[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6C63FJ2GEBBGZ5XSMV40KXB":3,"skill-same:01M6C63FJ2GEBBGZ5XSMV40KXB":65},{"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":24,"linkOnly":25,"markdownContent":26,"markdownBody":27,"frontMatter":28,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":14,"repositoryHtmlUrl":37,"repositoryHomepageUrl":6,"ownerHtmlUrl":38,"ownerBlogUrl":39,"ownerDescription":6,"updatedAt":40,"install":41,"resources":54},"01M6C63FJ2GEBBGZ5XSMV40KXB","runpodctl",null,"Runpod CLI to manage your GPU workloads.","CoralShades\u002Facm-ai","CoralShades","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F220297585?v=4","01M6C5211QSJHZ8HXSDDWCR507","Coral Shades AI Agency","01M6C52161FNQDRQ0FRR8DAA9D",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Frunpodctl\u002FSKILL.md",[],[5,19,20,21,22,23],"macos","cli","linux","gpu","Bash","2026-11-10 10:12:30",false,"---\nname: runpodctl\ndescription: Runpod CLI to manage your GPU workloads.\nallowed-tools: Bash(runpodctl:*)\ncompatibility: Linux, macOS\nmetadata:\n  author: runpod\n  version: \"2.1\"\nlicense: Apache-2.0\n---\n\n# Runpodctl\n\nManage GPU pods, serverless endpoints, templates, volumes, and models.\n\n> **Spelling:** \"Runpod\" (capital R). Command is `runpodctl` (lowercase).\n\n## Install\n\n```bash\n# Any platform (official installer)\ncurl -sSL https:\u002F\u002Fcli.runpod.net | bash\n\n# macOS (Homebrew)\nbrew install runpod\u002Frunpodctl\u002Frunpodctl\n\n# macOS (manual — universal binary)\nmkdir -p ~\u002F.local\u002Fbin && curl -sL https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpodctl\u002Freleases\u002Flatest\u002Fdownload\u002Frunpodctl-darwin-all.tar.gz | tar xz -C ~\u002F.local\u002Fbin\n\n# Linux\nmkdir -p ~\u002F.local\u002Fbin && curl -sL https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpodctl\u002Freleases\u002Flatest\u002Fdownload\u002Frunpodctl-linux-amd64.tar.gz | tar xz -C ~\u002F.local\u002Fbin\n\n# Windows (PowerShell)\nInvoke-WebRequest -Uri https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpodctl\u002Freleases\u002Flatest\u002Fdownload\u002Frunpodctl-windows-amd64.zip -OutFile runpodctl.zip; Expand-Archive runpodctl.zip -DestinationPath $env:LOCALAPPDATA\\runpodctl; [Environment]::SetEnvironmentVariable('Path', $env:Path + \";$env:LOCALAPPDATA\\runpodctl\", 'User')\n```\n\nEnsure `~\u002F.local\u002Fbin` is on your `PATH` (add `export PATH=\"$HOME\u002F.local\u002Fbin:$PATH\"` to `~\u002F.bashrc` or `~\u002F.zshrc`).\n\n## Quick start\n\n```bash\nrunpodctl doctor                    # First time setup (API key + SSH)\nrunpodctl gpu list                  # See available GPUs\nrunpodctl template search pytorch   # Find a template\nrunpodctl pod create --template-id runpod-torch-v21 --gpu-id \"NVIDIA RTX 4090\"  # Create from template\nrunpodctl pod list                  # List your pods\n```\n\nAPI key: https:\u002F\u002Frunpod.io\u002Fconsole\u002Fuser\u002Fsettings\n\n## Commands\n\n### Pods\n\n```bash\nrunpodctl pod list                                    # List running pods (default, like docker ps)\nrunpodctl pod list --all                              # List all pods including exited\nrunpodctl pod list --status exited                    # Filter by status (RUNNING, EXITED, etc.)