[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74ES61WQBAHKCZ9Y7RTHS1B":3,"skill-same:01M74ES61WQBAHKCZ9Y7RTHS1B":54},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":13,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M74ES61WQBAHKCZ9Y7RTHS1B","toolhive-cli-user",null,"Guide for using ToolHive CLI (thv) to run and manage MCP servers and skills. Use when running, listing, stopping, building, or configuring MCP servers locally. Covers server lifecycle, registry browsing, secrets management, client registration, groups, container builds, exports, permissions, network isolation, authentication, and skill management (install, uninstall, list, info, build, push, validate). NOT for Kubernetes operator usage or ToolHive development\u002Fcontributing.","lzy18001500226\u002FMoSim","lzy18001500226","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F152623587?v=4","01M71ZMEX36NK05B642131DEEK","01M71ZMEXSMX72KPVNJ572G0CM",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Flzy18001500226\u002FMoSim\u002Fblob\u002Fmain\u002FReferences\u002FAgent\u002FGateway\u002Ftoolhive\u002Fskills\u002Ftoolhive-cli-user\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: toolhive-cli-user\ndescription: >-\n  Guide for using ToolHive CLI (thv) to run and manage MCP servers and skills.\n  Use when running, listing, stopping, building, or configuring MCP servers locally.\n  Covers server lifecycle, registry browsing, secrets management, client registration,\n  groups, container builds, exports, permissions, network isolation, authentication,\n  and skill management (install, uninstall, list, info, build, push, validate).\n  NOT for Kubernetes operator usage or ToolHive development\u002Fcontributing.\nversion: 0.3.0\nlicense: Apache-2.0\n---\n\n# ToolHive CLI User Guide\n\n## Prerequisites\n\n- **Container Runtime**: Docker, Podman, Colima, or Rancher Desktop (with dockerd\u002Fmoby)\n- **ToolHive CLI**: Install with `brew install stacklok\u002Ftap\u002Fthv` (macOS\u002FLinux) or `winget install stacklok.thv` (Windows)\n\nVerify: `thv version`\n\n## Quick Start\n\n```bash\nthv run filesystem      # Run server from registry\nthv list                # List running servers\nthv status filesystem   # Detailed server info\nthv logs filesystem     # View logs\nthv stop filesystem     # Stop server\nthv rm filesystem       # Remove server\n```\n\n## Running MCP Servers\n\nFive input methods: registry name, container image, protocol scheme (`uvx:\u002F\u002F`, `npx:\u002F\u002F`, `go:\u002F\u002F`), exported config (`--from-config`), or remote URL.\n\n```bash\nthv run filesystem                                          # Registry\nthv run ghcr.io\u002Fgithub\u002Fgithub-mcp-server:latest -- \u003Cargs>   # Container image\nthv run uvx:\u002F\u002Fmcp-server-git                                # Python (uvx)\nthv run npx:\u002F\u002F@modelcontextprotocol\u002Fserver-filesystem       # Node.js (npx)\nthv run go:\u002F\u002Fgithub.com\u002Fexample\u002Fmcp-server                  # Go\nthv run --from-config .\u002Fconfig.json                         # Exported config\nthv run https:\u002F\u002Fapi.example.com\u002Fmcp --name my-remote        # Remote URL\n```\n\nFor all flags, authentication options, and telemetry configuration, see [COMMANDS.md](references\u002FCOMMANDS.md#thv-run).\nFor detailed usage patterns, see [EXAMPLES.md](references\u002FEXAMPLES.md).\n\n## Managing Servers\n\n```bash\nthv list                          # Running servers\nthv list --all                    # Include stopped\nthv list --format json            # JSON output\nthv list --format mcpservers      # MCP client config format\nthv list --group production       # Filter by group\n\nthv status filesystem             # Detailed server info (URL, port, transport, uptime)\nthv status filesystem --format json\n\nthv stop filesystem github        # Stop specific servers\nthv stop --all                    # Stop all\n\nthv start filesystem              # Resume stopped server\nthv start --all                   # Start all stopped servers\nthv start --group development     # Start all in group\nthv restart filesystem            # Alias for start (backward compat)\n\nthv rm filesystem github          # Remove servers\nthv rm --all                      # Remove all\n\nthv logs filesystem               # Container logs\nthv logs filesystem --follow      # Real-time\nthv logs filesystem --proxy       # Proxy logs\nthv logs prune                    # Clean orphaned logs\n```\n\nNote: Remote servers trigger fresh OAuth authentication on start.