email-batch-test
Use when Invoice-Downloader work involves mailbox batch tests, truth audit, regression validation, P0/P1/P2 decisions, packaged frontend acceptance, or clean reruns.
- License 许可
- MIT
- 最近更新
- 2026-11-07
- Stars
- ★ 11
- Forks
- 5
01 前言 Front Matter
- name
- email-batch-test
- description
- Use when Invoice-Downloader work involves mailbox batch tests, truth audit, regression validation, P0/P1/P2 decisions, packaged frontend acceptance, or clean reruns.
02 资源文件 2
- 参考文档references/regression-gate.md1.2 KB
- 参考文档references/test-standards.md974 B
03 SKILL.md 正文
Email Batch Test
Current Authority
Read AGENTS.md, then read both files under references/.
The canonical QQ full-range truth manifest is:
test_dataset/qq_20251125_20260614_rebuilt_20260614_1035/truth_manifest.json
Its required contract is:
included_count = 215pending_review_count = 0finalized = true- date range
2025-11-25through2026-06-14
Do not substitute an older manifest or describe a non-final truth set as authoritative.
Required Gate
- Build the Windows package from the exact candidate revision.
- Create a fresh child of
manual_frontend_runsand clear only its output-scoped state. - Preserve
%APPDATA%\InvoiceFlowAI\user_settings.jsonand its encrypted credentials. - Launch the packaged EXE visibly through
scripts/frontend_truth_acceptance.py. - Require finalized run evidence and a fresh
batch_validation.pyaudit. - Accept only an explicit result with P0, P1, P2, and manual counts all zero.
No result may be reported as probable, suspected, or unconfirmed. Missing authority is a failed gate.
Secondary Mailboxes
Run another mailbox only when its local manifest is present, finalized, has zero pending review, and the task explicitly requires that scope. Never depend on a stale or missing worktree path.
04 同仓库更多 Skills
xhs-pharma-social-listening
Run evidence-disciplined Xiaohongshu social listening for foreign pharma employee pain points. Use when the user asks to collect and analyze notes/comments about pharma companies, aliases, roles, compliance, medical affairs, or AI topics, then produce a cited and scored sampled-insight report. Includes independent-evidence counting, MediaCrawler batch collection, and CAPTCHA/461 fallback to Agent Reach/OpenCLI.
healthcare-phi-compliance
Protected Health Information (PHI) and Personally Identifiable Information (PII) compliance patterns for healthcare applications. Covers data classification, access control, audit trails, encryption, and common leak vectors. Use when code touches PHI or PII in a healthcare system, or when auditing access control, audit trails, or leak vectors.
healthcare-eval-harness
Patient safety evaluation harness for healthcare application deployments. Automated test suites for CDSS accuracy, PHI exposure, clinical workflow integrity, and integration compliance. Blocks deployments on safety failures. Use when a healthcare deployment must be gated on patient-safety tests for CDSS accuracy, PHI exposure, and workflow integrity.
healthcare-emr-patterns
EMR/EHR development patterns for healthcare applications. Clinical safety, encounter workflows, prescription generation, clinical decision support integration, and accessibility-first UI for medical data entry. Use when building EMR or EHR features such as encounter workflows, prescription generation, or clinical data entry UI.
healthcare-cdss-patterns
Clinical Decision Support System (CDSS) development patterns. Drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), alert severity classification, and integration into EMR workflows. Use when building clinical decision support — drug interaction checks, dose validation, clinical scoring, or alert severity.
dxy-task-clarify
用户的请求含糊、缺背景、缺资料说明、缺读者或用途时使用。先用少量带选项的追问把任务问清楚，写成任务卡，用户确认后再执行。尤其适用于医生、科研人员和药企各岗位的工作，例如「帮我分析一下这些数据」「帮我准备明天的拜访」「写个总结」「做个 PPT」「回一下这封邮件」「整理一下会议纪要」「整理一下这些文献」「帮我准备下周的讲课」「写个病例汇报」「帮我写个提示词」。用户说「先问我」「帮我理清需求」「我不知道怎么描述」「我不会问 AI」时也使用。用途、资料、读者都已说清的请求，纯翻译，以及写代码、改代码，不使用。