[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79FD87X8BF5ZP5JTH6ZAT77":3,"skill-same:01M79FD87X8BF5ZP5JTH6ZAT77":51},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":32,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M79FD87X8BF5ZP5JTH6ZAT77","dicom-medical-imaging",null,"Production DICOM medical imaging standards, DICOMweb RESTful services (WADO-RS, STOW-RS, QIDO-RS), PACS integration, anonymization\u002Fde-identification, and Cornerstone.js web rendering.","hamzabellouch\u002Fagent-skills","hamzabellouch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F237856042?v=4","01M79BRYW7XAMK3YDWQEMTWGWS","Hamza Bellouch","01M79BRYWXQV3JK2TGVTX8GN2A",8,"MIT","https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FScience\u002FBioTech_and_Health_Sciences\u002Fdicom-medical-imaging\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: dicom-medical-imaging\nmetadata:\n  category: Digital Health and BioTech (FHIR and HL7)\ndescription: Production DICOM medical imaging standards, DICOMweb RESTful services (WADO-RS, STOW-RS, QIDO-RS), PACS integration, anonymization\u002Fde-identification, and Cornerstone.js web rendering.\ncompatibility: DICOM PS3.0+, DICOMweb REST API, Orthanc \u002F dcm4chee PACS, Cornerstone.js \u002F pydicom\n---\n\n# DICOM Medical Imaging & PACS Architecture\n\n## Overview\nThis skill provides technical standards for handling, parsing, transmitting, and displaying medical imaging datasets via **DICOM (Digital Imaging and Communications in Medicine)** and **DICOMweb RESTful Services**. It covers PACS server integration, DICOM anonymization for HIPAA compliance, and web rendering with Cornerstone.js.\n\n---\n\n## 1. Medical Imaging Architecture Principles\n\n1. **DICOM Hierarchy Compliance**: Respect the core 4-level DICOM object model: `Patient -> Study -> Series -> Instance (Image)`.\n2. **Prefer DICOMweb over C-STORE\u002FC-FIND**: Use DICOMweb RESTful standards (`QIDO-RS` for query, `WADO-RS` for retrieve, `STOW-RS` for store) for modern web and cloud integrations rather than legacy DIMSE network protocols over raw sockets.\n3. **Mandatory PHI De-Identification**: Anonymize Protected Health Information (PHI) tags before transmitting images outside secure clinical perimeters. Strip tags like `PatientName (0010,0010)`, `PatientID (0010,0020)`, `PatientBirthDate (0010,0030)`, and burn-in annotations.\n4. **Lossless Compression Standards**: Maintain lossless compression (JPEG 2000 Lossless, High-Throughput JPEG 2000) for diagnostic primary readings; allow lossy compression only for fast web preview thumbnails.\n5. **Zero-Footprint Web Viewers**: Utilize WebGL \u002F WebGPU viewports (e.g., Cornerstone3D) for cross-platform rendering of 16-bit CT\u002FMRI arrays directly in web browsers.\n\n---\n\n## 2. PACS & DICOMweb Pipeline\n\n```\n[ Modality (CT \u002F MRI Scanner) ]\n       │  Legacy DIMSE (C-STORE)\n       ▼\n[ PACS Server (Orthanc \u002F dcm4chee) ] ──(STOW-RS \u002F DICOMweb)\n       │\n       ├── QIDO-RS (JSON Metadata Search) ──▶ [ Web PACS Client \u002F AI Inference ]\n       ├── WADO-RS (Retrieve Instance Frames)\n       └── DICOM De-identifier Service ────▶ [ Anonymized Research Dataset ]\n```\n\n| DICOMweb Service | Protocol \u002F Action | Equivalent DIMSE | Primary Use Case |\n| :--- | :--- | :--- | :--- |\n| **QIDO-RS** | `GET \u002Fstudies?PatientID=123` | `C-FIND` | Query studies, series, and instances |\n| **WADO-RS** | `GET \u002Fstudies\u002F{uid}\u002Fseries\u002F{uid}\u002Finstances\u002F{uid}` | `C-MOVE` \u002F `C-GET` | Retrieve pixel data \u002F frame arrays |\n| **STOW-RS** | `POST \u002Fstudies` | `C-STORE` | Store DICOM instances to PACS |\n| **WADO-URI** | `GET \u002Fobject?requestType=WADO` | N\u002FA | Simple JPEG\u002FPNG rendering request |\n\n---\n\n## 3. Anti-Patterns & Common Errors\n\n* **Anti-Pattern: Naive String Manipulation of Raw DICOM Byte Stream**\n  * *Risk*: Data corruption caused by incorrect handling of VR (Value Representation) byte alignment and endianness.