\n\n## Registry Operations\n\n```bash\nthv registry list                    # List all servers\nthv registry list --format json      # JSON output\nthv search github                    # Search by keyword\nthv registry info github             # Detailed server info\n```\n\nCustom registry:\n```bash\nthv config set-registry https:\u002F\u002Fmy-registry.example.com  # Remote\nthv config set-registry \u002Fpath\u002Fto\u002Flocal\u002Fregistry          # Local\nthv config get-registry                                   # View current\nthv config unset-registry                                 # Reset to default\n```\n\n## Group Management\n\nAll servers are assigned to `default` group unless specified.\n\n```bash\nthv group create development           # Create group\nthv group list                         # List groups\nthv run fetch --group development      # Assign server to group\nthv group run kubernetes               # Run all servers from registry group\nthv group rm development               # Remove group (servers move to default)\nthv group rm development --with-workloads  # Remove group AND its servers\n```\n\nEach server belongs to one group. To run same server in multiple groups, create uniquely named instances.\n\n## Secrets Management\n\nSetup is required before use: `thv secret setup` (interactive provider selection).\n\n**Providers:** Encrypted (AES-256-GCM, password in OS keyring) or 1Password (read-only, requires `OP_SERVICE_ACCOUNT_TOKEN`).\n\n```bash\nthv secret set MY_API_KEY              # Interactive input\necho \"value\" | thv secret set MY_KEY   # Piped input\nthv secret list                        # List all\nthv secret get MY_API_KEY              # Retrieve\nthv secret delete MY_API_KEY           # Remove\n```\n\nUsing secrets with servers:\n```bash\nthv run github --secret GITHUB_TOKEN,target=GITHUB_PERSONAL_ACCESS_TOKEN\nthv run server --secret KEY1,target=ENV1 --secret KEY2,target=ENV2\n```\n\n## Client Configuration\n\n```bash\nthv client status              # Check all supported clients\nthv client setup               # Interactive setup\nthv client register claude-code --group development  # Register with group\nthv client list-registered     # List registered\nthv client remove              # Remove client\n```\n\n## Permissions and Network Isolation\n\n**Permission profiles** control what a container can access (filesystem, network):\n\n```bash\nthv run myserver --permission-profile network          # Network access only\nthv run myserver --permission-profile none             # No extra permissions\nthv run myserver --permission-profile .\u002Fcustom.json    # Custom profile (JSON)\n```\n\nRegistry servers include a default profile. Without registry info, default is `network`.\n\n**Network isolation** restricts outbound traffic to an allowlist via an egress proxy:\n\n```bash\nthv run myserver --isolate-network    # Block all outbound except allowlisted hosts\n```\n\n**Volume mounts** for filesystem access:\n\n```bash\nthv run filesystem -v \u002Fhome\u002Fuser\u002Fprojects:\u002Fworkspace:ro    # Read-only mount\n```\n\n**.thvignore** hides sensitive files from volume mounts using gitignore-style patterns. Place `.thvignore` in mounted directories or globally at `~\u002F.config\u002Ftoolhive\u002Fthvignore`. Disable global patterns with `--ignore-globally=false`.\n\nFor detailed examples, see [EXAMPLES.md](references\u002FEXAMPLES.md#permissions-and-network-isolation).\n\n## Building, Export, and Tool Overrides\n\n```bash\nthv build uvx:\u002F\u002Fmcp-server-git                                      # Build container\nthv build --tag my-registry\u002Fserver:v1.0 npx:\u002F\u002Fpackage               # Custom tag\nthv build --dry-run --output Dockerfile.mcp uvx:\u002F\u002Fmcp-server-git    # Dockerfile only\n\nthv export my-server .\u002Fconfig.json              # Export JSON\nthv export my-server .\u002Fserver.yaml --format k8s # Export Kubernetes YAML\nthv run --from-config .\u002Fconfig.json             # Import config\n```\n\nFor tool overrides, see [EXAMPLES.md](references\u002FEXAMPLES.md#tool-filtering-and-overrides).\n\n## Skills Management\n\nRequires `thv serve` to be running. Skills have two scopes: `user` (global, default) and `project` (local to a project root).