菜单
Uncertainty-ranked gap report (spec §8b). Names a pharmacogenomic module the analysis could NOT complete and attributes the gap to a specific missing input (a genotype). Never tells the patient to get a test — it is a report on the tool's blind spots for the care team.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Open Targets gene-disease association lookup via the official MCP connector. One GraphQL round trip per gene. Emits Tier C informational evidence.
Standing watcher. Reruns the trial, literature (PubMed + bioRxiv), and ClinVar-relookup specialists against the FIXED profile and diffs against the stored baseline. Empty diff -> one calm "no significant changes" timeline entry.
PubMed + bioRxiv search for recent literature on the patient's genes and diagnosis. bioRxiv preprints are first-class (earliest signal). Emits Tier C; the LLM only summarizes genuine free text, it never asserts facts.
ClinicalTrials.gov v2 search for trials relevant to the patient's diagnosis and genes. Eligibility is surfaced as "may be eligible — confirm with your care team", never confirmed. Emits Tier C.
Uncertainty-ranked gap report (spec §8b). For an unresolved (Tier B) variant, names that the analysis can't resolve it and attributes the gap to a missing input — a documented family history — that would let the analysis weight it. Never a test order.
Deterministic CPIC pharmacogenomics lookup over the patient's current medications. Pure code, no LLM. Emits Tier A/B for CPIC Level A/B gene-drug pairs; flags a missing genotype instead of ever directing a dose change.
| name | next-data-pgx-coverage |
| kind | standing |
| domain | next_data |
| description | Uncertainty-ranked gap report (spec §8b). Names a pharmacogenomic module the analysis could NOT complete and attributes the gap to a specific missing input (a genotype). Never tells the patient to get a test — it is a report on the tool's blind spots for the care team. |
A standing next-data specialist (spec §8b). It does NOT order tests. It reports what the analysis currently cannot do and why, attributing the gap to a missing input, and states how much closing the gap would help.
For each CPIC pair on a current medication with no genotype on file, it emits a
next_data EvidenceRecord in the required frame:
"The analysis currently can't determine the specific pharmacogenomic guidance for {drug}; the input that would most change this is a {gene} genotype. Adding it would move this pair from unresolved to classifiable."
Enforced invariant (same code gate as §7): every claim names an analysis
limitation and attributes it to a missing input, and states how much closing it
helps. Banned: "you should get / you need / we recommend testing." This is
deterministic — derived from cpic.coverage_gaps, no LLM.
Entrypoint: specialist.run_specialist(profile, ctx).
