[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7E2GCWTAPBMM1T7FM4SR4H7":3,"skill-same:01M7E2GCWTAPBMM1T7FM4SR4H7":89},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":6,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M7E2GCWTAPBMM1T7FM4SR4H7","automating-ioc-enrichment",null,"Automates the enrichment of raw indicators of compromise with multi-source threat intelligence context using SOAR platforms, Python pipelines, or TIP playbooks to reduce analyst triage time and standardize enrichment outputs. Use when building automated enrichment workflows integrated with SIEM alerts, email submission pipelines, or bulk IOC processing from threat feeds. Activates for requests involving SOAR enrichment, Cortex XSOAR, Splunk SOAR, TheHive, Python enrichment pipelines, or automated IOC processing.","sanjeevafk\u002Fagent-skills","sanjeevafk","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F230678117?v=4","01M7C540EFY46ETG1NNWKS5X3Q","Sanjeev","01M7C540F366J5C1D587BMKH9Q",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fcollections\u002Fcybersecurity-skills\u002Fskills\u002Fautomating-ioc-enrichment\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fcollections\u002Fcybersecurity-skills\u002Fskills\u002Fautomating-ioc-enrichment\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: automating-ioc-enrichment\ndescription: 'Automates the enrichment of raw indicators of compromise with multi-source\n  threat intelligence context using SOAR platforms, Python pipelines, or TIP playbooks\n  to reduce analyst triage time and standardize enrichment outputs. Use when building\n  automated enrichment workflows integrated with SIEM alerts, email submission pipelines,\n  or bulk IOC processing from threat feeds. Activates for requests involving SOAR\n  enrichment, Cortex XSOAR, Splunk SOAR, TheHive, Python enrichment pipelines, or\n  automated IOC processing.\n\n  '\ndomain: cybersecurity\nsubdomain: threat-intelligence\ntags:\n- SOAR\n- enrichment\n- IOC\n- Cortex-XSOAR\n- Splunk-SOAR\n- VirusTotal\n- automation\n- CTI\n- NIST-CSF\nversion: 1.0.0\nauthor: team-cybersecurity\nlicense: Apache-2.0\nnist_csf:\n- ID.RA-01\n- ID.RA-05\n- DE.CM-01\n- DE.AE-02\nmitre_attack:\n- T1071.001\n- T1583.001\n- T1588.001\n- T1590.005\n- T1596\n---\n# Automating IOC Enrichment\n\n## When to Use\n\nUse this skill when:\n- Building a SOAR playbook that automatically enriches SIEM alerts with threat intelligence context before routing to analysts\n- Creating a Python pipeline for bulk IOC enrichment from phishing email submissions\n- Reducing analyst mean time to triage (MTTT) by pre-populating alert context with VT, Shodan, and MISP data\n\n**Do not use** this skill for fully automated blocking decisions without human review — enrichment automation should inform decisions, not execute blocks autonomously for high-impact actions.\n\n## Prerequisites\n\n- SOAR platform (Cortex XSOAR, Splunk SOAR, Tines, or n8n) or Python 3.9+ environment\n- API keys: VirusTotal, AbuseIPDB, Shodan, and at minimum one TIP (MISP or OpenCTI)\n- SIEM integration endpoint for alert consumption\n- Rate limit budgets documented per API (VT: 4\u002Fmin free, 500\u002Fmin enterprise)\n\n## Workflow\n\n### Step 1: Design Enrichment Pipeline Architecture\n\nDefine the enrichment flow for each IOC type:\n```\nSIEM Alert → Extract IOCs → Classify Type → Route to enrichment functions\n  IP Address → AbuseIPDB + Shodan + VirusTotal IP + MISP\n  Domain → VirusTotal Domain + PassiveTotal + Shodan + MISP\n  URL → URLScan.io + VirusTotal URL + Google Safe Browse\n  File Hash → VirusTotal Files + MalwareBazaar + MISP\n→ Aggregate results → Calculate confidence score → Update alert → Notify analyst\n```\n\n### Step 2: Implement Python Enrichment Functions\n\n```python\nimport requests\nimport time\nfrom dataclasses import dataclass, field\nfrom typing import Optional\n\nRATE_LIMIT_DELAY = 0.25  # 4 requests\u002Fsecond for VT free tier\n\n@dataclass\nclass EnrichmentResult:\n    ioc_value: str\n    ioc_type: str\n    vt_malicious: int = 0\n    vt_total: int = 0\n    abuse_confidence: int = 0\n    shodan_ports: list = field(default_factory=list)\n    misp_events: list = field(default_factory=list)\n    confidence_score: int = 0\n\ndef enrich_ip(ip: str, vt_key: str, abuse_key: str, shodan_key: str) -> EnrichmentResult:\n    result = EnrichmentResult(ip, \"ip\")\n\n    # VirusTotal IP lookup\n    vt_resp = requests.get(\n        f\"https:\u002F\u002Fwww.virustotal.com\u002Fapi\u002Fv3\u002Fip_addresses\u002F{ip}\",\n        headers={\"x-apikey\": vt_key}\n    )\n    if vt_resp.status_code == 200:\n        stats = vt_resp.json()[\"data\"][\"attributes\"][\"last_analysis_stats\"]\n        result.vt_malicious = stats.get(\"malicious\", 0)\n        result.vt_total = sum(stats.values())\n\n    time.sleep(RATE_LIMIT_DELAY)\n\n    # AbuseIPDB\n    abuse_resp = requests.get(\n        \"https:\u002F\u002Fapi.abuseipdb.com\u002Fapi\u002Fv2\u002Fcheck\",\n        headers={\"Key\": abuse_key, \"Accept\": \"application\u002Fjson\"},\n        params={\"ipAddress\": ip, \"maxAgeInDays\": 90}\n    )\n    if abuse_resp.status_code == 200:\n        result.abuse_confidence = abuse_resp.json()[\"data\"][\"abuseConfidenceScore\"]\n\n    # Calculate composite confidence score\n    result.confidence_score = min(\n        (result.vt_malicious \u002F max(result.vt_total, 1)) * 60 +\n        (result.abuse_confidence \u002F 100) * 40, 100\n    )\n\n    return result\n\ndef enrich_hash(sha256: str, vt_key: str) -> EnrichmentResult:\n    result = EnrichmentResult(sha256, \"sha256\")\n    vt_resp = requests.get(\n        f\"https:\u002F\u002Fwww.virustotal.com\u002Fapi\u002Fv3\u002Ffiles\u002F{sha256}\",\n        headers={\"x-apikey\": vt_key}\n    )\n    if vt_resp.status_code == 200:\n        stats = vt_resp.json()[\"data\"][\"attributes\"][\"last_analysis_stats\"]\n        result.vt_malicious = stats.get(\"malicious\", 0)\n        result.vt_total = sum(stats.values())\n        result.confidence_score = int((result.vt_malicious \u002F max(result.vt_total, 1)) * 100)\n    return result\n```\n\n### Step 3: Build SOAR Playbook (Cortex XSOAR)\n\nIn Cortex XSOAR, create an enrichment playbook:\n1. **Trigger**: Alert created in SIEM (via webhook or polling)\n2. **Extract IOCs**: Use \"Extract Indicators\" task with regex patterns for IP, domain, URL, hash\n3. **Parallel enrichment**: Fan-out to multiple enrichment tasks simultaneously\n4. **VT Enrichment**: Call `!vt-file-scan` or `!vt-ip-scan` commands\n5. **AbuseIPDB check**: Call `!abuseipdb-check-ip` command\n6. **MISP Lookup**: Call `!misp-search` for cross-referencing\n7. **Score aggregation**: Python transform task computing composite score\n8. **Conditional routing**: If score ≥70 → High Priority queue; if 40–69 → Medium; \u003C40 → Auto-close with note\n9. **Alert enrichment**: Write enrichment results to alert context for analyst view\n\n### Step 4: Handle Rate Limiting and Failures\n\n```python\nimport time\nfrom functools import wraps\n\ndef rate_limited(max_per_second):\n    min_interval = 1.0 \u002F max_per_second\n    def decorator(func):\n        last_called = [0.0]\n        @wraps(func)\n        def wrapper(*args, **kwargs):\n            elapsed = time.time() - last_called[0]\n            wait = min_interval - elapsed\n            if wait > 0:\n                time.sleep(wait)\n            result = func(*args, **kwargs)\n            last_called[0] = time.time()\n            return result\n        return wrapper\n    return decorator\n\ndef retry_on_429(max_retries=3):\n    def decorator(func):\n        @wraps(func)\n        def wrapper(*args, **kwargs):\n            for attempt in range(max_retries):\n                response = func(*args, **kwargs)\n                if response.status_code == 