\nrunpodctl pod list --since 24h                        # Pods created within last 24 hours\nrunpodctl pod list --created-after 2025-01-15         # Pods created after date\nrunpodctl pod get \u003Cpod-id>                            # Get pod details (includes SSH info)\nrunpodctl pod create --template-id runpod-torch-v21 --gpu-id \"NVIDIA RTX 4090\"  # Create from template\nrunpodctl pod create --image \"runpod\u002Fpytorch:2.1.0-py3.10-cuda11.8.0-devel-ubuntu22.04\" --gpu-id \"NVIDIA RTX 4090\"  # Create with image\nrunpodctl pod create --compute-type cpu --image ubuntu:22.04  # Create CPU pod\nrunpodctl pod start \u003Cpod-id>                          # Start stopped pod\nrunpodctl pod stop \u003Cpod-id>                           # Stop running pod\nrunpodctl pod restart \u003Cpod-id>                        # Restart pod\nrunpodctl pod reset \u003Cpod-id>                          # Reset pod\nrunpodctl pod update \u003Cpod-id> --name \"new\"            # Update pod\nrunpodctl pod delete \u003Cpod-id>                         # Delete pod (aliases: rm, remove)\n```\n\n**List flags:** `--all` \u002F `-a`, `--status`, `--since`, `--created-after`, `--name`, `--compute-type`\n**Get flags:** `--include-machine`, `--include-network-volume`\n\n**Create flags:** `--template-id` (required if no `--image`), `--image` (required if no `--template-id`), `--name`, `--gpu-id`, `--gpu-count`, `--compute-type`, `--ssh` (default true), `--container-disk-in-gb`, `--volume-in-gb`, `--volume-mount-path`, `--ports`, `--env`, `--cloud-type`, `--data-center-ids`, `--global-networking`, `--public-ip`\n\n### Serverless (alias: sls)\n\n```bash\nrunpodctl serverless list                             # List all endpoints\nrunpodctl serverless get \u003Cendpoint-id>                # Get endpoint details\nrunpodctl serverless create --name \"x\" --template-id \"tpl_abc\"  # Create endpoint\nrunpodctl serverless update \u003Cendpoint-id> --workers-max 5       # Update endpoint\nrunpodctl serverless delete \u003Cendpoint-id>             # Delete endpoint\n```\n\n**List flags:** `--include-template`, `--include-workers`\n**Update flags:** `--name`, `--workers-min`, `--workers-max`, `--idle-timeout`, `--scaler-type` (QUEUE_DELAY or REQUEST_COUNT), `--scaler-value`\n**Create flags:** `--name`, `--template-id`, `--gpu-id`, `--gpu-count`, `--compute-type`, `--workers-min`, `--workers-max`, `--data-center-ids`\n\n### Templates (alias: tpl)\n\n```bash\nrunpodctl template list                               # Official + community (first 10)\nrunpodctl template list --type official               # All official templates\nrunpodctl template list --type community              # Community templates (first 10)\nrunpodctl template list --type user                   # Your own templates\nrunpodctl template list --all                         # Everything including user\nrunpodctl template list --limit 50                    # Show 50 templates\nrunpodctl template search pytorch                     # Search for \"pytorch\" templates\nrunpodctl template search comfyui --limit 5           # Search, limit to 5 results\nrunpodctl template search vllm --type official        # Search only official\nrunpodctl template get \u003Ctemplate-id>                  # Get template details (includes README, env, ports)\nrunpodctl template create --name \"x\" --image \"img\"    # Create template\nrunpodctl template create --name \"x\" --image \"img\" --serverless  # Create serverless template\nrunpodctl template update \u003Ctemplate-id> --name \"new\"  # Update template\nrunpodctl template delete \u003Ctemplate-id>               # Delete template\n```\n\n**List flags:** `--type` (official, community, user), `--limit`, `--offset`, `--all`\n**Create flags:** `--name`, `--image`, `--container-disk-in-gb`, `--volume-in-gb`, `--volume-mount-path`, `--ports`, `--env`, `--docker-start-cmd`, `--docker-entrypoint`, `--serverless`, `--readme`\n\n### Network Volumes (alias: nv)\n\n```bash\nrunpodctl network-volume list                         # List all volumes\nrunpodctl network-volume get \u003Cvolume-id>              # Get volume details\nrunpodctl network-volume create --name \"x\" --size 100 --data-center-id \"US-GA-1\"  # Create volume\nrunpodctl network-volume update \u003Cvolume-id> --name \"new\"  # Update volume\nrunpodctl network-volume delete \u003Cvolume-id>           # Delete volume\n```\n\n**Create flags:** `--name`, `--size`, `--data-center-id`\n\n### Models\n\n```bash\nrunpodctl model list                                  # List your models\nrunpodctl model list --all                            # List all models\nrunpodctl model list --name \"llama\"                   # Filter by name\nrunpodctl model list --provider \"meta\"                # Filter by provider\nrunpodctl model add --name \"my-model\" --model-path .\u002Fmodel  # Add model\nrunpodctl model remove --name \"my-model\"              # Remove model\n```\n\n### Registry (alias: reg)\n\n```bash\nrunpodctl registry list                               # List registry auths\nrunpodctl registry get \u003Cregistry-id>                  # Get registry auth\nrunpodctl registry create --name \"x\" --username \"u\" --password \"p\"  # Create registry auth\nrunpodctl registry delete \u003Cregistry-id>               # Delete registry auth\n```\n\n### Info\n\n```bash\nrunpodctl user                                        # Account info and balance (alias: me)\nrunpodctl gpu list                                    # List available GPUs\nrunpodctl gpu list --include-unavailable              # Include unavailable GPUs\nrunpodctl datacenter list                             # List datacenters (alias: dc)\nrunpodctl billing pods                                # Pod billing history\nrunpodctl billing serverless                          # Serverless billing history\nrunpodctl billing network-volume                      # Volume billing history\n```\n\n### SSH\n\n```bash\nrunpodctl ssh info \u003Cpod-id>                           # Get SSH info (command + key, does not connect)\nrunpodctl ssh list-keys                               # List SSH keys\nrunpodctl ssh add-key                                 # Add SSH key\n```\n\n**Agent note:** `ssh info` returns connection details, not an interactive session. If interactive SSH is not available, execute commands remotely via `ssh user@host \"command\"`.\n\n### File Transfer\n\n```bash\nrunpodctl send \u003Cpath>                                 # Send files (outputs code)\nrunpodctl receive \u003Ccode>                              # Receive files using code\n```\n\n### Utilities\n\n```bash\nrunpodctl doctor                                      # Diagnose and fix CLI issues\nrunpodctl update                                      # Update CLI\nrunpodctl version                                     # Show version\nrunpodctl completion bash >> ~\u002F.bashrc                # Install bash completion\nrunpodctl completion zsh >> ~\u002F.zshrc                  # Install zsh completion\n```\n\n## URLs\n\n### Pod URLs\n\nAccess exposed ports on your pod:\n\n```\nhttps:\u002F\u002F\u003Cpod-id>-\u003Cport>.proxy.runpod.net\n```\n\nExample: `https:\u002F\u002Fabc123xyz-8888.proxy.runpod.net`\n\n### Serverless URLs\n\n```\nhttps:\u002F\u002Fapi.runpod.ai\u002Fv2\u002F\u003Cendpoint-id>\u002Frun        # Async request\nhttps:\u002F\u002Fapi.runpod.ai\u002Fv2\u002F\u003Cendpoint-id>\u002Frunsync    # Sync request\nhttps:\u002F\u002Fapi.runpod.ai\u002Fv2\u002F\u003Cendpoint-id>\u002Fhealth     # Health check\nhttps:\u002F\u002Fapi.runpod.ai\u002Fv2\u002F\u003Cendpoint-id>\u002Fstatus\u002F\u003Cjob-id>  # Job status\n```\n","# Runpodctl\n\nManage GPU pods, serverless endpoints, templates, volumes, and models.\n\n> **Spelling:** \"Runpod\" (capital R). Command is `runpodctl` (lowercase).