Update to Maven Bio

{
  "description": "Validate the genetic basis of a drug target: gene-disease association strength, gene constraint, tractability, and known drugs, from public biomedical databases. Use when a thesis turns on whether a target is genetically validated.",
  "included_files": [
    {
      "relative_path": "LICENSE",
      "size_in_bytes": 802
    },
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 333
    }
  ],
  "name": "validate-target",
  "skill_md_contents": "---\nname: validate-target\ndescription: \"Validate the genetic basis of a drug target: gene-disease association strength, gene constraint, tractability, and known drugs, from public biomedical databases. Use when a thesis turns on whether a target is genetically validated.\"\n---\n\n# Validate Target\n\n## Using this skill\n\nUse the connected Maven Bio MCP server at `https://mcp.mavenbio.com/`. Follow the user's explicit scope, depth, and output preferences; the workflow and output structure below are defaults. Report coverage limits instead of silently narrowing an explicitly requested set.\n\nHyphenated primitive names refer to other skills in this Maven Bio bundle. Consult the relevant skill when composing its workflow. Use the available MCP tool schemas for arguments; pass document identifiers to `read_document` through `ids`, and include a claim-specific `query` when using `format=\"citations\"`.\n\nThis primitive answers \"is this target genetically validated, and how strongly\" with evidence from public databases (Open Targets, gnomAD, GWAS Catalog).\n\n## Use When\n\n- the thesis or landscape turns on a target's genetic validation\n- a workflow needs gene-disease association strength before ranking programs\n- you need target tractability / druggability or gene constraint (LOEUF)\n- you need the drugs in development against a target, or repurposing hypotheses (speculative)\n\n## Core Tools\n\n- `match_entity` - confirm the gene / disease / target is the one you mean, and pick up its canonical name and synonyms. Use the resolved *name*, not the returned `tgt_` id, when calling `research_bio_evidence`.\n- `research_bio_evidence(name, entity_type, aspects)` - the bio evidence tool. Select `aspects`:\n  - `tractability` - target druggability\n  - `constraint` - gene constraint (gnomAD LOEUF)\n  - `associations` - gene<->disease association (genetic + L2G + overall score); pass `context=<disease>` to scope a target to one disease\n  - `known_drugs` - drugs and clinical candidates in development against the target\n  - `repurposing` - repurposing candidates (opt-in; always speculative)\n- `research_entity`, `search_documents`, `read_document` - strengthen or cross-check bio findings against the Maven corpus\n\n## Output Contract\n\nReturn a structured target-validation object that can include:\n\n- resolved target (gene symbol) and disease (EFO/MONDO id)\n- association strength with `evidence_rating` (Direct for curated DB associations, Indirect for inferred/aggregated scores)\n- gene constraint and tractability with `evidence_rating`\n- drugs in development against the target\n- repurposing hypotheses, each explicitly marked speculative\n- explicit gaps (unresolved ids, fuzzy disease-ontology matches, no association found)\n\nEach claim carries: `claim`, `evidence_rating`, `citations` ([{source_id, quote}]), optional `notes`. Evidence is structured metadata attached to claims, not inline prose markup.\n\n## Quality Bar\n\n- a fuzzy disease-ontology match downgrades the evidence_rating one level and is flagged\n- repurposing output is always labeled speculative; never Direct Evidence\n- a curated database association (with a source record) is Direct; an inferred score is Indirect\n- do not treat an entity-resolution result as a citation\n- pass `research_bio_evidence` a raw gene symbol or disease name (`PCSK9`, `NASH`), never a Maven `tgt_`/`ind_` id. It resolves against external databases, which do not know Maven ids, and an id silently returns `resolved: false` with no error rather than failing loudly. For a target-disease pair, put the disease in `context`\n- check `resolution.resolved` on every `research_bio_evidence` response before reading the payload. When it is false, retry once with an official gene symbol or a documented synonym from `match_entity` before concluding anything\n- report an unvalidated target only when a resolved lookup came back with no association. `resolved: false` means the name did not match, not that the target lacks evidence; the two must never be reported the same way\n"
}