Agent skill · data analytics · jeremylongshore
openevidence-common-errors
Diagnose weak, incomplete, or poorly grounded OpenEvidence results using prompt, model, citation, and workflow checks. Use when working with OpenEvidence in a healthcare organization. Trigger with "openevidence common errors", "OpenEvidence troubleshooting", or a matching workflow request.
Why this skill is useful
Provides specific error handling patterns and solutions for OpenEvidence API that the AI wouldn't reliably generate on its own.
What it needs
Requires openevidence account access. About 2k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
OpenEvidence Answer-Quality Troubleshooting Overview Separate access trouble, prompt ambiguity, evidence limitations, and unsafe interpretation before anyone acts on an answer. 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 OpenEvidence answers cite sources and may expose EvidenceGrade; neither removes the need for professional review. Model and feature behavior can change, so the live guide and visible product state outrank cached instructions. Do not paste identifiable patient data into a diagnostic packet. 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. Classify the symptom as access, missing context, irrelevant evidence, conflicting evidence, citation mismatch, or product failure. 2. Reduce the question to the clinical decision, population, intervention, comparator, outcome, and time horizon that matter. 3. Compare an ordinary Ask response with an appropriate model or Snow only when the current guide supports that choice. 4. Open the cited sources and verify population, date, endpoint, recommendation strength, and applicability. 5. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/openevidence-common-errors--a9de5c