\n\n## Install\n\n```bash\n# Any platform (official installer)\ncurl -sSL https:\u002F\u002Fcli.runpod.net | bash\n\n# macOS (Homebrew)\nbrew install runpod\u002Frunpodctl\u002Frunpodctl\n\n# macOS (manual — universal binary)\nmkdir -p ~\u002F.local\u002Fbin && curl -sL https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpodctl\u002Freleases\u002Flatest\u002Fdownload\u002Frunpodctl-darwin-all.tar.gz | tar xz -C ~\u002F.local\u002Fbin\n\n# Linux\nmkdir -p ~\u002F.local\u002Fbin && curl -sL https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpodctl\u002Freleases\u002Flatest\u002Fdownload\u002Frunpodctl-linux-amd64.tar.gz | tar xz -C ~\u002F.local\u002Fbin\n\n# Windows (PowerShell)\nInvoke-WebRequest -Uri https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpodctl\u002Freleases\u002Flatest\u002Fdownload\u002Frunpodctl-windows-amd64.zip -OutFile runpodctl.zip; Expand-Archive runpodctl.zip -DestinationPath $env:LOCALAPPDATA\\runpodctl; [Environment]::SetEnvironmentVariable('Path', $env:Path + \";$env:LOCALAPPDATA\\runpodctl\", 'User')\n```\n\nEnsure `~\u002F.local\u002Fbin` is on your `PATH` (add `export PATH=\"$HOME\u002F.local\u002Fbin:$PATH\"` to `~\u002F.bashrc` or `~\u002F.zshrc`).\n\n## Quick start\n\n```bash\nrunpodctl doctor                    # First time setup (API key + SSH)\nrunpodctl gpu list                  # See available GPUs\nrunpodctl template search pytorch   # Find a template\nrunpodctl pod create --template-id runpod-torch-v21 --gpu-id \"NVIDIA RTX 4090\"  # Create from template\nrunpodctl pod list                  # List your pods\n```\n\nAPI key: https:\u002F\u002Frunpod.io\u002Fconsole\u002Fuser\u002Fsettings\n\n## Commands\n\n### Pods\n\n```bash\nrunpodctl pod list                                    # List running pods (default, like docker ps)\nrunpodctl pod list --all                              # List all pods including exited\nrunpodctl pod list --status exited                    # Filter by status (RUNNING, EXITED, etc.)\nrunpodctl pod list --since 24h                        # Pods created within last 24 hours\nrunpodctl pod list --created-after 2025-01-15         # Pods created after date\nrunpodctl pod get \u003Cpod-id>                            # Get pod details (includes SSH info)\nrunpodctl pod create --template-id runpod-torch-v21 --gpu-id \"NVIDIA RTX 4090\"  # Create from template\nrunpodctl pod create --image \"runpod\u002Fpytorch:2.1.0-py3.10-cuda11.8.0-devel-ubuntu22.04\" --gpu-id \"NVIDIA RTX 4090\"  # Create with image\nrunpodctl pod create --compute-type cpu --image ubuntu:22.04  # Create CPU pod\nrunpodctl pod start \u003Cpod-id>                          # Start stopped pod\nrunpodctl pod stop \u003Cpod-id>                           # Stop running pod\nrunpodctl pod restart \u003Cpod-id>                        # Restart pod\nrunpodctl pod reset \u003Cpod-id>                          # Reset pod\nrunpodctl pod update \u003Cpod-id> --name \"new\"            # Update pod\nrunpodctl pod delete \u003Cpod-id>                         # Delete pod (aliases: rm, remove)\n```\n\n**List flags:** `--all` \u002F `-a`, `--status`, `--since`, `--created-after`, `--name`, `--compute-type`\n**Get flags:** `--include-machine`, `--include-network-volume`\n\n**Create flags:** `--template-id` (required if no `--image`), `--image` (required if no `--template-id`), `--name`, `--gpu-id`, `--gpu-count`, `--compute-type`, `--ssh` (default true), `--container-disk-in-gb`, `--volume-in-gb`, `--volume-mount-path`, `--ports`, `--env`, `--cloud-type`, `--data-center-ids`, `--global-networking`, `--public-ip`\n\n### Serverless (alias: sls)\n\n```bash\nrunpodctl serverless list                             # List all endpoints\nrunpodctl serverless get \u003Cendpoint-id>                # Get endpoint details\nrunpodctl serverless create --name \"x\" --template-id \"tpl_abc\"  # Create endpoint\nrunpodctl serverless update \u003Cendpoint-id> --workers-max 5       # Update endpoint\nrunpodctl serverless delete \u003Cendpoint-id>             # Delete endpoint\n```\n\n**List flags:** `--include-template`, `--include-workers`\n**Update flags:** `--name`, `--workers-min`, `--workers-max`, `--idle-timeout`, `--scaler-type` (QUEUE_DELAY or REQUEST_COUNT), `--scaler-value`\n**Create flags:** `--name`, `--template-id`, `--gpu-id`, `--gpu-count`, `--compute-type`, `--workers-min`, `--workers-max`, `--data-center-ids`\n\n### Templates (alias: tpl)\n\n```bash\nrunpodctl template list                               # Official + community (first 10)\nrunpodctl template list --type official               # All official templates\nrunpodctl template list --type community              # Community templates (first 10)\nrunpodctl template list --type user                   # Your own templates\nrunpodctl template list --all                         # Everything including user\nrunpodctl template list --limit 50                    # Show 50 templates\nrunpodctl template search pytorch                     # Search for \"pytorch\" templates\nrunpodctl template search comfyui --limit 5           # Search, limit to 5 results\nrunpodctl template search vllm --type official        # Search only official\nrunpodctl template get \u003Ctemplate-id>                  # Get template details (includes README, env, ports)\nrunpodctl template create --name \"x\" --image \"img\"    # Create template\nrunpodctl template create --name \"x\" --image \"img\" --serverless  # Create serverless template\nrunpodctl template update \u003Ctemplate-id> --name \"new\"  # Update template\nrunpodctl template delete \u003Ctemplate-id>               # Delete template\n```\n\n**List flags:** `--type` (official, community, user), `--limit`, `--offset`, `--all`\n**Create flags:** `--name`, `--image`, `--container-disk-in-gb`, `--volume-in-gb`, `--volume-mount-path`, `--ports`, `--env`, `--docker-start-cmd`, `--docker-entrypoint`, `--serverless`, `--readme`\n\n### Network Volumes (alias: nv)\n\n```bash\nrunpodctl network-volume list                         # List all volumes\nrunpodctl network-volume get \u003Cvolume-id>              # Get volume details\nrunpodctl network-volume create --name \"x\" --size 100 --data-center-id \"US-GA-1\"  # Create volume\nrunpodctl network-volume update \u003Cvolume-id> --name \"new\"  # Update volume\nrunpodctl network-volume delete \u003Cvolume-id>           # Delete volume\n```\n\n**Create flags:** `--name`, `--size`, `--data-center-id`\n\n### Models\n\n```bash\nrunpodctl model list                                  # List your models\nrunpodctl model list --all                            # List all models\nrunpodctl model list --name \"llama\"                   # Filter by name\nrunpodctl model list --provider \"meta\"                # Filter by provider\nrunpodctl model add --name \"my-model\" --model-path .\u002Fmodel  # Add model\nrunpodctl model remove --name \"my-model\"              # Remove model\n```\n\n### Registry (alias: reg)\n\n```bash\nrunpodctl registry list                               # List registry auths\nrunpodctl registry get \u003Cregistry-id>                  # Get registry auth\nrunpodctl registry create --name \"x\" --username \"u\" --password \"p\"  # Create registry auth\nrunpodctl registry delete \u003Cregistry-id>               # Delete registry auth\n```\n\n### Info\n\n```bash\nrunpodctl user                                        # Account info and balance (alias: me)\nrunpodctl gpu list                                    # List available GPUs\nrunpodctl gpu list --include-unavailable              # Include