[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7A7D2TZZWK7KAE2P3J59WHB":3,"skill-same:01M7A7D2TZZWK7KAE2P3J59WHB":94},{"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":57,"commitSha":58,"skillDirectory":59,"forksCount":14,"repositoryHtmlUrl":60,"repositoryHomepageUrl":6,"ownerHtmlUrl":61,"ownerBlogUrl":6,"ownerDescription":62,"updatedAt":63,"install":64,"resources":77},"01M7A7D2TZZWK7KAE2P3J59WHB","hunting-advanced-persistent-threats",null,"Proactively hunts for Advanced Persistent Threat (APT) activity within enterprise environments using hypothesis-driven searches across endpoint telemetry, network logs, and memory artifacts. Use when conducting scheduled threat hunting cycles, investigating anomalous behavior flagged by UEBA, or validating that known APT TTPs are not present in the environment. Activates for requests involving MITRE ATT&CK, Velociraptor, osquery, Zeek, or threat hunting playbooks.","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\u002Fhunting-advanced-persistent-threats\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fhunting-advanced-persistent-threats\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: hunting-advanced-persistent-threats\ndescription: 'Proactively hunts for Advanced Persistent Threat (APT) activity within\n  enterprise environments using hypothesis-driven searches across endpoint telemetry,\n  network logs, and memory artifacts. Use when conducting scheduled threat hunting\n  cycles, investigating anomalous behavior flagged by UEBA, or validating that known\n  APT TTPs are not present in the environment. Activates for requests involving MITRE\n  ATT&CK, Velociraptor, osquery, Zeek, or threat hunting playbooks.\n\n  '\ndomain: cybersecurity\nsubdomain: threat-intelligence\ntags:\n- MITRE-ATT&CK\n- threat-hunting\n- APT\n- Velociraptor\n- osquery\n- Zeek\n- TTP\n- NIST-CSF\n- EDR\nversion: 1.0.0\nauthor: mahipal\nlicense: Apache-2.0\nd3fend_techniques:\n- File Metadata Consistency Validation\n- Application Protocol Command Analysis\n- Identifier Analysis\n- Content Format Conversion\n- Message Analysis\nnist_csf:\n- ID.RA-01\n- ID.RA-05\n- DE.CM-01\n- DE.AE-02\nmitre_attack:\n- T1591\n- T1592\n- T1593\n- T1589\n- T1005\n---\n# Hunting Advanced Persistent Threats\n\n## When to Use\n\nUse this skill when:\n- Conducting proactive threat hunting sprints (typically 2–4 week cycles) based on newly published APT intelligence\n- A UEBA alert or anomaly detection system flags behavioral deviations warranting deeper investigation\n- A peer organization or ISAC sharing partner reports active APT compromise and you need to validate your own exposure\n\n**Do not use** this skill as a substitute for incident response when a confirmed breach is in progress — escalate to IR procedures (NIST SP 800-61).\n\n## Prerequisites\n\n- EDR platform with telemetry retention (CrowdStrike Falcon, Microsoft Defender for Endpoint, or SentinelOne) covering 30+ days\n- Access to MITRE ATT&CK Navigator for hypothesis development\n- Network flow data (NetFlow, Zeek, or Suricata logs) in a queryable SIEM\n- Threat hunting platform or query interface (Velociraptor, osquery fleet, or Splunk ES)\n\n## Workflow\n\n### Step 1: Develop Hunt Hypothesis\n\nSelect a threat actor relevant to your sector using MITRE ATT&CK Groups (https:\u002F\u002Fattack.mitre.org\u002Fgroups\u002F). Review the group's known TTPs mapped to ATT&CK techniques. Example hypothesis: \"APT29 (Cozy Bear) uses spearphishing with ISO attachments (T1566.001) and living-off-the-land binaries (T1218) — test for unusual mshta.exe and rundll32.exe parent-child relationships.\"\n\nDocument hypothesis using the Threat Hunting Loop framework: hypothesis → data collection → pattern analysis → response.\n\n### Step 2: Identify Required Data Sources\n\nMap each ATT&CK technique to required log sources using the ATT&CK Data Sources taxonomy:\n- Process creation (T1059): Windows Security Event 4688 or Sysmon Event ID 1\n- Network connections (T1071): Zeek conn.log, NetFlow, EDR network telemetry\n- Registry modifications (T1547): Sysmon Event ID 13, Windows Security 4657\n- Memory injection (T1055): EDR memory scan telemetry, Volatility output\n\nVerify log coverage using ATT&CK Coverage Calculator or a custom data source matrix.