[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73BAAP11TMKXEEXREEVYZ2K":3,"skill-same:01M73BAAP11TMKXEEXREEVYZ2K":64},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":45,"ownerHtmlUrl":46,"ownerBlogUrl":47,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M73BAAP11TMKXEEXREEVYZ2K","autonomous-oncology-agent",null,"Precision Oncology","bg-szy\u002FTOP-SKILLS","bg-szy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F106576190?v=4","01M73A4E8KPV67SFXRY8XZGNBX","ShuZhiyong","01M73A4E96MQ294MHM74TZBVQD",6,"MIT","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fawesome-skills\u002Fautonomous-oncology-agent\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: autonomous-oncology-agent\ndescription: Precision Oncology\nkeywords:\n  - oncology\n  - multimodal\n  - H&E\n  - biomarkers\n  - NCCN\nmeasurable_outcome: Generate a prioritized treatment plan with evidence levels and predicted biomarker status (MSI\u002FKRAS) within 5 minutes of data ingest.\nlicense: MIT\nmetadata:\n  author: Nature Cancer 2025\n  version: \"1.0.0\"\ncompatibility:\n  - system: Python 3.9+\nallowed-tools:\n  - run_shell_command\n  - web_fetch\n---\n\n\u003C!--\n# COPYRIGHT NOTICE\n# This file is part of the \"Universal Biomedical Skills\" project.\n# Copyright (c) 2026 MD BABU MIA, PhD \u003Cmd.babu.mia@mssm.edu>\n# All Rights Reserved.\n#\n# This code is proprietary and confidential.\n# Unauthorized copying of this file, via any medium is strictly prohibited.\n#\n# Provenance: Authenticated by MD BABU MIA\n\n-->\n\n\n# Autonomous Clinical AI Agent (Oncology)\n\nThis skill implements the capabilities of the \"Autonomous Clinical AI Agent\" described in Nature Cancer (2025). It combines Large Language Models (LLMs) for reasoning with specialized vision models for pathology image analysis to support precision oncology decision-making.\n\n## When to Use This Skill\n\n*   **Precision Oncology**: For interpreting complex cancer cases involving pathology, genomics, and clinical history.\n*   **Biomarker Detection**: To identify status of key biomarkers (MSI, KRAS, BRAF) from pathology slides (H&E).\n*   **Guideline Adherence**: To check treatment plans against NCCN or ASCO guidelines (via OncoKB\u002FPubMed).\n*   **Multimodal Synthesis**: When you need to combine image data and text reports.\n\n## Core Capabilities\n\n1.  **Vision Transformer Analysis**: Detects MSI status and key mutations (KRAS, BRAF) directly from H&E images.\n2.  **Clinical Reasoning**: Synthesizes patient history, pathology, and genomics to recommend therapies.\n3.  **Evidence Retrieval**: Integrates real-time knowledge from OncoKB and PubMed.\n4.  **Decision Support**: Provides ranked treatment options with evidence levels.\n\n## Workflow\n\n1.  **Input Processing**:\n    *   Text: Clinical notes, pathology reports, genomic panels.\n    *   Image: H&E histology slides.\n2.  **Analysis**:\n    *   Vision model predicts molecular features from slides.\n    *   LLM extracts key clinical entities (Stage, Histology, Mutations).\n3.  **Reasoning**:\n    *   Query OncoKB for actionable mutations.\n    *   Match against standard of care guidelines.\n4.  **Output**: Generate a comprehensive \"Tumor Board\" style report.\n\n## Example Usage\n\n**User**: \"Review this case of metastatic colorectal cancer. The H&E slide is attached. What is the predicted MSI status and recommended first-line therapy?\"\n\n**Agent Action**:\n1.  Runs vision model on H&E image -> Output: \"MSI-High (Predicted)\".\n2.  Reads clinical notes -> \"Patient is fit, ECOG 0.\"\n3.  Consults Knowledge Base -> \"MSI-High CRC responds to Pembrolizumab.\"\n4.  Recommends: \"Based on predicted MSI-High status, immunotherapy (Pembrolizumab) is recommended over standard chemotherapy...\"\n\n\n\u003C!