Agent skill · software engineering · jeremylongshore
openevidence-debug-bundle
Assemble a reproducible, privacy-safe OpenEvidence support packet for product failures without exposing credentials or patient data. Use when working with OpenEvidence in a healthcare organization. Trigger with "openevidence debug bundle", "OpenEvidence support", or a matching workflow request.
Why this skill is useful
Adds an executable script that collects diagnostic evidence from OpenEvidence API integrations, which the AI cannot generate on its own.
What it needs
Requires curl, jq, tar installed locally. 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 Redacted Support Packet Overview Capture enough browser/app and workflow context for support while excluding PHI, credentials, and speculative API probes. 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 supported public surface is the documented product UI and mobile app, not guessed private endpoints. A useful packet identifies time, surface, feature, steps, expected result, actual result, and redaction method. Clinical disagreement belongs in evidence review; technical malfunction belongs in a support 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 issue as access, browser/device, feature availability, data loss, recording, output, or clinical-content concern. 2. Reproduce with synthetic or fully de-identified content when safe; stop if reproduction could affect care. 3. Record UTC time, app/web version cues, browser/device, feature path, steps, expected behavior, and actual behavior. 4. Capture only redacted screenshots or text; remove names, dates of birth, record numbers, credentials, and hidden metadata. 5. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/openevidence-debug-bundle