[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ABZDN8W222N582NSTMPBQJ":3,"skill-same:01M7ABZDN8W222N582NSTMPBQJ":96},{"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":47,"commitSha":48,"skillDirectory":49,"forksCount":14,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":6,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M7ABZDN8W222N582NSTMPBQJ","triaging-vulnerabilities-with-ssvc-framework",null,"Triages and prioritizes vulnerabilities with CISA's Stakeholder-Specific Vulnerability Categorization (SSVC) decision tree, weighing exploitation status (via the CISA KEV catalog and FIRST EPSS API), technical impact, automatability, and mission prevalence to output Track\u002FTrack*\u002FAttend\u002FAct decisions. Use when prioritizing vulnerability scan results (OpenVAS, Nessus, Qualys) for remediation planning beyond raw CVSS scores.","NeelakshSaxena\u002FVayu","NeelakshSaxena","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F87892838?v=4","01M7A3B9YFS6F6N9DD1787DT86","Neelaksh Saxena","01M7A3B9ZKBT09MNMPX2XN69BY",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftriaging-vulnerabilities-with-ssvc-framework\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftriaging-vulnerabilities-with-ssvc-framework\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: triaging-vulnerabilities-with-ssvc-framework\ndescription: Triages and prioritizes vulnerabilities with CISA's Stakeholder-Specific\n  Vulnerability Categorization (SSVC) decision tree, weighing exploitation status\n  (via the CISA KEV catalog and FIRST EPSS API), technical impact, automatability,\n  and mission prevalence to output Track\u002FTrack*\u002FAttend\u002FAct decisions. Use when\n  prioritizing vulnerability scan results (OpenVAS, Nessus, Qualys) for remediation\n  planning beyond raw CVSS scores.\ndomain: cybersecurity\nsubdomain: vulnerability-management\ntags:\n- ssvc\n- vulnerability-triage\n- cisa\n- vulnerability-prioritization\n- decision-tree\n- cvss\n- remediation\n- risk-management\nversion: '1.0'\nauthor: mahipal\nlicense: Apache-2.0\nnist_csf:\n- ID.RA-01\n- ID.RA-02\n- ID.IM-02\n- ID.RA-06\nmitre_attack:\n- T1190\n- T1203\n- T1068\n---\n\n# Triaging Vulnerabilities with SSVC Framework\n\n## Overview\n\nThe Stakeholder-Specific Vulnerability Categorization (SSVC) framework, developed by Carnegie Mellon University's Software Engineering Institute (SEI) in collaboration with CISA, provides a structured decision-tree methodology for vulnerability prioritization. Unlike CVSS alone, SSVC accounts for exploitation status, technical impact, automatability, mission prevalence, and public well-being impact to produce one of four actionable outcomes: **Track**, **Track***, **Attend**, or **Act**.\n\n\n## When to Use\n\n- When managing security operations that require triaging vulnerabilities with ssvc framework\n- When improving security program maturity and operational processes\n- When establishing standardized procedures for security team workflows\n- When integrating threat intelligence or vulnerability data into operations\n\n## Prerequisites\n\n- Python 3.9+ with `requests`, `pandas`, and `jinja2` libraries\n- Access to CISA KEV catalog API and EPSS API from FIRST\n- NVD API key (optional, for higher rate limits)\n- Vulnerability scan results from tools like OpenVAS, Nessus, or Qualys\n\n## SSVC Decision Points\n\n### 1. Exploitation Status\nAssess current exploitation activity:\n- **None** - No evidence of active exploitation\n- **PoC** - Proof-of-concept exists publicly\n- **Active** - Active exploitation observed in the wild (check CISA KEV)\n\n```bash\n# Check if a CVE is in CISA Known Exploited Vulnerabilities catalog\ncurl -s \"https:\u002F\u002Fwww.cisa.gov\u002Fsites\u002Fdefault\u002Ffiles\u002Ffeeds\u002Fknown_exploited_vulnerabilities.json\" | \\\n  python3 -c \"import sys,json; data=json.load(sys.stdin); cves=[v['cveID'] for v in data['vulnerabilities']]; print('Active' if 