\n  * *Remediation*: Use validated DICOM parsers (`pydicom`, `dcmjs`, `dicom-parser`).\n* **Anti-Pattern: Omitting Pixel Spacing Scaling in UI**\n  * *Risk*: Inaccurate physical distance measurements (millimeters) on diagnostic monitors, risking misdiagnosis.\n  * *Remediation*: Parse tag `PixelSpacing (0028,0030)` and apply calibration multipliers in viewer viewports.\n* **Anti-Pattern: Failing to Strip Burned-in Text Annotations**\n  * *Risk*: HIPAA PHI violation when patient details are rendered inside pixel arrays instead of standard metadata headers.\n  * *Remediation*: Inspect tag `BurnedInAnnotation (0028,0301)` and execute automated OCR\u002Fpixel redaction.\n\n---\n\n## 4. Production Python & JS DICOM Snippets\n\n### A. Python DICOM De-Identification Script (`dicom_anonymizer.py`)\n\n```python\n#!\u002Fusr\u002Fbin\u002Fenv python3\n\"\"\"\nHIPAA-Compliant DICOM Anonymization & PACS De-identification Script\n\"\"\"\n\nimport pydicom\nfrom pydicom.dataset import Dataset\n\n# Mandatory DICOM Tags to wipe or randomize for Safe De-identification\nTAGS_TO_REMOVE = [\n    (0x0010, 0x0010),  # Patient's Name\n    (0x0010, 0x0030),  # Patient's Birth Date\n    (0x0010, 0x0040),  # Patient's Sex\n    (0x0010, 0x1000),  # Other Patient IDs\n    (0x0008, 0x0080),  # Institution Name\n    (0x0008, 0x0090),  # Referring Physician's Name\n]\n\ndef anonymize_dicom_file(input_path: str, output_path: str, anon_patient_id: str):\n    \"\"\"\n    Reads a DICOM file, scrubs PHI headers, updates UIDs, and saves anonymized output.\n    \"\"\"\n    ds = pydicom.dcmread(input_path)\n\n    # 1. Scrub Specific PHI Tags\n    for tag in TAGS_TO_REMOVE:\n        if tag in ds:\n            del ds[tag]\n\n    # 2. Assign Pseudonym Patient ID\n    ds.PatientID = anon_patient_id\n    ds.PatientName = f\"ANON^{anon_patient_id}\"\n\n    # 3. Mark Burned-in Annotation tag as NO\n    ds.BurnedInAnnotation = \"NO\"\n\n    # 4. Save clean file\n    ds.save_as(output_path)\n    print(f\"[ANONYMIZED] {input_path} -> {output_path} (ID: {anon_patient_id})\")\n\nif __name__ == \"__main__\":\n    anonymize_dicom_file(\"sample_ct.dcm\", \"clean_ct.dcm\", \"SUBJ-99482\")\n```\n\n---\n\n### B. JavaScript DICOMweb Client with WADO-RS & Cornerstone3D (`dicom_viewer.js`)\n\n```javascript\nimport { api } from 'dicomweb-client';\n\nconst url = 'https:\u002F\u002Fpacs.hospital.org\u002Fdicomweb';\nconst client = new api.DICOMwebClient({ url });\n\n\u002F**\n * Fetch Study Metadata via QIDO-RS\n *\u002F\nexport async function searchPatientStudies(patientId) {\n  const options = {\n    queryParams: {\n      PatientID: patientId,\n      Limit: 10\n    }\n  };\n\n  const studies = await client.searchForStudies(options);\n  console.log(`Found ${studies.length} studies for Patient: ${patientId}`);\n  \n  return studies.map(study => ({\n    studyInstanceUid: study['0020000D'].Value[0],\n    patientName: study['00100010'] ? study['00100010'].Value[0].Alphabetical : 'N\u002FA',\n    studyDate: study['00080020'] ? study['00080020'].Value[0] : 'Unknown'\n  }));\n}\n\n\u002F**\n * Fetch WADO-RS Frames for Web Image Rendering\n *\u002F\nexport async function fetchInstanceFrames(studyUid, seriesUid, instanceUid) {\n  const options = {\n    studyInstanceUID: studyUid,\n    seriesInstanceUID: seriesUid,\n    sopInstanceUID: instanceUid,\n    mediaTypes: [{ mediaType: 'multipart\u002Frelated', type: 'application\u002Foctet-stream' }]\n  };\n\n  const frameArrayBuffers = await client.retrieveInstanceFrames(options);\n  console.log(`Fetched ${frameArrayBuffers.length} frame buffers.