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE -->","\u003C!--\n# COPYRIGHT NOTICE\n# This file is part of the \"Universal Biomedical Skills\" project.\n# Copyright (c) 2026 MD BABU MIA, PhD \u003Cmd.babu.mia@mssm.edu>\n# All Rights Reserved.\n#\n# This code is proprietary and confidential.\n# Unauthorized copying of this file, via any medium is strictly prohibited.\n#\n# Provenance: Authenticated by MD BABU MIA\n\n-->\n\n\n# Autonomous Clinical AI Agent (Oncology)\n\nThis skill implements the capabilities of the \"Autonomous Clinical AI Agent\" described in Nature Cancer (2025). It combines Large Language Models (LLMs) for reasoning with specialized vision models for pathology image analysis to support precision oncology decision-making.\n\n## When to Use This Skill\n\n*   **Precision Oncology**: For interpreting complex cancer cases involving pathology, genomics, and clinical history.\n*   **Biomarker Detection**: To identify status of key biomarkers (MSI, KRAS, BRAF) from pathology slides (H&E).\n*   **Guideline Adherence**: To check treatment plans against NCCN or ASCO guidelines (via OncoKB\u002FPubMed).\n*   **Multimodal Synthesis**: When you need to combine image data and text reports.\n\n## Core Capabilities\n\n1.  **Vision Transformer Analysis**: Detects MSI status and key mutations (KRAS, BRAF) directly from H&E images.\n2.  **Clinical Reasoning**: Synthesizes patient history, pathology, and genomics to recommend therapies.\n3.  **Evidence Retrieval**: Integrates real-time knowledge from OncoKB and PubMed.\n4.  **Decision Support**: Provides ranked treatment options with evidence levels.\n\n## Workflow\n\n1.  **Input Processing**:\n    *   Text: Clinical notes, pathology reports, genomic panels.\n    *   Image: H&E histology slides.\n2.  **Analysis**:\n    *   Vision model predicts molecular features from slides.\n    *   LLM extracts key clinical entities (Stage, Histology, Mutations).\n3.  **Reasoning**:\n    *   Query OncoKB for actionable mutations.\n    *   Match against standard of care guidelines.\n4.  **Output**: Generate a comprehensive \"Tumor Board\" style report.\n\n## Example Usage\n\n**User**: \"Review this case of metastatic colorectal cancer. The H&E slide is attached. What is the predicted MSI status and recommended first-line therapy?\"\n\n**Agent Action**:\n1.  Runs vision model on H&E image -> Output: \"MSI-High (Predicted)\".\n2.  Reads clinical notes -> \"Patient is fit, ECOG 0.\"\n3.  Consults Knowledge Base -> \"MSI-High CRC responds to Pembrolizumab.\"\n4.  Recommends: \"Based on predicted MSI-High status, immunotherapy (Pembrolizumab) is recommended over standard chemotherapy...\"\n\n\n\u003C!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE -->",{"name":5,"license":15,"keywords":24,"metadata":30,"description":7,"allowed-tools":33,"compatibility":36,"measurable_outcome":39},[25,26,27,28,29],"oncology","multimodal","H&E","biomarkers","NCCN",{"author":31,"version":32},"Nature Cancer 2025","1.0.0",[34,35],"run_shell_command","web_fetch",[37],{"system":38},"Python 3.9+","Generate a prioritized treatment plan with evidence levels and predicted biomarker status (MSI\u002FKRAS) within 5 minutes of data ingest.","master","63f17866001c5ca854bf2fa0b678ce277133de5b","skills\u002Fawesome-skills\u002Fautonomous-oncology-agent",0,"https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS","https:\u002F\u002Fbg-szy.github.io\u002FTOP-SKILLS\u002F","https:\u002F\u002Fgithub.com\u002Fbg-szy","https:\u002F\u002Fwww.ecust.edu.cn\u002F","a student of East China University of Science and Technology","2026-11-15 03:38:02",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add bg-szy\u002FTOP-SKILLS --skill autonomous-oncology-agent",{"tool":56,"command":57},"bunx","bunx skills add bg-szy\u002FTOP-SKILLS --skill autonomous-oncology-agent",{"tool":59,"command":60},"pnpm","pnpm dlx skills add bg-szy\u002FTOP-SKILLS --skill autonomous-oncology-agent","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fawesome-skills\u002Fautonomous-oncology-agent\u002FSKILL.md",true,[],[65,73,81,88,96,104],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":72},"01M76KYA4EKM5BWW1HCAH84Z78","zipcode-search","Look up a Korean postcode and official English address from a known address with the official ePost integrated search page.