'CVE-2024-3400' in cves else 'Check PoC\u002FNone')\"\n```\n\n### 2. Technical Impact\nDetermine scope of compromise if exploited:\n- **Partial** - Limited to a subset of system functionality or data\n- **Total** - Full control of the affected system, complete data access\n\n### 3. Automatability\nEvaluate if exploitation can be automated at scale:\n- **No** - Requires manual, targeted exploitation per victim\n- **Yes** - Can be scripted or worm-like propagation is possible\n\n### 4. Mission Prevalence\nHow widespread is the affected product in your environment:\n- **Minimal** - Limited deployment, non-critical systems\n- **Support** - Supports mission-critical functions indirectly\n- **Essential** - Directly enables core mission capabilities\n\n### 5. Public Well-Being Impact\nPotential consequences for physical safety and public welfare:\n- **Minimal** - Negligible impact on safety or public services\n- **Material** - Noticeable degradation of public services\n- **Irreversible** - Loss of life, major property damage, or critical infrastructure failure\n\n## SSVC Decision Outcomes\n\n| Outcome | Action Required | SLA |\n|---------|----------------|-----|\n| **Track** | Monitor, remediate in normal patch cycle | 90 days |\n| **Track*** | Monitor closely, prioritize in next patch window | 60 days |\n| **Attend** | Escalate to senior management, accelerate remediation | 14 days |\n| **Act** | Apply mitigations immediately, executive-level awareness | 48 hours |\n\n## Workflow\n\n### Step 1: Ingest Vulnerability Data\n```python\nimport requests\nimport json\n\n# Fetch CISA KEV catalog\nkev_url = \"https:\u002F\u002Fwww.cisa.gov\u002Fsites\u002Fdefault\u002Ffiles\u002Ffeeds\u002Fknown_exploited_vulnerabilities.json\"\nkev_data = requests.get(kev_url).json()\nkev_cves = {v['cveID'] for v in kev_data['vulnerabilities']}\n\n# Fetch EPSS scores for context\nepss_url = \"https:\u002F\u002Fapi.first.org\u002Fdata\u002Fv1\u002Fepss\"\nepss_response = requests.get(epss_url, params={\"cve\": \"CVE-2024-3400\"}).json()\n```\n\n### Step 2: Evaluate Each Decision Point\n```python\ndef evaluate_exploitation(cve_id, kev_set):\n    \"\"\"Determine exploitation status from CISA KEV and EPSS data.\"\"\"\n    if cve_id in kev_set:\n        return \"active\"\n    epss = requests.get(\n        \"https:\u002F\u002Fapi.first.org\u002Fdata\u002Fv1\u002Fepss\",\n        params={\"cve\": cve_id}\n    ).json()\n    if epss.get(\"data\"):\n        score = float(epss[\"data\"][0].get(\"epss\", 0))\n        if score > 0.5:\n            return \"poc\"\n    return \"none\"\n\ndef evaluate_technical_impact(cvss_vector):\n    \"\"\"Parse CVSS vector for scope and impact metrics.\"\"\"\n    if \"S:C\" in cvss_vector or \"C:H\u002FI:H\u002FA:H\" in cvss_vector:\n        return \"total\"\n    return \"partial\"\n\ndef evaluate_automatability(cvss_vector, cve_description):\n    \"\"\"Check if attack vector is network-based with low complexity.\"\"\"\n    if \"AV:N\" in cvss_vector and \"AC:L\" in cvss_vector and \"UI:N\" in cvss_vector:\n        return \"yes\"\n    return \"no\"\n```\n\n### Step 3: Apply SSVC Decision Tree\n```python\ndef ssvc_decision(exploitation, tech_impact, automatability, mission_prevalence, public_wellbeing):\n    \"\"\"CISA SSVC decision tree implementation.\"\"\"\n    if exploitation == \"active\":\n        if tech_impact == \"total\" or automatability == \"yes\":\n            return \"Act\"\n        if mission_prevalence in (\"essential\", \"support\"):\n            return \"Act\"\n        return \"Attend\"\n    if exploitation == \"poc\":\n        if automatability == \"yes\" and tech_impact == \"total\":\n            return \"Attend\"\n        if mission_prevalence == \"essential\":\n            return \"Attend\"\n        return \"Track*\"\n    # exploitation == \"none\"\n    if tech_impact == \"total\" and mission_prevalence == \"essential\":\n        return \"Track*\"\n    