`);\n  return frameArrayBuffers[0]; \u002F\u002F Raw 16-bit ArrayBuffer for WebGL canvas\n}\n```\n","# DICOM Medical Imaging & PACS Architecture\n\n## Overview\nThis skill provides technical standards for handling, parsing, transmitting, and displaying medical imaging datasets via **DICOM (Digital Imaging and Communications in Medicine)** and **DICOMweb RESTful Services**. It covers PACS server integration, DICOM anonymization for HIPAA compliance, and web rendering with Cornerstone.js.\n\n---\n\n## 1. Medical Imaging Architecture Principles\n\n1. **DICOM Hierarchy Compliance**: Respect the core 4-level DICOM object model: `Patient -> Study -> Series -> Instance (Image)`.\n2. **Prefer DICOMweb over C-STORE\u002FC-FIND**: Use DICOMweb RESTful standards (`QIDO-RS` for query, `WADO-RS` for retrieve, `STOW-RS` for store) for modern web and cloud integrations rather than legacy DIMSE network protocols over raw sockets.\n3. **Mandatory PHI De-Identification**: Anonymize Protected Health Information (PHI) tags before transmitting images outside secure clinical perimeters. Strip tags like `PatientName (0010,0010)`, `PatientID (0010,0020)`, `PatientBirthDate (0010,0030)`, and burn-in annotations.\n4. **Lossless Compression Standards**: Maintain lossless compression (JPEG 2000 Lossless, High-Throughput JPEG 2000) for diagnostic primary readings; allow lossy compression only for fast web preview thumbnails.\n5. **Zero-Footprint Web Viewers**: Utilize WebGL \u002F WebGPU viewports (e.g., Cornerstone3D) for cross-platform rendering of 16-bit CT\u002FMRI arrays directly in web browsers.\n\n---\n\n## 2. PACS & DICOMweb Pipeline\n\n```\n[ Modality (CT \u002F MRI Scanner) ]\n       │  Legacy DIMSE (C-STORE)\n       ▼\n[ PACS Server (Orthanc \u002F dcm4chee) ] ──(STOW-RS \u002F DICOMweb)\n       │\n       ├── QIDO-RS (JSON Metadata Search) ──▶ [ Web PACS Client \u002F AI Inference ]\n       ├── WADO-RS (Retrieve Instance Frames)\n       └── DICOM De-identifier Service ────▶ [ Anonymized Research Dataset ]\n```\n\n| DICOMweb Service | Protocol \u002F Action | Equivalent DIMSE | Primary Use Case |\n| :--- | :--- | :--- | :--- |\n| **QIDO-RS** | `GET \u002Fstudies?PatientID=123` | `C-FIND` | Query studies, series, and instances |\n| **WADO-RS** | `GET \u002Fstudies\u002F{uid}\u002Fseries\u002F{uid}\u002Finstances\u002F{uid}` | `C-MOVE` \u002F `C-GET` | Retrieve pixel data \u002F frame arrays |\n| **STOW-RS** | `POST \u002Fstudies` | `C-STORE` | Store DICOM instances to PACS |\n| **WADO-URI** | `GET \u002Fobject?requestType=WADO` | N\u002FA | Simple JPEG\u002FPNG rendering request |\n\n---\n\n## 3. Anti-Patterns & Common Errors\n\n* **Anti-Pattern: Naive String Manipulation of Raw DICOM Byte Stream**\n  * *Risk*: Data corruption caused by incorrect handling of VR (Value Representation) byte alignment and endianness.\n  * *Remediation*: Use validated DICOM parsers (`pydicom`, `dcmjs`, `dicom-parser`).\n* **Anti-Pattern: Omitting Pixel Spacing Scaling in UI**\n  * *Risk*: Inaccurate physical distance measurements (millimeters) on diagnostic monitors, risking misdiagnosis.\n  * *Remediation*: Parse tag `PixelSpacing (0028,0030)` and apply calibration multipliers in viewer viewports.\n* **Anti-Pattern: Failing to Strip Burned-in Text Annotations**\n  * *Risk*: HIPAA PHI violation when patient details are rendered inside pixel arrays instead of standard metadata headers.\n  * *Remediation*: Inspect tag `BurnedInAnnotation (0028,0301)` and execute automated OCR\u002Fpixel redaction.\n\n---\n\n## 4. Production Python & JS DICOM Snippets\n\n### A. Python DICOM De-Identification Script (`dicom_anonymizer.py`)\n\n```python\n#!