\n\n### Step 3: Execute Hunts with Velociraptor or osquery\n\n**Velociraptor VQL hunt** for unusual PowerShell execution:\n```vql\nSELECT Pid, Ppid, Name, CommandLine, CreateTime\nFROM pslist()\nWHERE Name =~ \"powershell.exe\"\nAND CommandLine =~ \"-enc|-nop|-w hidden\"\n```\n\n**osquery** for persistence via scheduled tasks:\n```sql\nSELECT name, action, enabled, path\nFROM scheduled_tasks\nWHERE action NOT LIKE '%System32%'\nAND enabled = 1;\n```\n\n**Splunk SPL** for lateral movement via PsExec:\n```spl\nindex=windows EventCode=7045 ServiceFileName=\"*PSEXESVC*\"\n| stats count by ComputerName, ServiceName, ServiceFileName\n```\n\n### Step 4: Analyze Results and Pivot\n\nFor each anomaly identified, pivot across dimensions:\n- Temporal: Did this occur before or after known IOC timestamps?\n- Host: How many endpoints exhibit this behavior?\n- User: Is the associated account a service account, privileged user, or regular user?\n- Network: Does the host communicate with external IPs not in baseline?\n\nApply the Diamond Model (adversary, capability, infrastructure, victim) to structure findings.\n\n### Step 5: Document and Operationalize Findings\n\nIf hunting reveals confirmed malicious activity, activate IR procedures. If hunting reveals a gap (hunt found nothing but data coverage was insufficient), document the coverage gap and remediate.\n\nConvert successful hunt queries into SIEM detection rules using Sigma format for portability across platforms.\n\n## Key Concepts\n\n| Term | Definition |\n|------|-----------|\n| **TTP** | Tactics, Techniques, and Procedures — adversary behavioral patterns as defined in MITRE ATT&CK |\n| **Diamond Model** | Analytical framework with four vertices (adversary, capability, infrastructure, victim) used to structure intrusion analysis |\n| **Living-off-the-Land (LotL)** | Attacker technique using legitimate OS tools (PowerShell, WMI, certutil) to evade detection |\n| **UEBA** | User and Entity Behavior Analytics — ML-based detection of anomalous behavior baselines |\n| **Sigma** | Open standard for SIEM-agnostic detection rule format, analogous to YARA for network\u002Flog detection |\n| **Hunt Hypothesis** | A testable prediction about adversary presence based on threat intelligence and environmental knowledge |\n\n## Tools & Systems\n\n- **Velociraptor**: Open-source DFIR platform with VQL query language for scalable endpoint hunting across thousands of systems\n- **osquery**: SQL-based OS instrumentation framework for real-time endpoint telemetry queries\n- **MITRE ATT&CK Navigator**: Web-based tool for visualizing ATT&CK coverage and technique prioritization\n- **Zeek (formerly Bro)**: Network traffic analyzer producing structured logs (conn, dns, http, ssl) suitable for hunting\n- **Elastic Security**: EQL (Event Query Language) enables sequence-based hunting for multi-stage attack patterns\n- **Sigma**: Detection rule format with translators for Splunk, QRadar, Sentinel, and Elastic\n\n## Common Pitfalls\n\n- **Confirmation bias**: Starting a hunt expecting to find something and interpreting benign data as malicious. Document null results — they validate controls.\n- **Insufficient data retention**: Many APT techniques require 90+ days of log history to identify slow-and-low patterns. Default retention periods are often too short.\n- **Hunting without baselines**: Cannot identify anomalies without knowing normal. Spend time on baseline documentation before hunting.\n- **Query performance impact**: Broad queries against production SIEM during business hours can degrade analyst workflows. Schedule intensive hunts during off-peak hours.\n- **Ignoring false positives systematically**: Track false positive rates per query. Queries with >80% FP rate should be refined or retired before operationalization.\n","# Hunting Advanced Persistent Threats\n\n## When to Use\n\nUse this skill when:\n- Conducting proactive threat hunting sprints (typically 2–4 week cycles) based on newly published APT intelligence\n- A UEBA alert or anomaly detection system flags behavioral deviations warranting deeper investigation\n- A peer organization or ISAC sharing partner reports active APT compromise and you need to validate your own exposure\n\n**Do not use** this skill as a substitute for incident response when a confirmed breach is in progress — escalate to IR procedures (NIST SP 800-61).