429:\n                    retry_after = int(response.headers.get(\"Retry-After\", 60))\n                    time.sleep(retry_after)\n                else:\n                    return response\n        return wrapper\n    return decorator\n```\n\n### Step 5: Metrics and Tuning\n\nTrack pipeline performance weekly:\n- **Enrichment latency**: Target \u003C30 seconds from alert trigger to enriched output\n- **API success rate**: Target >99% (identify rate limit or outage events)\n- **True positive rate**: Track analyst overrides of automated confidence scores\n- **Cost**: Track API call volume against budget (VT Enterprise: $X per 1M lookups)\n\n## Key Concepts\n\n| Term | Definition |\n|------|-----------|\n| **SOAR** | Security Orchestration, Automation, and Response — platform for automating security workflows and integrating disparate tools |\n| **Enrichment Playbook** | Automated workflow sequence that adds contextual intelligence to raw security events |\n| **Rate Limiting** | API provider restrictions on request frequency (e.g., VT free: 4 requests\u002Fminute); pipelines must respect these limits |\n| **Composite Confidence Score** | Single score aggregating signals from multiple enrichment sources using weighted formula |\n| **Fan-out Pattern** | Parallel execution of multiple enrichment queries simultaneously to minimize total enrichment latency |\n\n## Tools & Systems\n\n- **Cortex XSOAR (Palo Alto)**: Enterprise SOAR with 700+ marketplace integrations including VT, MISP, Shodan, and AbuseIPDB\n- **Splunk SOAR (Phantom)**: SOAR platform with Python-based playbooks; native Splunk SIEM integration\n- **Tines**: No-code SOAR platform with webhook-driven automation; cost-effective for smaller teams\n- **TheHive + Cortex**: Open-source IR\u002Fenrichment platform with observable enrichment via Cortex analyzers\n\n## Common Pitfalls\n\n- **Blocking on enrichment latency**: If enrichment takes >5 minutes, analysts start working unenriched alerts, defeating the purpose. Set timeout limits and provide partial results.\n- **No caching**: Querying the same IOC 50 times generates unnecessary API costs. Cache enrichment results for 24 hours by default.\n- **Ignoring API failures silently**: Failed enrichment calls should be logged and trigger fallback logic, not silently produce empty results that appear as clean IOCs.\n- **Automating blocks on enrichment score alone**: Composite scores contain false positives; require human confirmation for blocking decisions against shared infrastructure.\n","# Automating IOC Enrichment\n\n## When to Use\n\nUse this skill when:\n- Building a SOAR playbook that automatically enriches SIEM alerts with threat intelligence context before routing to analysts\n- Creating a Python pipeline for bulk IOC enrichment from phishing email submissions\n- Reducing analyst mean time to triage (MTTT) by pre-populating alert context with VT, Shodan, and MISP data\n\n**Do not use** this skill for fully automated blocking decisions without human review — enrichment automation should inform decisions, not execute blocks autonomously for high-impact actions.\n\n## Prerequisites\n\n- SOAR platform (Cortex XSOAR, Splunk SOAR, Tines, or n8n) or Python 3.9+ environment\n- API keys: VirusTotal, AbuseIPDB, Shodan, and at minimum one TIP (MISP or OpenCTI)\n- SIEM integration endpoint for alert consumption\n- Rate limit budgets documented per API (VT: 4\u002Fmin free, 500\u002Fmin enterprise)\n\n## Workflow\n\n### Step 1: Design Enrichment Pipeline Architecture\n\nDefine the enrichment flow for each IOC type:\n```\nSIEM Alert → Extract IOCs → Classify Type → Route to enrichment functions\n  IP Address → AbuseIPDB + Shodan + VirusTotal IP + MISP\n  Domain → VirusTotal Domain + PassiveTotal + Shodan + MISP\n  URL → URLScan.io + VirusTotal URL + Google Safe Browse\n  File Hash → VirusTotal Files + MalwareBazaar + MISP\n→ Aggregate results → Calculate