unavailable GPUs\nrunpodctl datacenter list                             # List datacenters (alias: dc)\nrunpodctl billing pods                                # Pod billing history\nrunpodctl billing serverless                          # Serverless billing history\nrunpodctl billing network-volume                      # Volume billing history\n```\n\n### SSH\n\n```bash\nrunpodctl ssh info \u003Cpod-id>                           # Get SSH info (command + key, does not connect)\nrunpodctl ssh list-keys                               # List SSH keys\nrunpodctl ssh add-key                                 # Add SSH key\n```\n\n**Agent note:** `ssh info` returns connection details, not an interactive session. If interactive SSH is not available, execute commands remotely via `ssh user@host \"command\"`.\n\n### File Transfer\n\n```bash\nrunpodctl send \u003Cpath>                                 # Send files (outputs code)\nrunpodctl receive \u003Ccode>                              # Receive files using code\n```\n\n### Utilities\n\n```bash\nrunpodctl doctor                                      # Diagnose and fix CLI issues\nrunpodctl update                                      # Update CLI\nrunpodctl version                                     # Show version\nrunpodctl completion bash >> ~\u002F.bashrc                # Install bash completion\nrunpodctl completion zsh >> ~\u002F.zshrc                  # Install zsh completion\n```\n\n## URLs\n\n### Pod URLs\n\nAccess exposed ports on your pod:\n\n```\nhttps:\u002F\u002F\u003Cpod-id>-\u003Cport>.proxy.runpod.net\n```\n\nExample: `https:\u002F\u002Fabc123xyz-8888.proxy.runpod.net`\n\n### Serverless URLs\n\n```\nhttps:\u002F\u002Fapi.runpod.ai\u002Fv2\u002F\u003Cendpoint-id>\u002Frun        # Async request\nhttps:\u002F\u002Fapi.runpod.ai\u002Fv2\u002F\u003Cendpoint-id>\u002Frunsync    # Sync request\nhttps:\u002F\u002Fapi.runpod.ai\u002Fv2\u002F\u003Cendpoint-id>\u002Fhealth     # Health check\nhttps:\u002F\u002Fapi.runpod.ai\u002Fv2\u002F\u003Cendpoint-id>\u002Fstatus\u002F\u003Cjob-id>  # Job status\n```\n",{"name":5,"license":15,"metadata":29,"description":7,"allowed-tools":32,"compatibility":33},{"author":30,"version":31},"runpod","2.1","Bash(runpodctl:*)","Linux, macOS","main","1ca81b0a7de199942400f965edd4d7544077ac5d",".qwen\u002Fskills\u002Frunpodctl","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai","https:\u002F\u002Fgithub.com\u002FCoralShades","coralshades.com.au","2026-04-18 00:45:07",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":53},[43,46,49],{"tool":44,"command":45},"npx","npx skills add CoralShades\u002Facm-ai --skill runpodctl",{"tool":47,"command":48},"bunx","bunx skills add CoralShades\u002Facm-ai --skill runpodctl",{"tool":50,"command":51},"pnpm","pnpm dlx skills add CoralShades\u002Facm-ai --skill runpodctl","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Frunpodctl\u002FSKILL.md",true,[55,61],{"path":56,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":59,"sourceHtmlUrl":60},"SOURCE.md","REFERENCE","参考文档",191,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fai-crypto\u002Fclawplaza-task-marketplace\u002FSOURCE.md",{"path":62,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":63,"sourceHtmlUrl":64},"TRUST.auto.yaml",2217,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fai-crypto\u002Fclawplaza-task-marketplace\u002FTRUST.auto.yaml",[66,91,107,129,139,156],{"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":70,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":78,"publishedAt":24},"01M6C63HKXA890HHV47WBAX0TB","uncodixfy","Prevents generic AI\u002FCodex UI patterns when generating frontend code. Use this skill whenever generating HTML, CSS, React, Vue, Svelte, or any