return \"Track\"\n```\n\n### Step 4: Generate Triage Report\n```bash\n# Run the SSVC triage script against scan results\npython3 scripts\u002Fprocess.py --input scan_results.csv --output ssvc_triage_report.json\n\n# View summary\ncat ssvc_triage_report.json | python3 -m json.tool | head -50\n```\n\n## Integration with Vulnerability Scanners\n\n### Import from Nessus CSV\n```bash\n# Export Nessus scan as CSV, then process\npython3 scripts\u002Fprocess.py \\\n  --input nessus_export.csv \\\n  --format nessus \\\n  --output ssvc_results.json\n```\n\n### Import from OpenVAS\n```bash\n# Export OpenVAS results as XML\npython3 scripts\u002Fprocess.py \\\n  --input openvas_report.xml \\\n  --format openvas \\\n  --output ssvc_results.json\n```\n\n## Validation and Testing\n\n```bash\n# Test SSVC decision logic with known CVEs\npython3 -c \"\nfrom scripts.process import ssvc_decision\n# CVE-2024-3400 - Palo Alto PAN-OS command injection (KEV listed)\nassert ssvc_decision('active', 'total', 'yes', 'essential', 'material') == 'Act'\n# CVE-2024-21887 - Ivanti Connect Secure (PoC available)\nassert ssvc_decision('poc', 'total', 'yes', 'support', 'minimal') == 'Attend'\nprint('All SSVC decision tests passed')\n\"\n```\n\n## References\n\n- [CISA SSVC Framework](https:\u002F\u002Fwww.cisa.gov\u002Fstakeholder-specific-vulnerability-categorization-ssvc)\n- [CERT\u002FCC SSVC Documentation](https:\u002F\u002Fcertcc.github.io\u002FSSVC\u002F)\n- [CISA SSVC Guide PDF](https:\u002F\u002Fwww.cisa.gov\u002Fsites\u002Fdefault\u002Ffiles\u002Fpublications\u002Fcisa-ssvc-guide%20508c.pdf)\n- [FIRST EPSS API](https:\u002F\u002Fwww.first.org\u002Fepss\u002F)\n- [CISA Known Exploited Vulnerabilities](https:\u002F\u002Fwww.cisa.gov\u002Fknown-exploited-vulnerabilities-catalog)\n","# Triaging Vulnerabilities with SSVC Framework\n\n## Overview\n\nThe Stakeholder-Specific Vulnerability Categorization (SSVC) framework, developed by Carnegie Mellon University's Software Engineering Institute (SEI) in collaboration with CISA, provides a structured decision-tree methodology for vulnerability prioritization. Unlike CVSS alone, SSVC accounts for exploitation status, technical impact, automatability, mission prevalence, and public well-being impact to produce one of four actionable outcomes: **Track**, **Track***, **Attend**, or **Act**.\n\n\n## When to Use\n\n- When managing security operations that require triaging vulnerabilities with ssvc framework\n- When improving security program maturity and operational processes\n- When establishing standardized procedures for security team workflows\n- When integrating threat intelligence or vulnerability data into operations\n\n## Prerequisites\n\n- Python 3.9+ with `requests`, `pandas`, and `jinja2` libraries\n- Access to CISA KEV catalog API and EPSS API from FIRST\n- NVD API key (optional, for higher rate limits)\n- Vulnerability scan results from tools like OpenVAS, Nessus, or Qualys\n\n## SSVC Decision Points\n\n### 1. Exploitation Status\nAssess current exploitation activity:\n- **None** - No evidence of active exploitation\n- **PoC** - Proof-of-concept exists publicly\n- **Active** - Active exploitation observed in the wild (check CISA KEV)\n\n```bash\n# Check if a CVE is in CISA Known Exploited Vulnerabilities catalog\ncurl -s \"https:\u002F\u002Fwww.cisa.gov\u002Fsites\u002Fdefault\u002Ffiles\u002Ffeeds\u002Fknown_exploited_vulnerabilities.json\" | \\\n  python3 -c \"import sys,json; data=json.load(sys.stdin); cves=[v['cveID'] for v in data['vulnerabilities']]; print('Active' if 'CVE-2024-3400' in cves else 'Check PoC\u002FNone')\"\n```\n\n### 2. Technical Impact\nDetermine scope of compromise if exploited:\n- **Partial** - Limited to a subset of system functionality or data\n- **Total** - Full control of the affected system, complete data access\n\n### 3. Automatability\nEvaluate if exploitation can be automated at scale:\n- **No** - Requires manual, targeted