Agent skill · software engineering · jeremylongshore
openevidence-sdk-patterns
Select supported OpenEvidence interaction and prompting patterns while preventing use of nonexistent public SDKs. Use when working with OpenEvidence in a healthcare organization. Trigger with "openevidence sdk patterns", "OpenEvidence patterns", or a matching workflow request.
Why this skill is useful
Provides specific patterns and error handling for integrating with the OpenEvidence clinical evidence API, which 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 Supported Interaction Patterns Overview Convert an SDK-shaped request into a documented product workflow or a vendor-confirmation question. 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 Current Contract The audited first-party materials do not publish an OpenEvidence SDK or developer API. Similarly named npm and PyPI packages are not an authenticated OpenEvidence integration path. Supported patterns include end-user Ask and documented feature workflows, subject to current guide and account availability. 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. Identify the desired outcome and why the requester thinks code integration is required. 2. Search current first-party documentation for an explicit developer contract, package, authentication method, and terms. 3. If absent, reject package installation, private-endpoint probing, browser automation, and credential extraction. 4. Map the outcome to a supported product pattern: focused Ask, Snow literature investigation, Collections, Dotflows, Visits, or approved manual handoff. 5. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/openevidence-sdk-patterns