Skip to content
FunCoding

Search

Search docs, Skills and MCP

abridge-debug-bundle

Produce a PHI-minimized Abridge support bundle with provenance, redaction, and protected escalation boundaries. Use when support needs reproducible evidence for an Abridge issue. Trigger with "build an Abridge debug bundle".

DevOps 与云2.8kskills/.curated/abridge-debug-bundle/SKILL.md

Install

Send this to Claude Code, Codex or Cursor. The agent checks the Skill for safety first and installs it only after you confirm.

读取 https://funcoding.ai/skills/jeremylongshore/tons-of-skills-marketplace/abridge-debug-bundle/install.md ,按里面的步骤帮我安装这个 Skill。

SKILL.md

Abridge Minimum-Necessary Support Bundle

Overview

Collect configuration presence, component versions, coarse timestamps, correlation references, and observed outcomes without copying recordings, transcripts, generated notes, patient identifiers, tokens, or unrestricted logs.

Prerequisites

  • The authorized Abridge environment, clinical owner, and health-system policy set
  • Current tenant-specific implementation evidence for every private interface in scope
  • Synthetic data or the organization's formally approved test-record procedure

Tool Discipline

Use Read, Glob, and Grep to inspect repository configuration, adapters, tests, policies, and existing evidence. Use WebFetch only for current official Abridge, HHS, or named EHR documentation. Use Write or Edit only after confirming scope, environment, owners, patient-data boundary, and approval state. These tools do not confer access to Abridge, an EHR, or a clinical record; return exact operator steps or an approval-gated handoff for live actions.

Current Contract

  • Abridge describes secure data handling and provides a protected support route, but public support content does not authorize exporting clinical content into ordinary tickets.
  • HIPAA's minimum-necessary principle should shape diagnostic collection and access.
  • A redacted value can still be identifying when combined with exact timestamps, user IDs, or rare workflow details.

Authentication

Use only the health system's provisioned Abridge application access, SSO, administrative role, or tenant-specific partner authentication documented for the approved environment. Do not infer public API credentials, reuse production secrets in tests, or expose tokens and session material. Verify identity owner, least privilege, environment binding, storage, rotation, and revocation before any authenticated action.

Instructions

  1. Define the incident, recipient, protected channel, retention period, and exact evidence questions before collection.
  2. Use Read, Glob, and Grep to locate approved logs and configuration names; do not recursively collect an application directory.
  3. Allowlist fields such as component version, environment label, coarse time bucket, outcome class, and opaque support correlation reference.
  4. Reject audio, transcript, note text, patient or clinician identifiers, URLs with query data, secrets, cookies, and authorization headers.
  5. Use Write or Edit to create the bounded bundle and a manifest; have a second reviewer attest to the redaction.
  6. Use WebFetch only to confirm current official Abridge security and support guidance before transfer.

Approval Boundaries

Do not attach a bundle to email, chat, or a public issue unless the privacy and security owners approve that channel and the bundle passes review.

Output

Return manifest, source classes, allowlisted fields, redaction counts, reviewer, destination, expiry, and excluded evidence classes. Separate verified facts, tenant-specific evidence, assumptions, and actions still awaiting approval.

Error Handling

ConditionResponse
Sensitive value cannot be classifiedExclude it by default.
Recipient requests raw logsMove to the approved protected disclosure process.
Bundle cannot reproduce the symptomDocument the limitation; do not broaden collection silently.

Example

The example is a redacted operational receipt, not patient data or proof of vendor certification.

incident=INC-2041; window=15m-rounded; files=3; rejected-fields=17; phi=none-observed; reviewer=privacy-oncall; expiry=7d

Resources

Read the source map before changing a workflow. Recheck tenant-specific implementation evidence for every interface or capability that public documentation does not define.

Next Steps

Revalidate the evidence date and tenant-specific authority before repeating this workflow in another environment, cohort, care setting, or integration mode.

Similar Skills

shipping-and-launch
addyosmani/agent-skills103k

shipping-and-launch

Prepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.

DevOps & cloud

publish
code-yeongyu/oh-my-openagent70k

publish

Publish oh-my-opencode to npm by triggering the GitHub Actions publish workflow and verifying its artifacts. Ship-only: never runs pre-publish-review or re-reviews merged code unless the user explicitly asks. Argument: <patch|minor|major|explicit-semver>. Triggers: publish, release, deploy, npm publish.

DevOps & cloud

acceptance-orchestrator
sickn33/agentic-awesome-skills47k

acceptance-orchestrator

Use when a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human re-intervention.

DevOps & cloud

event-store-design
wshobson/agents40k

event-store-design

Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.

DevOps & cloud

arize-ai-provider-integration
github/awesome-copilot40k

arize-ai-provider-integration

Creates, reads, updates, and deletes Arize AI integrations that store LLM provider credentials used by evaluators and other Arize features. Supports any LLM provider (e.g. OpenAI, Anthropic, Azure OpenAI, AWS Bedrock, Vertex AI, Gemini, NVIDIA NIM). Use when the user mentions AI integration, LLM provider credentials, create integration, list integrations, update credentials, delete integration, or connecting an LLM provider to Arize.

DevOps & cloud

appinsights-instrumentation
github/awesome-copilot40k

appinsights-instrumentation

Instrument a webapp to send useful telemetry data to Azure App Insights

DevOps & cloud