exploitation per victim\n- **Yes** - Can be scripted or worm-like propagation is possible\n\n### 4. Mission Prevalence\nHow widespread is the affected product in your environment:\n- **Minimal** - Limited deployment, non-critical systems\n- **Support** - Supports mission-critical functions indirectly\n- **Essential** - Directly enables core mission capabilities\n\n### 5. Public Well-Being Impact\nPotential consequences for physical safety and public welfare:\n- **Minimal** - Negligible impact on safety or public services\n- **Material** - Noticeable degradation of public services\n- **Irreversible** - Loss of life, major property damage, or critical infrastructure failure\n\n## SSVC Decision Outcomes\n\n| Outcome | Action Required | SLA |\n|---------|----------------|-----|\n| **Track** | Monitor, remediate in normal patch cycle | 90 days |\n| **Track*** | Monitor closely, prioritize in next patch window | 60 days |\n| **Attend** | Escalate to senior management, accelerate remediation | 14 days |\n| **Act** | Apply mitigations immediately, executive-level awareness | 48 hours |\n\n## Workflow\n\n### Step 1: Ingest Vulnerability Data\n```python\nimport requests\nimport json\n\n# Fetch CISA KEV catalog\nkev_url = \"https:\u002F\u002Fwww.cisa.gov\u002Fsites\u002Fdefault\u002Ffiles\u002Ffeeds\u002Fknown_exploited_vulnerabilities.json\"\nkev_data = requests.get(kev_url).json()\nkev_cves = {v['cveID'] for v in kev_data['vulnerabilities']}\n\n# Fetch EPSS scores for context\nepss_url = \"https:\u002F\u002Fapi.first.org\u002Fdata\u002Fv1\u002Fepss\"\nepss_response = requests.get(epss_url, params={\"cve\": \"CVE-2024-3400\"}).json()\n```\n\n### Step 2: Evaluate Each Decision Point\n```python\ndef evaluate_exploitation(cve_id, kev_set):\n    \"\"\"Determine exploitation status from CISA KEV and EPSS data.\"\"\"\n    if cve_id in kev_set:\n        return \"active\"\n    epss = requests.get(\n        \"https:\u002F\u002Fapi.first.org\u002Fdata\u002Fv1\u002Fepss\",\n        params={\"cve\": cve_id}\n    ).json()\n    if epss.get(\"data\"):\n        score = float(epss[\"data\"][0].get(\"epss\", 0))\n        if score > 0.5:\n            return \"poc\"\n    return \"none\"\n\ndef evaluate_technical_impact(cvss_vector):\n    \"\"\"Parse CVSS vector for scope and impact metrics.\"\"\"\n    if \"S:C\" in cvss_vector or \"C:H\u002FI:H\u002FA:H\" in cvss_vector:\n        return \"total\"\n    return \"partial\"\n\ndef evaluate_automatability(cvss_vector, cve_description):\n    \"\"\"Check if attack vector is network-based with low complexity.\"\"\"\n    if \"AV:N\" in cvss_vector and \"AC:L\" in cvss_vector and \"UI:N\" in cvss_vector:\n        return \"yes\"\n    return \"no\"\n```\n\n### Step 3: Apply SSVC Decision Tree\n```python\ndef ssvc_decision(exploitation, tech_impact, automatability, mission_prevalence, public_wellbeing):\n    \"\"\"CISA SSVC decision tree implementation.\"\"\"\n    if exploitation == \"active\":\n        if tech_impact == \"total\" or automatability == \"yes\":\n            return \"Act\"\n        if mission_prevalence in (\"essential\", \"support\"):\n            return \"Act\"\n        return \"Attend\"\n    if exploitation == \"poc\":\n        if automatability == \"yes\" and tech_impact == \"total\":\n            return \"Attend\"\n        if mission_prevalence == \"essential\":\n            return \"Attend\"\n        return \"Track*\"\n    # exploitation == \"none\"\n    if tech_impact == \"total\" and mission_prevalence == \"essential\":\n        return \"Track*\"\n    return \"Track\"\n```\n\n### Step 4: Generate Triage Report\n```bash\n# Run the SSVC triage script against scan results\npython3 scripts\u002Fprocess.py --input scan_results.csv --output ssvc_triage_report.json\n\n# View summary\ncat ssvc_triage_report.json | python3 -m json.tool | head -50\n```\n\n## Integration with Vulnerability Scanners\n\n### Import from Nessus CSV\n```bash\n# Export Nessus scan