pinned ESMC weights for private or custom work |\n| Public ESMC inference, including bounded concurrent calls | Biohub managed API | self-host for private, custom, sustained, or owned-compute work |\n| One or modest structure predictions | Biohub managed ESMFold2 | full + MSA for difficult targets; Modal for bulk |\n| Many independent folds or sweeps | Modal open weights | user-owned GPUs |\n| Minibinder, binder, or scFv design | Modal or self-hosted open weights | never Biohub managed API until documented |\n| Private, offline, air-gapped, data-resident, customized, fine-tuned, sustained | Hugging Face weights on user-owned compute | user owns capacity and operations |\n\nRun the deterministic router when the route is not already explicit:\n\n```bash\npython3 <plugin-root>/scripts/biohub_esm.py route --task fold --item-count 500\n```\n\nThe 32-item scale-out threshold applies to folding. It is a planning heuristic, not a Biohub account quota. Public ESMC calls stay on the managed API; the plugin ships no ESMC Modal function. Do not hardcode account-specific capacity limits.\n\n## Natural starter experiences\n\nTreat the plugin page's exact prompts as outcome-rich launchers into the official tutorial contracts in `../../examples/tutorial-use-cases.json`:\n\n- `Map the mutational landscape of PETase and show me where it is most constrained or tolerant.`\n- `Show me what ESMC has learned about ATP synthase and map the strongest features onto its structure.`\n- `Model how a modified GLP-1 peptide with a lipid linker might engage GLP-1R, then show me the complex.`\n\nResolve their hidden scientific inputs, select the specialist and model, produce the tutorial-shaped analysis, and present the visual result without making the user translate the request into sequences or SDK objects. The focused GB1 regression launchers in `../../examples/starter-examples.json` remain supported:\n\n- `What might W43F do to GB1?`\n- `Show me what GB1 looks like.`\n- `Find proteins similar to GB1.`\n\nThe three exact plugin-page prompts are curated official-tutorial launchers. Before adopting their pinned target or construct, disclose its exact identity together with the execution route, model, item and call counts, parameters, artifact plan, and available cost information. The PETase prompt authorizes only its disclosed exact 259-request managed runtime once access is configured. The ATP-synthase and GLP-1R prompts do not authorize provider calls; obtain separate explicit current-turn confirmation for their disclosed exact calls. No prompt authorizes a substituted target, a different request scope, or Modal, self-hosted, or bulk-transfer work. An explicit planning-only or no-network request overrides execution. Outside those three exact prompts, resolve a bundled literal only for an explicitly named tutorial example. A generic target request, or a prompt that says “my A3M/MSA,” must use the user's supplied biological input or pause for the missing input; never substitute a tutorial fixture. The 259-context PETase landscape runs on the managed API through the shipped replay-safe command, fanned out through a bounded pool of concurrent managed calls as the quickstart documents.\n\nDo not ask the user to paste the bundled GB1 sequence or recite implementation details already owned by the contract. Resolve these launchers to the pinned RCSB 1PGA chain-A record, then validate the internal literal sequence, digest, and mutation numbering. For other named targets, prefer a user-provided file or stable identifier; otherwise resolve an authoritative sequence source and ask one question only when ambiguity would change the biological input.\n\nFor a managed route, run status-only preflight first; it reads no credential value and costs nothing. If it reports `missing`, load `$biohub-esm-setup` and give the user its key message with the returned `obtain_key_url`, not a plan they cannot run, then resume automatically once the key is configured. Otherwise resolve and validate the input locally, then follow that workflow's authorization boundary and execute only its exact pinned request count without implicit retries. The focused GB1 starters and exact PETase runtime run without separate confirmation; ATP-synthase and GLP-1R require it as stated above. Managed requests may incur cost. Report provider-returned credit or token usage when available; otherwise state that the API did not report usage or cost, and never invent an estimate. Continue automatically through local recovery and result presentation after successful artifact creation. Lead with the result, not with a description of what you are about to do. Small public Atlas API reads need no spend confirmation, but still obey a caller's explicit no-network or planning-only boundary. Before a bulk anonymous-S3 transfer, freeze the exact source prefix, destination, estimated bytes, storage and egress impact, and cost ceiling, then obtain separate explicit current-turn confirmation.\n\n## Hand off\n\nAfter choosing the route, explicitly load exactly the focused specialist(s) needed for the request. These specialists are explicit-only so the router stays the single implicit entry point.\n\n- Representation, logits, entropy, mutation, SAE activation extraction/interpretation, fitted-head, or fine-tuning requests: use `$esmc`.\n- Protein/DNA/RNA/modified-residue/ligand folding: use `$esmfold2`.\n- Similar proteins, MD5 records, clusters, the existing Atlas feature catalog, thumbnails, or Atlas batch data: use `$esm-atlas`.\n- Binder/minibinder/scFv design: use `$esmfold2-binder-design`.\n- Install, authentication, environment, or preflight problems: use `$biohub-esm-setup`.\n\n## Invariants\n\n- Atlas is a public data/discovery API and anonymous dataset, not a model to deploy on Modal or Hugging Face.\n- Biohub managed inference needs `ESM_API_KEY`.\n- Modal public-weight workflows need Modal authentication, not `ESM_API_KEY`.\n- Public Hugging Face weights do not require `HF_TOKEN`; it is optional for authenticated Hub access.\n- Do not ask for credentials in chat or print, persist, screenshot, or commit them. Preflight reports only configured/missing.\n- Preserve machine-readable artifacts and provenance, not UI-only results.\n- Finish successful workflows with the default [result presentation handoff](../../references/structure-viewer-handoff.md): use semantic viewing/display capabilities, open each verified artifact once, and keep pending or unavailable presentation separate from scientific artifact success.\n\nRead [routing details](references/routing.md), [failure handling](references/failures.md), and the shared [safety/provenance contract](../../references/safety-and-provenance.md).\n"
}