htlin222

Breast Cancer Uptodate — AI skill for Claude Code

AI community

Automated oncology treatment trend reporter for breast cancer and hematologic malignancies — scrapes clinical trials, medical trials, medical conferences, and AI-powered evidence via OpenEvidence, ESM.

How to install Breast Cancer Uptodate

This entry records only its repository, not the path inside it, so there is no exact command to give. Open htlin222/breast-cancer-uptodate and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Breast Cancer Uptodate does

Alternatives in AI

Hexstrike AI — HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomousl 8.2k ★
Academic Humanizer — Strip AI-writing tells from papers and grant proposals (NSF/NIH), while keeping scholarly voice and tying clai 1.1k ★
AI Investigator — An automated AI system (Python framework) designed to analyze any type of website content and generate structu 733 ★

README

Oncology Weekly Trend Reporter

自動生成腫瘤科每週治療趨勢報告，以繁體中文撰寫（英文醫學名詞不翻譯）。

目前設定：**乳癌（Breast Cancer）**

資料來源：OpenEvidence AI · OncDaily RSS · OncLive · ESMO · ClinicalTrials.gov

週報範例：[2026-W16](https://github.com/htlin222/breast-cancer-uptodate/wiki/2026-W16)

快速開始

# 安裝 uv（Python 套件管理）
curl -LsSf https://astral.sh/uv/install.sh | sh

# 安裝相依套件
uv sync

# 執行爬蟲 + 報告（OncDaily / OncLive / ESMO）
uv run python main.py scrape

# 生成報告（需手動補充 OpenEvidence 段落，或直接在 Claude Code 中執行）
uv run python main.py report

報告輸出至 `reports/YYYY-Wxx.md`，push 到 `main` 後 GitHub Actions 自動發布至 Wiki。

專案結構

.
├── source/                   ← 所有可調整參數（不需改 Python）
│   ├── keywords.yml          ← 疾病相關關鍵詞（過濾用）
│   ├── drug_groups.yml       ← 藥物分組 + 會議關鍵詞
│   ├── search_queries.yml    ← Twitter 搜尋 query
│   ├── web_sources.yml       ← 爬蟲來源（RSS URL、Google News site）
│   └── twitter.yml           ← GraphQL op_id、cookie skip 清單
├── config/
│   └── seeds.txt             ← KOL Twitter 帳號種子清單
├── src/
│   ├── config.py             ← YAML 載入器（lru_cache）
│   ├── webscraper.py         ← 網路爬蟲（driven by web_sources.yml）
│   ├── fetcher.py            ← Twitter 爬蟲（driven by twitter.yml）
│   ├── reporter.py           ← 推文聚合報告生成
│   ├── discover.py           ← KOL 自動發掘
│   └── db.py                 ← SQLite 儲存
├── reports/                  ← 產出的週報（push 即觸發 wiki 發布）
├── main.py                   ← CLI 入口
└── .github/workflows/
    └── publish-wiki.yml      ← 自動發布 wiki 的 GitHub Action

切換到其他癌症 / 血液腫瘤

本系統設計為**癌症無關（cancer-agnostic）**，所有領域知識都集中在 `source/` 下的 YAML 檔案，切換癌種只需修改這五個檔案，**不需動任何 Python 程式碼**。

步驟 1 — 替換 `source/keywords.yml`

# 以瀰漫性大 B 細胞淋巴瘤（DLBCL）為例
breast_cancer_keywords:       # ← 改這個 key 的值（key 名稱不重要）
  - DLBCL
  - diffuse large B-cell lymphoma
  - rituximab
  - R-CHOP
  - polatuzumab vedotin
  - Polivy
  - CAR-T
  - axicabtagene
  - lisocabtagene
  - loncastuximab
  - tafasitamab
  - Monjuvi
  - bispecific
  - epcoritamab
  - glofitamab
  - BCL2
  - venetocl