as CSV, then process\npython3 scripts\u002Fprocess.py \\\n  --input nessus_export.csv \\\n  --format nessus \\\n  --output ssvc_results.json\n```\n\n### Import from OpenVAS\n```bash\n# Export OpenVAS results as XML\npython3 scripts\u002Fprocess.py \\\n  --input openvas_report.xml \\\n  --format openvas \\\n  --output ssvc_results.json\n```\n\n## Validation and Testing\n\n```bash\n# Test SSVC decision logic with known CVEs\npython3 -c \"\nfrom scripts.process import ssvc_decision\n# CVE-2024-3400 - Palo Alto PAN-OS command injection (KEV listed)\nassert ssvc_decision('active', 'total', 'yes', 'essential', 'material') == 'Act'\n# CVE-2024-21887 - Ivanti Connect Secure (PoC available)\nassert ssvc_decision('poc', 'total', 'yes', 'support', 'minimal') == 'Attend'\nprint('All SSVC decision tests passed')\n\"\n```\n\n## References\n\n- [CISA SSVC Framework](https:\u002F\u002Fwww.cisa.gov\u002Fstakeholder-specific-vulnerability-categorization-ssvc)\n- [CERT\u002FCC SSVC Documentation](https:\u002F\u002Fcertcc.github.io\u002FSSVC\u002F)\n- [CISA SSVC Guide PDF](https:\u002F\u002Fwww.cisa.gov\u002Fsites\u002Fdefault\u002Ffiles\u002Fpublications\u002Fcisa-ssvc-guide%20508c.pdf)\n- [FIRST EPSS API](https:\u002F\u002Fwww.first.org\u002Fepss\u002F)\n- [CISA Known Exploited Vulnerabilities](https:\u002F\u002Fwww.cisa.gov\u002Fknown-exploited-vulnerabilities-catalog)\n",{"name":5,"tags":25,"author":34,"domain":35,"license":15,"version":36,"nist_csf":37,"subdomain":42,"description":7,"mitre_attack":43},[26,27,28,29,30,31,32,33],"ssvc","vulnerability-triage","cisa","vulnerability-prioritization","decision-tree","cvss","remediation","risk-management","mahipal","cybersecurity","1.0",[38,39,40,41],"ID.RA-01","ID.RA-02","ID.IM-02","ID.RA-06","vulnerability-management",[44,45,46],"T1190","T1203","T1068","main","7540bbccf0c1ded6156a467b02c95b61ad62413f",".agents\u002Fskills\u002Ftriaging-vulnerabilities-with-ssvc-framework","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena","Currently exploring the intersection of tech","2026-09-11 03:02:31",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add NeelakshSaxena\u002FVayu --skill triaging-vulnerabilities-with-ssvc-framework",{"tool":60,"command":61},"bunx","bunx skills add NeelakshSaxena\u002FVayu --skill triaging-vulnerabilities-with-ssvc-framework",{"tool":63,"command":64},"pnpm","pnpm dlx skills add NeelakshSaxena\u002FVayu --skill triaging-vulnerabilities-with-ssvc-framework","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftriaging-vulnerabilities-with-ssvc-framework\u002FSKILL.md",true,[68,72,78,82,86,92],{"path":69,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":16},"LICENSE","许可证",11255,{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fapi-reference.md","REFERENCE","参考文档",2178,"https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftriaging-vulnerabilities-with-ssvc-framework\u002Freferences\u002Fapi-reference.md",{"path":79,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fstandards.md",3294,"https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftriaging-vulnerabilities-with-ssvc-framework\u002Freferences\u002Fstandards.md",{"path":83,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Fworkflows.md",4350,"https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftriaging-vulnerabilities-with-ssvc-framework\u002Freferences\u002Fworkflows.md",{"path":87,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":90,"sourceHtmlUrl":91},"scripts\u002Fagent.py","SCRIPT","脚本",8262,"https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftriaging-vulnerabilities-with-ssvc-framework\u002Fscripts\u002Fagent.py",{"path":93,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":94,"sourceHtmlUrl":95},"scripts\u002Fprocess.py",12187,"https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftriaging-vulnerabilities-with-ssvc-framework\u002Fscripts\u002Fprocess.py",[97,104,111,118,125,132],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":20},"01M7ACCCVNCFKMA9X6D15X6G98","runpodctl","Runpod