\n\n## Prerequisites\n\n- EDR platform with telemetry retention (CrowdStrike Falcon, Microsoft Defender for Endpoint, or SentinelOne) covering 30+ days\n- Access to MITRE ATT&CK Navigator for hypothesis development\n- Network flow data (NetFlow, Zeek, or Suricata logs) in a queryable SIEM\n- Threat hunting platform or query interface (Velociraptor, osquery fleet, or Splunk ES)\n\n## Workflow\n\n### Step 1: Develop Hunt Hypothesis\n\nSelect a threat actor relevant to your sector using MITRE ATT&CK Groups (https:\u002F\u002Fattack.mitre.org\u002Fgroups\u002F). Review the group's known TTPs mapped to ATT&CK techniques. Example hypothesis: \"APT29 (Cozy Bear) uses spearphishing with ISO attachments (T1566.001) and living-off-the-land binaries (T1218) — test for unusual mshta.exe and rundll32.exe parent-child relationships.\"\n\nDocument hypothesis using the Threat Hunting Loop framework: hypothesis → data collection → pattern analysis → response.\n\n### Step 2: Identify Required Data Sources\n\nMap each ATT&CK technique to required log sources using the ATT&CK Data Sources taxonomy:\n- Process creation (T1059): Windows Security Event 4688 or Sysmon Event ID 1\n- Network connections (T1071): Zeek conn.log, NetFlow, EDR network telemetry\n- Registry modifications (T1547): Sysmon Event ID 13, Windows Security 4657\n- Memory injection (T1055): EDR memory scan telemetry, Volatility output\n\nVerify log coverage using ATT&CK Coverage Calculator or a custom data source matrix.\n\n### Step 3: Execute Hunts with Velociraptor or osquery\n\n**Velociraptor VQL hunt** for unusual PowerShell execution:\n```vql\nSELECT Pid, Ppid, Name, CommandLine, CreateTime\nFROM pslist()\nWHERE Name =~ \"powershell.exe\"\nAND CommandLine =~ \"-enc|-nop|-w hidden\"\n```\n\n**osquery** for persistence via scheduled tasks:\n```sql\nSELECT name, action, enabled, path\nFROM scheduled_tasks\nWHERE action NOT LIKE '%System32%'\nAND enabled = 1;\n```\n\n**Splunk SPL** for lateral movement via PsExec:\n```spl\nindex=windows EventCode=7045 ServiceFileName=\"*PSEXESVC*\"\n| stats count by ComputerName, ServiceName, ServiceFileName\n```\n\n### Step 4: Analyze Results and Pivot\n\nFor each anomaly identified, pivot across dimensions:\n- Temporal: Did this occur before or after known IOC timestamps?\n- Host: How many endpoints exhibit this behavior?\n- User: Is the associated account a service account, privileged user, or regular user?\n- Network: Does the host communicate with external IPs not in baseline?\n\nApply the Diamond Model (adversary, capability, infrastructure, victim) to structure findings.\n\n### Step 5: Document and Operationalize Findings\n\nIf hunting reveals confirmed malicious activity, activate IR procedures. If hunting reveals a gap (hunt found nothing but data coverage was insufficient), document the coverage gap and remediate.\n\nConvert successful hunt queries into SIEM detection rules using Sigma format for portability across platforms.\n\n## Key Concepts\n\n| Term | Definition |\n|------|-----------|\n| **TTP** | Tactics, Techniques, and Procedures — adversary behavioral patterns as defined in MITRE ATT&CK |\n| **Diamond Model** | Analytical framework with four vertices (adversary, capability, infrastructure, victim) used to structure intrusion analysis |\n| **Living-off-the-Land (LotL)** | Attacker technique using legitimate OS tools (PowerShell, WMI, certutil) to evade detection |\n| **UEBA** | User and Entity Behavior Analytics — ML-based detection of anomalous behavior baselines |\n| **Sigma** | Open standard for SIEM-agnostic detection rule format, analogous to YARA for network\u002Flog detection |\n| **Hunt Hypothesis** | A testable prediction about adversary presence based on threat intelligence and environmental knowledge |\n\n## Tools & Systems\n\n- **Velociraptor**: Open-source DFIR platform with VQL query language for scalable endpoint hunting across thousands of systems\n- **osquery**: SQL-based OS instrumentation framework for real-time endpoint telemetry queries\n- **MITRE ATT&CK Navigator**: Web-based tool for visualizing ATT&CK coverage and technique prioritization\n- **Zeek (formerly Bro)**: Network traffic analyzer producing structured logs (conn, dns, http, ssl) suitable for hunting\n- **Elastic Security**: EQL (Event Query Language) enables sequence-based hunting for multi-stage attack patterns\n- **Sigma**: Detection rule format with translators for Splunk, QRadar, Sentinel, and Elastic\n\n## Common Pitfalls\n\n- **Confirmation bias**: Starting a hunt expecting to find something and interpreting benign data as malicious. Document null results — they validate controls.