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fzipcode-search\u002FSKILL.md",[],[],"2026-11-12 13:55:43",{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":77,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":72},"01M76KX458K8BXKWWPKHQSX891","yomiyasu","AIが生成した日本語を推敲するスキル。利用者が yomiyasu の名前を出して頼んだとき（「\u002Fyomiyasu」、「$yomiyasu:yomiyasu」、「yomiyasu で推敲して」など）と、スキルを使った日本語の推敲をはっきり頼んだときだけ使う。CLAUDE.md、AGENTS.md、カスタム指示などで yomiyasu を使うよう求められているときも、名前を出して頼まれたものとして扱う。名前を出さずに日本語の文章を書かせる依頼や、コード、設定、ドキュメントの更新では使わない。意味と条件を保ち、不自然な比喩、曖昧な主述関係、不要な装飾やコピー調を整える。","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fyomiyasu\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fyomiyasu\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":72},"01M76KVC1BYEQGRREW8PWBQ4Z0","x402-api-paywall","Add stablecoin micropayment paywalls to FastAPI and Express routes using the HTTP 402 standard. Use when: Monetize specific high-cost API endpoints for AI agent consumption; Enforce per-request billing without managing complex user accounts; Integrate standard HTTP 402 handshakes into existing Node or Python backends.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fx402-api-paywall\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":92,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":72},"01M76KTAM7XE6683XDWXP15M39","write-natural","Create, revise, humanize, translate, and audit natural, evidence-led Persian and English writing. Use for anti-slop editing, detector-aware revision, academic\u002Fscientific papers and theses, web\u002FSEO articles, product descriptions, landing pages, copywriting, sales, email, reports, essays, and creative prose. Preserve facts, qualifications, author voice, and purpose while removing generic AI phrasing. Trigger on natural writing, humanize, AI tells, anti-slop, AI detector flags, نگارش، نویسندگی، ضد اسلپ، انسانی‌سازی، متن فارسی، مقاله، پایان‌نامه، سئو، کپی‌رایتینگ، و ضد تشخیص. Detector-aware means informed editing and honest evaluation, never guaranteed undetectability.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fwrite-natural\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fwrite-natural\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":100,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":72},"01M76KT27RP09F7YK7B19B90ZA","write-gbp-post","Write and publish Google Business Profile posts (GMB posts, Google My Business updates, offers and events) with the Reach MCP server. Turns a short brief into post text, shows the exact post with its type, button, image, time and timezone, and publishes or schedules it only after the owner says yes. Use when someone asks to write a Google post, announce an offer or event on their Google listing, or schedule a GBP post.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fwrite-gbp-post\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fwrite-gbp-post\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":72},"01M76KSXQHA01V041SNBVK95GE","write-agents-md","Draft a short, accurate AGENTS.md (and a CLAUDE.md bridge) for a repository from evidence in the repo. Use when a project has no agent instructions, or when asked to create or rewrite AGENTS.md.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fwrite-agents-md\u002FSKILL.md",[],[]]