\u002Fusr\u002Fbin\u002Fenv python3\n\"\"\"\nHIPAA-Compliant DICOM Anonymization & PACS De-identification Script\n\"\"\"\n\nimport pydicom\nfrom pydicom.dataset import Dataset\n\n# Mandatory DICOM Tags to wipe or randomize for Safe De-identification\nTAGS_TO_REMOVE = [\n    (0x0010, 0x0010),  # Patient's Name\n    (0x0010, 0x0030),  # Patient's Birth Date\n    (0x0010, 0x0040),  # Patient's Sex\n    (0x0010, 0x1000),  # Other Patient IDs\n    (0x0008, 0x0080),  # Institution Name\n    (0x0008, 0x0090),  # Referring Physician's Name\n]\n\ndef anonymize_dicom_file(input_path: str, output_path: str, anon_patient_id: str):\n    \"\"\"\n    Reads a DICOM file, scrubs PHI headers, updates UIDs, and saves anonymized output.\n    \"\"\"\n    ds = pydicom.dcmread(input_path)\n\n    # 1. Scrub Specific PHI Tags\n    for tag in TAGS_TO_REMOVE:\n        if tag in ds:\n            del ds[tag]\n\n    # 2. Assign Pseudonym Patient ID\n    ds.PatientID = anon_patient_id\n    ds.PatientName = f\"ANON^{anon_patient_id}\"\n\n    # 3. Mark Burned-in Annotation tag as NO\n    ds.BurnedInAnnotation = \"NO\"\n\n    # 4. Save clean file\n    ds.save_as(output_path)\n    print(f\"[ANONYMIZED] {input_path} -> {output_path} (ID: {anon_patient_id})\")\n\nif __name__ == \"__main__\":\n    anonymize_dicom_file(\"sample_ct.dcm\", \"clean_ct.dcm\", \"SUBJ-99482\")\n```\n\n---\n\n### B. JavaScript DICOMweb Client with WADO-RS & Cornerstone3D (`dicom_viewer.js`)\n\n```javascript\nimport { api } from 'dicomweb-client';\n\nconst url = 'https:\u002F\u002Fpacs.hospital.org\u002Fdicomweb';\nconst client = new api.DICOMwebClient({ url });\n\n\u002F**\n * Fetch Study Metadata via QIDO-RS\n *\u002F\nexport async function searchPatientStudies(patientId) {\n  const options = {\n    queryParams: {\n      PatientID: patientId,\n      Limit: 10\n    }\n  };\n\n  const studies = await client.searchForStudies(options);\n  console.log(`Found ${studies.length} studies for Patient: ${patientId}`);\n  \n  return studies.map(study => ({\n    studyInstanceUid: study['0020000D'].Value[0],\n    patientName: study['00100010'] ? study['00100010'].Value[0].Alphabetical : 'N\u002FA',\n    studyDate: study['00080020'] ? study['00080020'].Value[0] : 'Unknown'\n  }));\n}\n\n\u002F**\n * Fetch WADO-RS Frames for Web Image Rendering\n *\u002F\nexport async function fetchInstanceFrames(studyUid, seriesUid, instanceUid) {\n  const options = {\n    studyInstanceUID: studyUid,\n    seriesInstanceUID: seriesUid,\n    sopInstanceUID: instanceUid,\n    mediaTypes: [{ mediaType: 'multipart\u002Frelated', type: 'application\u002Foctet-stream' }]\n  };\n\n  const frameArrayBuffers = await client.retrieveInstanceFrames(options);\n  console.log(`Fetched ${frameArrayBuffers.length} frame buffers.`);\n  return frameArrayBuffers[0]; \u002F\u002F Raw 16-bit ArrayBuffer for WebGL canvas\n}\n```\n",{"name":5,"metadata":24,"description":7,"compatibility":26},{"category":25},"Digital Health and BioTech (FHIR and HL7)","DICOM PS3.0+, DICOMweb REST API, Orthanc \u002F dcm4chee PACS, Cornerstone.js \u002F pydicom","main","e905af21e5f1e1c3ca605e9656c3a7930360a84e","Science\u002FBioTech_and_Health_Sciences\u002Fdicom-medical-imaging",1,"https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills","https:\u002F\u002Fhamzabellouch.github.io\u002F","https:\u002F\u002Fgithub.com\u002Fhamzabellouch","hamzabellouch.github.io","CEO & Founder of @tknoglobal | Researcher in Technology & Applied Sciences.","2026-10-17 03:20:19",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add hamzabellouch\u002Fagent-skills --skill dicom-medical-imaging",{"tool":43,"command":44},"bunx","bunx skills add hamzabellouch\u002Fagent-skills --skill dicom-medical-imaging",{"tool":46,"command":47},"pnpm","pnpm dlx skills