\n- **Insufficient data retention**: Many APT techniques require 90+ days of log history to identify slow-and-low patterns. Default retention periods are often too short.\n- **Hunting without baselines**: Cannot identify anomalies without knowing normal. Spend time on baseline documentation before hunting.\n- **Query performance impact**: Broad queries against production SIEM during business hours can degrade analyst workflows. Schedule intensive hunts during off-peak hours.\n- **Ignoring false positives systematically**: Track false positive rates per query. Queries with >80% FP rate should be refined or retired before operationalization.\n",{"name":5,"tags":25,"author":35,"domain":36,"license":15,"version":37,"nist_csf":38,"subdomain":43,"description":44,"mitre_attack":45,"d3fend_techniques":51},[26,27,28,29,30,31,32,33,34],"MITRE-ATT&CK","threat-hunting","APT","Velociraptor","osquery","Zeek","TTP","NIST-CSF","EDR","mahipal","cybersecurity","1.0.0",[39,40,41,42],"ID.RA-01","ID.RA-05","DE.CM-01","DE.AE-02","threat-intelligence","Proactively hunts for Advanced Persistent Threat (APT) activity within enterprise environments using hypothesis-driven searches across endpoint telemetry, network logs, and memory artifacts. Use when conducting scheduled threat hunting cycles, investigating anomalous behavior flagged by UEBA, or validating that known APT TTPs are not present in the environment. Activates for requests involving MITRE ATT&CK, Velociraptor, osquery, Zeek, or threat hunting playbooks.\n",[46,47,48,49,50],"T1591","T1592","T1593","T1589","T1005",[52,53,54,55,56],"File Metadata Consistency Validation","Application Protocol Command Analysis","Identifier Analysis","Content Format Conversion","Message Analysis","main","7540bbccf0c1ded6156a467b02c95b61ad62413f",".agents\u002Fskills\u002Fhunting-advanced-persistent-threats","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":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add NeelakshSaxena\u002FVayu --skill hunting-advanced-persistent-threats",{"tool":70,"command":71},"bunx","bunx skills add NeelakshSaxena\u002FVayu --skill hunting-advanced-persistent-threats",{"tool":73,"command":74},"pnpm","pnpm dlx skills add NeelakshSaxena\u002FVayu --skill hunting-advanced-persistent-threats","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fhunting-advanced-persistent-threats\u002FSKILL.md",true,[78,82,88],{"path":79,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":81,"sourceHtmlUrl":16},"LICENSE","许可证",11255,{"path":83,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fapi-reference.md","REFERENCE","参考文档",2114,"https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fhunting-advanced-persistent-threats\u002Freferences\u002Fapi-reference.md",{"path":89,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":92,"sourceHtmlUrl":93},"scripts\u002Fagent.py","SCRIPT","脚本",7246,"https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fhunting-advanced-persistent-threats\u002Fscripts\u002Fagent.py",[95,102,109,116,123,130],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"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":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"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":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"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":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"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":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":129,"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":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":136,"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",[],[]]