confidence score → Update alert → Notify analyst\n```\n\n### Step 2: Implement Python Enrichment Functions\n\n```python\nimport requests\nimport time\nfrom dataclasses import dataclass, field\nfrom typing import Optional\n\nRATE_LIMIT_DELAY = 0.25  # 4 requests\u002Fsecond for VT free tier\n\n@dataclass\nclass EnrichmentResult:\n    ioc_value: str\n    ioc_type: str\n    vt_malicious: int = 0\n    vt_total: int = 0\n    abuse_confidence: int = 0\n    shodan_ports: list = field(default_factory=list)\n    misp_events: list = field(default_factory=list)\n    confidence_score: int = 0\n\ndef enrich_ip(ip: str, vt_key: str, abuse_key: str, shodan_key: str) -> EnrichmentResult:\n    result = EnrichmentResult(ip, \"ip\")\n\n    # VirusTotal IP lookup\n    vt_resp = requests.get(\n        f\"https:\u002F\u002Fwww.virustotal.com\u002Fapi\u002Fv3\u002Fip_addresses\u002F{ip}\",\n        headers={\"x-apikey\": vt_key}\n    )\n    if vt_resp.status_code == 200:\n        stats = vt_resp.json()[\"data\"][\"attributes\"][\"last_analysis_stats\"]\n        result.vt_malicious = stats.get(\"malicious\", 0)\n        result.vt_total = sum(stats.values())\n\n    time.sleep(RATE_LIMIT_DELAY)\n\n    # AbuseIPDB\n    abuse_resp = requests.get(\n        \"https:\u002F\u002Fapi.abuseipdb.com\u002Fapi\u002Fv2\u002Fcheck\",\n        headers={\"Key\": abuse_key, \"Accept\": \"application\u002Fjson\"},\n        params={\"ipAddress\": ip, \"maxAgeInDays\": 90}\n    )\n    if abuse_resp.status_code == 200:\n        result.abuse_confidence = abuse_resp.json()[\"data\"][\"abuseConfidenceScore\"]\n\n    # Calculate composite confidence score\n    result.confidence_score = min(\n        (result.vt_malicious \u002F max(result.vt_total, 1)) * 60 +\n        (result.abuse_confidence \u002F 100) * 40, 100\n    )\n\n    return result\n\ndef enrich_hash(sha256: str, vt_key: str) -> EnrichmentResult:\n    result = EnrichmentResult(sha256, \"sha256\")\n    vt_resp = requests.get(\n        f\"https:\u002F\u002Fwww.virustotal.com\u002Fapi\u002Fv3\u002Ffiles\u002F{sha256}\",\n        headers={\"x-apikey\": vt_key}\n    )\n    if vt_resp.status_code == 200:\n        stats = vt_resp.json()[\"data\"][\"attributes\"][\"last_analysis_stats\"]\n        result.vt_malicious = stats.get(\"malicious\", 0)\n        result.vt_total = sum(stats.values())\n        result.confidence_score = int((result.vt_malicious \u002F max(result.vt_total, 1)) * 100)\n    return result\n```\n\n### Step 3: Build SOAR Playbook (Cortex XSOAR)\n\nIn Cortex XSOAR, create an enrichment playbook:\n1. **Trigger**: Alert created in SIEM (via webhook or polling)\n2. **Extract IOCs**: Use \"Extract Indicators\" task with regex patterns for IP, domain, URL, hash\n3. **Parallel enrichment**: Fan-out to multiple enrichment tasks simultaneously\n4. **VT Enrichment**: Call `!vt-file-scan` or `!vt-ip-scan` commands\n5. **AbuseIPDB check**: Call `!abuseipdb-check-ip` command\n6. **MISP Lookup**: Call `!misp-search` for cross-referencing\n7. **Score aggregation**: Python transform task computing composite score\n8. **Conditional routing**: If score ≥70 → High Priority queue; if 40–69 → Medium; \u003C40 → Auto-close with note\n9. **Alert enrichment**: Write enrichment results to alert context for analyst view\n\n### Step 4: Handle Rate Limiting and Failures\n\n```python\nimport time\nfrom functools import wraps\n\ndef rate_limited(max_per_second):\n    min_interval = 1.0 \u002F max_per_second\n    def decorator(func):\n        last_called = [0.0]\n        @wraps(func)\n        def wrapper(*args, **kwargs):\n            elapsed = time.time() - last_called[0]\n            wait = min_interval - elapsed\n            if wait > 0:\n                time.sleep(wait)\n            result = func(*args, **kwargs)\n            last_called[0] = time.time()\n            return result\n        return wrapper\n    return decorator\n\ndef