openevidence-deploy-integration — Claude Code skill: rollout plan
openevidence-deploy-integration plans an OpenEvidence rollout for a clinical workflow, covering the pilot, staff training, governance checks, and rollback conditions.
MIT 1 installs ★ 2,935 updated 2026-10-29
npx skills add jeremylongshore/tons-of-skills-marketplace --skill openevidence-deploy-integration -a claude-codeWhat openevidence-deploy-integration does
The skill lays out a staged rollout: choose a bounded workflow, verify access and data terms, prepare training, run a pilot, then review results before expanding. It can help record the launch decision, accountable owners, open risks, and the next action.
A plan needs a defined clinical owner, organizational policies, and current OpenEvidence documentation. Pilot scenarios should use synthetic data or data authorized for that purpose and limited to what is needed. Product access and feature availability require confirmation. The skill does not authorize a production pilot, handling PHI, or clinical decisions; a qualified professional remains responsible for care decisions.
What it helps with
- draft a bounded OpenEvidence rollout plan
- set pilot scope and success criteria
- prepare training on citation checks and failure escalation
- record rollout owners, risks, and rollback triggers
Example prompts for the agent
- Plan a pilot for OpenEvidence in this clinical workflow.
- Review this OpenEvidence rollout plan against our policies and current product documentation.
- List the owners, review criteria, and rollback triggers for an OpenEvidence pilot.
How to install openevidence-deploy-integration
1Skills CLI (Vercel)
npx skills add jeremylongshore/tons-of-skills-marketplace --skill openevidence-deploy-integration -a claude-code2Manually: put the files in place
~/.claude/skills/openevidence-deploy-integration/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/openevidence-deploy-integration/
1Skills CLI (Vercel)
npx skills add jeremylongshore/tons-of-skills-marketplace --skill openevidence-deploy-integration -a codex2Manually: put the files in place
.agents/skills/openevidence-deploy-integration/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add jeremylongshore/tons-of-skills-marketplace --skill openevidence-deploy-integration -a cursor2Manually: put the files in place
.cursor/skills/openevidence-deploy-integration/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install jeremylongshore/tons-of-skills-marketplace skills/.curated/openevidence-deploy-integration2Manually: put the files in place
.github/skills/openevidence-deploy-integration/SKILL.md1Skills CLI (Vercel)
npx skills add jeremylongshore/tons-of-skills-marketplace --skill openevidence-deploy-integration -a gemini-cli2Platform CLI
gemini skills install https://github.com/jeremylongshore/tons-of-skills-marketplace --path skills/.curated/openevidence-deploy-integrationManually: put the files in place
.devin/skills/openevidence-deploy-integration/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add jeremylongshore/tons-of-skills-marketplace --skill openevidence-deploy-integration -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about openevidence-deploy-integration
How do I install openevidence-deploy-integration in Claude Code?
Run npx skills add jeremylongshore/tons-of-skills-marketplace --skill openevidence-deploy-integration -a claude-code. The skill file is placed at ~/.claude/skills/openevidence-deploy-integration/SKILL.md.
What does openevidence-deploy-integration do?
It helps plan an OpenEvidence rollout in a clinical workflow, from setting scope and training staff to reviewing a pilot and recording launch or rollback decisions.
What do I need before planning the rollout?
Define a bounded workflow and accountable clinical owner, and gather organizational policies plus current OpenEvidence documentation. Pilot scenarios should use synthetic data or properly authorized data limited to what is needed.
Source text
SKILL.md · MIT
--- name: openevidence-deploy-integration description: >- Plan a controlled OpenEvidence rollout across clinical workflows, training, governance, and rollback boundaries. Use when working with OpenEvidence in a healthcare organization. Trigger with "openevidence deploy integration", "OpenEvidence deployment", or a matching workflow request. argument-hint: "[practice-plan-path] [workflow]" allowed-tools: Read, Glob, Grep, WebFetch, Write, Edit version: 1.14.0 author: Jeremy Longshore <[email protected]> license: MIT tags: - saas - openevidence - deployment - change-management model: inherit effort: high compatibility: Designed for Claude Code; requires authorized OpenEvidence access and qualified clinical review for patient-care use --- # OpenEvidence Practice Rollout Plan ## Overview Treat rollout as clinical workflow change, not software API deployment. 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 is delivered through documented end-user product surfaces. - Institution-specific availability, integrations, commitments, and data terms require written confirmation. - A rollout needs clinical, privacy, security, operational, and training ownership. ## 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. Select one bounded workflow and define users, patients affected, systems touched, success criteria, and explicit exclusions. 2. Confirm account eligibility, feature availability, agreement terms, data handling, consent, and support path. 3. Design training for prompting, EvidenceGrade, citation verification, professional judgment, and failure escalation. 4. Pilot with synthetic scenarios, then a small authorized cohort under heightened review. 5. Review quality, safety signals, adoption, workflow burden, and unresolved controls before expansion. 6. Record launch/no-launch, rollback trigger, owners, training evidence, and next review date. ## Approval Boundaries Do not create or share accounts; change access, roles, agreements, consent, retention, or security settings; enter PHI; record a conversation; copy content into another system; contact a patient; make a diagnosis or treatment decision; submit billing; transmit a support packet; run a production pilot; or represent vendor capabilities without explicit approval from the accountable owner. A qualified professional remains responsible for clinical decisions. ## Output Return scope, current first-party evidence and date, data classification, workflow or findings, citations reviewed, assumptions rejected, clinical and governance owners, approval state, unresolved risk, and the exact next action. Redact patient and credential data. ## Error Handling | Condition | Response | |---|---| | Feature not documented | Exclude it until OpenEvidence or the contract owner confirms support. | | Governance owner missing | Do not launch the workflow. | | Pilot creates unsafe reliance | Pause, retrain, and reassess before resuming. | ## Examples This compact example shows the minimum reviewable handoff; adapt fields to the approved workflow without adding sensitive data. Input: ```text workflow=Ask for guideline summaries; cohort=5 clinicians; phase=pilot ``` Expected handoff: ```text decision=conditional-go; controls=verified; rollback=defined; review=14d ``` ## Resources - [OpenEvidence official evidence register](references/official-docs.md) - [OpenEvidence User Guide](https://www.openevidence.com/user-guide) - [OpenEvidence Terms of Use](https://www.openevidence.com/policies/terms)
© Jeremy Longshore · MIT · jeremylongshore/tons-of-skills-marketplace