CLI for managing GPU\u002FCPU workloads from the terminal — pods, serverless endpoints, templates, network volumes, Hub deploys, models, SSH, and file transfer (send\u002Freceive). Use for terminal\u002FCI\u002Fscripting, Hub browse\u002Fdeploy, SSH setup, `doctor`, or when the Runpod MCP tools are not connected. For structured tool calls in an MCP-enabled session, prefer runpod-mcp.","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frunpodctl\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":20},"01M7ACC63SRHEA5KMCHSMZK2TC","runpod","Start here for any Runpod task — running GPU\u002FCPU pods, deploying serverless endpoints, templates, network volumes, building images, or understanding how Runpod works. Routes to the right skill (runpod-mcp, runpodctl, flash, companion-clis, runpod-usage, runpod-templates, runpod-migrate) and indexes two dozen live-verified end-to-end examples (golden paths) — use it when the lane is unclear, and for any multi-step or provisioning task even when it is not.","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frunpod\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":20},"01M7ACC0Q1C89N9BZBV91CTQTF","runpod-usage","How Runpod works and how to work it — pods vs serverless, GPU\u002FVRAM selection, storage, building a container, networking, plus the agentic pod development loop (provision → ssh-exec → set up → poll readiness) and on-pod install hygiene (uv\u002Fapt). Use to answer \"how does X work\", \"which GPU\", \"how do I build a container\", or \"how do I stand up a workload on a pod\". Guidance, not a tool — execute with runpodctl, runpod-mcp, or flash.","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frunpod-usage\u002FSKILL.md",[],[],{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":20},"01M7ACBRPE345GF5GM5B8P8RRC","runpod-templates","Runpod's official prebuilt pod templates (ComfyUI, PyTorch, and others): what each image ships, which ports and paths it uses, how to pick one, how to pin a version, and what is missing on first boot. Use when a task says \"run \u003CX> on a pod\" and an official template already covers it, instead of building an image — and when a user needs help with or wants to fix something about a Runpod template they are already running (won't boot, can't reach the UI, missing models, wrong CUDA line, broken ComfyUI workflow metadata on imported workflows): start here and route onward. Deploy with runpodctl or runpod-mcp; end-to-end walkthroughs live in the runpod router's golden paths.","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frunpod-templates\u002FSKILL.md",[],[],{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":20},"01M7ACBJATHKVX1TWES2F44GY8","runpod-migrate","Migrate a codebase from the Runpod GraphQL API or REST v1 to REST v2 — inventory which parts use which API version, rewrite the call sites, flag breaking changes, and verify. Use when someone asks to move to v2, asks what v2 would change, or asks which Runpod API their code is on. For managing infrastructure rather than migrating code, use runpod-mcp or runpodctl.","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frunpod-migrate\u002FSKILL.md",[],[],{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":138,"publishedAt":20},"01M7ACBC7GHVH6T9YEAPCG2AP8","runpod-mcp","Manage Runpod infrastructure — pods, serverless endpoints, jobs, templates, network volumes, container-registry auth, GPU\u002FCPU catalog, and billing — via the Runpod MCP server's structured tool calls. Use when the Runpod MCP tools (create-pod, list-endpoints, …) are connected in this session, or to connect them (hosted OAuth or local npx). Prefer this over runpodctl for plain infra CRUD when MCP is available; use runpodctl for the terminal, file transfer, or SSH setup.","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frunpod-mcp\u002FSKILL.md",[],[]]