retry_on_429(max_retries=3):\n    def decorator(func):\n        @wraps(func)\n        def wrapper(*args, **kwargs):\n            for attempt in range(max_retries):\n                response = func(*args, **kwargs)\n                if response.status_code == 429:\n                    retry_after = int(response.headers.get(\"Retry-After\", 60))\n                    time.sleep(retry_after)\n                else:\n                    return response\n        return wrapper\n    return decorator\n```\n\n### Step 5: Metrics and Tuning\n\nTrack pipeline performance weekly:\n- **Enrichment latency**: Target \u003C30 seconds from alert trigger to enriched output\n- **API success rate**: Target >99% (identify rate limit or outage events)\n- **True positive rate**: Track analyst overrides of automated confidence scores\n- **Cost**: Track API call volume against budget (VT Enterprise: $X per 1M lookups)\n\n## Key Concepts\n\n| Term | Definition |\n|------|-----------|\n| **SOAR** | Security Orchestration, Automation, and Response — platform for automating security workflows and integrating disparate tools |\n| **Enrichment Playbook** | Automated workflow sequence that adds contextual intelligence to raw security events |\n| **Rate Limiting** | API provider restrictions on request frequency (e.g., VT free: 4 requests\u002Fminute); pipelines must respect these limits |\n| **Composite Confidence Score** | Single score aggregating signals from multiple enrichment sources using weighted formula |\n| **Fan-out Pattern** | Parallel execution of multiple enrichment queries simultaneously to minimize total enrichment latency |\n\n## Tools & Systems\n\n- **Cortex XSOAR (Palo Alto)**: Enterprise SOAR with 700+ marketplace integrations including VT, MISP, Shodan, and AbuseIPDB\n- **Splunk SOAR (Phantom)**: SOAR platform with Python-based playbooks; native Splunk SIEM integration\n- **Tines**: No-code SOAR platform with webhook-driven automation; cost-effective for smaller teams\n- **TheHive + Cortex**: Open-source IR\u002Fenrichment platform with observable enrichment via Cortex analyzers\n\n## Common Pitfalls\n\n- **Blocking on enrichment latency**: If enrichment takes >5 minutes, analysts start working unenriched alerts, defeating the purpose. Set timeout limits and provide partial results.\n- **No caching**: Querying the same IOC 50 times generates unnecessary API costs. Cache enrichment results for 24 hours by default.\n- **Ignoring API failures silently**: Failed enrichment calls should be logged and trigger fallback logic, not silently produce empty results that appear as clean IOCs.\n- **Automating blocks on enrichment score alone**: Composite scores contain false positives; require human confirmation for blocking decisions against shared infrastructure.\n",{"name":5,"tags":25,"author":35,"domain":36,"license":15,"version":37,"nist_csf":38,"subdomain":43,"description":44,"mitre_attack":45},[26,27,28,29,30,31,32,33,34],"SOAR","enrichment","IOC","Cortex-XSOAR","Splunk-SOAR","VirusTotal","automation","CTI","NIST-CSF","team-cybersecurity","cybersecurity","1.0.0",[39,40,41,42],"ID.RA-01","ID.RA-05","DE.CM-01","DE.AE-02","threat-intelligence","Automates the enrichment of raw indicators of compromise with multi-source threat intelligence context using SOAR platforms, Python pipelines, or TIP playbooks to reduce analyst triage time and standardize enrichment outputs. Use when building automated enrichment workflows integrated with SIEM alerts, email submission pipelines, or bulk IOC processing from threat feeds. Activates for requests involving SOAR enrichment, Cortex XSOAR, Splunk SOAR, TheHive, Python enrichment pipelines, or automated IOC processing.