菜单
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.
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.
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.
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.
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 | trial-matcher |
| kind | oneshot |
| domain | trial |
| description | 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. |
Query ClinicalTrials.gov v2 (/api/v2/studies) with a tight fields= list for
trials matching the diagnosis and genes. Emit Tier C EvidenceRecords.
Hard rule (spec §9): trial eligibility matching is a known-unsolved problem. Eligibility text needs an LLM parse, and the result is surfaced as "may be eligible — confirm with your care team", NEVER as confirmed eligibility. The code gate must pass every rendered string.
STATUS: live via app/trials.py against the public ClinicalTrials.gov v2 REST
API (no MCP/auth needed). Runs only when BWCLS_LIVE_SOURCES=1; returns [] when
off so the suite stays deterministic. Emits Tier C hedged records; free-text titles
are gate-scanned and dropped if not clean. world-evidence-watch reuses the same
search_trials for its diff.
NOTE: ClinicalTrials.gov's WAF returns 403 to this build environment's datacenter IP, so the live path is verified only by the offline tests (mocked API response) here; it degrades calmly to an empty Tier C (no crash) when the API is unreachable. It should work from a residential IP / the developer's machine. If the WAF blocks there too, switch to the developer's ClinicalTrials.gov MCP connector.
TODO (optional): add an LLM eligibility parse (still surfaced only as "may be eligible — confirm with your care team").