frontend UI code to enforce clean, human-designed aesthetics inspired by Linear, Raycast, Stripe, and GitHub instead of typical AI-generated UI.","MIT","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Funcodixfy\u002FSKILL.md",[73],{"categoryNo":74,"categoryName":75,"taxonomyType":76,"taxonomyTypeDesc":77},"01JBSEEDCAT000000000000009","前端开发","SCENARIO","使用场景",[68,79,80,81,82,83,84,85,86,87,88,89,90],"html","use","generated","vue","ui","linear","code","frontend","css","github","codex","react",{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":70,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":24},"01M6C63DPAV46TFVQ01SFYPJ7X","langgraph-persistence","INVOKE THIS SKILL when your LangGraph needs to persist state, remember conversations, travel through history, or configure subgraph checkpointer scoping. Covers checkpointers, thread_id, time travel, Store, and subgraph persistence modes.","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Flanggraph-persistence\u002FSKILL.md",[],[98,99,100,101,102,103,104,105,106],"persistence","langgraph","langgraph persistence","configure","remember","state","history","scoping","travel",{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":70,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":118,"publishedAt":24},"01M6C63BNS9CQEBTB8RNSSBFPA","langgraph-human-in-the-loop","INVOKE THIS SKILL when implementing human-in-the-loop patterns, pausing for approval, or handling errors in LangGraph. Covers interrupt(), Command(resume=...), approval\u002Fvalidation workflows, and the 4-tier error handling strategy.","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Flanggraph-human-in-the-loop\u002FSKILL.md",[113],{"categoryNo":114,"categoryName":115,"taxonomyType":116,"taxonomyTypeDesc":117},"01JBSEEDCAT000000000000038","人力资源","PROFESSION","适用职业",[119,99,120,121,122,123,124,125,126,127,128],"loop","langgraph human in the loop","strategy","validation","approval","resume","command","workflows","error handling","human-in-the-loop",{"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":70,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":24},"01M6C639GVYZFX3NFPV5FBDR4F","langgraph-fundamentals","INVOKE THIS SKILL when writing ANY LangGraph code. Covers StateGraph, state schemas, nodes, edges, Command, Send, invoke, streaming, and error handling.","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Flanggraph-fundamentals\u002FSKILL.md",[],[136,99,137,85,127,103,138,125],"langgraph fundamentals","writing","streaming",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":70,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":145,"publishedAt":24},"01M6C6375N34YX2GZ3SD3R7XR2","langchain-rag","INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. Covers document loaders, RecursiveCharacterTextSplitter, embeddings (OpenAI), and vector stores (Chroma, FAISS, Pinecone).","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Flangchain-rag\u002FSKILL.md",[],[146,147,148,149,150,151,152,153,154,155],"langchain rag","langchain","rag","vector stores","openai","vector","embeddings","system","chroma","faiss",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":70,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":162,"publishedAt":24},"01M6C63579N74QKMQQF41YA9EF","langchain-middleware","INVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output. Covers HumanInTheLoopMiddleware for human approval of dangerous tool calls, creating custom middleware with hooks, Command resume patterns, and structured output with Pydantic\u002FZod.","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Flangchain-middleware\u002FSKILL.md",[],[163,147,128,119,164,165,125,123,166,124,167],"langchain middleware","tool","zod","hooks","Pydantic"]