\n",[46,47,48,49,50],"T1071.001","T1583.001","T1588.001","T1590.005","T1596","main","4e084e84eb42fc53e144c89c0f7f48b39c8a4b0f","collections\u002Fcybersecurity-skills\u002Fskills\u002Fautomating-ioc-enrichment",1,"https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills","https:\u002F\u002Fgithub.com\u002Fsanjeevafk","First make it work. Then make it right. Then make it fast.","2026-11-14 13:36:16",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add sanjeevafk\u002Fagent-skills --skill automating-ioc-enrichment",{"tool":65,"command":66},"bunx","bunx skills add sanjeevafk\u002Fagent-skills --skill automating-ioc-enrichment",{"tool":68,"command":69},"pnpm","pnpm dlx skills add sanjeevafk\u002Fagent-skills --skill automating-ioc-enrichment","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fcollections\u002Fcybersecurity-skills\u002Fskills\u002Fautomating-ioc-enrichment\u002FSKILL.md",true,[73,77,83],{"path":74,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":16},"LICENSE","许可证",11255,{"path":78,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fapi-reference.md","REFERENCE","参考文档",1845,"https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fcollections\u002Fcybersecurity-skills\u002Fskills\u002Fautomating-ioc-enrichment\u002Freferences\u002Fapi-reference.md",{"path":84,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":87,"sourceHtmlUrl":88},"scripts\u002Fagent.py","SCRIPT","脚本",7997,"https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fcollections\u002Fcybersecurity-skills\u002Fskills\u002Fautomating-ioc-enrichment\u002Fscripts\u002Fagent.py",[90,98,106,114,122,129],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":94,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":20},"01M7EFHX67M3KKXT1BXVPA5ADT","zarr-python","Chunked N-D arrays for cloud storage (Zarr-Python 3). Compressed arrays, parallel I\u002FO, S3\u002FGCS via fsspec, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","MIT","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzarr-python\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":94,"licenseFileUrl":102,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":20},"01M7EFFQGM51TZBGRENXY50ZYM","whiteboard-diagrams","Create accurate, simple, hand-drawn whiteboard diagrams from a user's process, system, architecture, learning workflow, comparison, or causal explanation. Use when the user asks for a scribbly whiteboard visual, educational workflow graphic, hand-drawn explainer, or diagram like the bundled reference; ask one focused clarification question when the subject or relationships are missing, then generate and visually verify the final image.","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwhiteboard-diagrams\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwhiteboard-diagrams\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":110,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":20},"01M7EFF1CSQNTDMHFK4ZGY6NYK","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[],[],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":118,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":20},"01M7EFE8106X6C28FT8PA74427","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fweb-artifacts-builder\u002FSKILL.md",[],[],{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":94,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":20},"01M7EFCSNZM9G7ZHS6F127Q71X","verification-loop","A comprehensive verification system for Claude Code sessions.","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fverification-loop\u002FSKILL.md",[],[],{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":94,"licenseFileUrl":133,"sourceHtmlUrl":134,"categories":135,"keywords":136,"publishedAt":20},"01M7EFCE7EZMKPRYDDNKBQ9EEH","vercel-deploy","Deploy applications and websites to Vercel. Use when the user requests deployment actions like \"deploy my app\", \"deploy and give me the link\", \"push this live\", or \"create a preview deployment\".","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fvercel-deploy\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fvercel-deploy\u002FSKILL.md",[],[]]