Agent skill · data analytics · jeremylongshore
openevidence-observability
Monitor OpenEvidence workflow quality, evidence traceability, adoption, and safety signals using approved local evidence. Use when working with OpenEvidence in a healthcare organization. Trigger with "openevidence observability", "OpenEvidence quality", or a matching workflow request.
Why this skill is useful
Provides specific metrics and alerting rules for monitoring clinical query performance that the AI wouldn't reliably generate on its own.
What it needs
About 2k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
OpenEvidence Quality and Adoption Audit Overview Create a human-centered review loop without claiming access to private product telemetry. Keep inputs minimal, separate observed facts from assumptions, and leave consequential decisions with the named accountable owner. Prerequisites A clearly bounded workflow, accountable clinical owner, and organizational policy Current first-party OpenEvidence documentation and applicable institution agreements Synthetic or properly authorized minimum-necessary data Tool Discipline Use Read, Glob, and Grep to inspect supplied policies, plans, and evidence. Use WebFetch only for current first-party OpenEvidence documentation. Use Write or Edit only when the user requests a named deliverable with an approved destination. Never expose credentials, PHI, recordings, or unrestricted environment output. Current Contract No public observability API or standard metrics export is documented. Measurements must come from authorized account/institution records and redacted quality samples. Volume and speed are insufficient without citation, applicability, and safety review. Authentication Use only the official OpenEvidence web/mobile sign-in or an institution-approved access path. Do not invent API keys, OAuth clients, SDK credentials, service accounts, or private endpoints. Never ask a user to reveal a password, session token, cookie, or recovery code. Instructions 1. Define the monitored workflow, cohort, period, data authority, clinical owner, and escalation thresholds. 2. Select measures for completion, citation traceability, unsupported claims, reviewer overrides, time burden, incidents, and training gaps. 3. Sample the minimum authorized records and de-identify evidence used outside the care record. 4. Have qualified reviewers score outputs with a stable rubric and record inter-reviewer disagreement. 5. Trend results without inferring patient outcomes or vendor-wide performance from a local sample. 6. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/openevidence-observability