add hamzabellouch\u002Fagent-skills --skill dicom-medical-imaging","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FScience\u002FBioTech_and_Health_Sciences\u002Fdicom-medical-imaging\u002FSKILL.md",true,[],[52,59,66,73,80,87],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M79FHH2H815A9TAP6WNKH4Q8","security-audit","Comprehensive security guidance, source code audit, vulnerability assessment, and penetration test review for codebases, APIs, microservices, CLI tools, libraries, and LLM-backed applications. Triggers on requests to audit a codebase, conduct security reviews, find vulnerabilities or flaws, pen-test source code, or when the user asks in Arabic (فحص أمني، تدقيق الكود أمنياً، مراجعة الثغرات، فحص أمان المشروع). Supports Guidance mode (focused review) and Full Audit mode (deterministic 6-phase harness).","https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FSecurity\u002FSecurity_Audit_and_Code_Review\u002Fsecurity-audit\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M79FHBGXVBY6VQ1X7ETAZMF1","malware-analysis-reversing","Production malware analysis workflows, reverse engineering methodologies, isolated sandbox triage, static\u002Fdynamic binary analysis, memory forensics, and YARA detection rule authoring.","https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FSecurity\u002FOffensive_Security_and_Pentesting\u002Fmalware-analysis-reversing\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M79FH6EACDR801TZCE4R8SAC","application-security-pentesting","Production Application Security (AppSec) standards, OWASP Top 10 vulnerability remediation, SAST\u002FDAST pipeline integration, secure code review, threat modeling, and defensive security posture.","https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FSecurity\u002FOffensive_Security_and_Pentesting\u002Fapplication-security-pentesting\u002FSKILL.md",[],[],{"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":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M79FH0VKVT44FK923K520ZQA","oauth2-oidc-security-flows","Implement enterprise OAuth 2.1 and OpenID Connect (OIDC) authorization code flow with Proof Key for Code Exchange (PKCE), state and nonce verification, refresh token rotation, token revocation, and centralized IdP federation (Keycloak, Auth0, Okta). Trigger when building secure authentication, single sign-on (SSO), or third-party delegated authorization.","https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FSecurity\u002FIdentity_and_Access_Management_IAM\u002Foauth2-oidc-security-flows\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M79FGVVB3R4T88XXD8FRSV5B","jwt-session-management-hardening","Harden JWT-based authentication and session lifecycles using asymmetric signing (RS256\u002FEdDSA), JWKS rotation, strict claims validation, Redis-backed sliding window sessions, revocation lists, and secure HttpOnly cookie storage. Trigger when implementing token validation, session revocation, or hardening API authentication.","https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FSecurity\u002FIdentity_and_Access_Management_IAM\u002Fjwt-session-management-hardening\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M79FGNCPZ85CVEY0B3NE4H3B","soc2-compliance-automation","Best practices for implementing SOC 2 Type II compliance controls, continuous evidence collection, infrastructure policy-as-code, and automated security monitoring. Use when automating Trust Services Criteria (Security, Availability, Confidentiality, Processing Integrity, Privacy), audit logging, IAM least privilege, or CI\u002FCD security gates.","https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FSecurity\u002FGovernance_Compliance_and_Legal_Tech\u002Fsoc2-compliance-automation\u002FSKILL.md",[],[]]