\n\n```bash\nthv skill install my-skill                              # Install from registry\nthv skill install ghcr.io\u002Forg\u002Fskill:v1.0                # Install by OCI reference\nthv skill install my-skill --clients claude-code          # Target specific client(s)\nthv skill install my-skill --scope project --project-root .  # Project-scoped\nthv skill install my-skill --group development           # Add to group\nthv skill install my-skill --force                       # Overwrite existing\n\nthv skill list                                           # List all installed\nthv skill ls --scope user --format json                  # Filter and format\nthv skill ls --client claude-code --group dev            # Filter by client\u002Fgroup\n\nthv skill info my-skill                                  # Show details\nthv skill info my-skill --format json                    # JSON output\n\nthv skill uninstall my-skill                             # Remove skill\nthv skill uninstall my-skill --scope project --project-root .\n\nthv skill validate .\u002Fmy-skill-dir                        # Check skill definition\nthv skill build .\u002Fmy-skill-dir                           # Build OCI artifact\nthv skill build .\u002Fmy-skill-dir --tag ghcr.io\u002Forg\u002Fskill:v1.0\nthv skill push ghcr.io\u002Forg\u002Fskill:v1.0                   # Push to registry\n```\n\nFor all flags and detailed examples, see [COMMANDS.md](references\u002FCOMMANDS.md#skill-commands) and [EXAMPLES.md](references\u002FEXAMPLES.md#skills-management-examples).\n\n## Debugging\n\n```bash\nthv inspector filesystem                        # MCP Inspector UI\nthv mcp list tools --server filesystem\nthv mcp list resources --server filesystem\nthv mcp list prompts --server filesystem\nthv mcp call read_file --server filesystem --args '{\"path\":\"\u002Fetc\u002Fhosts\"}'  # Invoke a tool\nthv runtime check                               # Verify container runtime\n```\n\nFor tool invocation patterns (file args, stdin, JSON output, error handling), see [EXAMPLES.md](references\u002FEXAMPLES.md#invoke-a-tool).\n\n## Guardrails\n\n- NEVER use `docker rm` or `podman rm` on ToolHive-managed containers -- always use `thv rm` for proper cleanup.\n- NEVER pass secrets as `-e SECRET=value` -- use `--secret` with managed secrets instead.\n- Confirm destructive operations (`thv rm --all`, `thv stop --all`, `thv group rm --with-workloads`) with the user before running.\n- Skill commands require `thv serve` to be running. If a skill command fails with a connection error, suggest starting `thv serve` first.\n- If the user asks about Kubernetes deployment, this skill does not cover the operator -- direct them accordingly.\n\n## Error Handling\n\n| Symptom | Cause | Recovery |\n|---------|-------|----------|\n| Container can't reach localhost | Bridge network isolation | Use `host.docker.internal` (Docker Desktop), `host.containers.internal` (Podman), `172.17.0.1` (Linux) |\n| Port already in use | Another server on same port | Use `--proxy-port \u003Cdifferent-port>` |\n| Permission denied on volume | Mount path or profile issue | Check volume mount paths and permission profiles (`--permission-profile`) |\n| Container runtime not found | No runtime or socket issue | Run `thv runtime check`; override socket with `TOOLHIVE_PODMAN_SOCKET`, `TOOLHIVE_COLIMA_SOCKET`, or `TOOLHIVE_DOCKER_SOCKET` |\n| Secret operation fails | Provider not configured | Run `thv secret setup` first |\n| Image pull fails | Network or auth issue | Check network connectivity; for private registries, ensure credentials are configured |\n| Remote auth token expired | OAuth token lifetime exceeded | Restart the server (`thv restart`) to trigger fresh authentication |\n| Sensitive files exposed in mount | No `.thvignore` configured | Add `.thvignore` in mounted directory or globally at `~\u002F.config\u002Ftoolhive\u002Fthvignore` |\n| Skill command fails with connection error | `thv serve` not running | Start `thv serve` before using skill commands |\n| Skill validation fails | Invalid SKILL.md or directory structure | Run `thv skill validate .\u002Fpath` and fix reported errors |\n\n## Global Options\n\n- `--debug`: Verbose output\n- `-h, --help`: Command help\n\nContainer runtime auto-detected: Podman -> Colima -> Docker.\n\n## See Also\n\n- [COMMANDS.md](references\u002FCOMMANDS.md) - Complete command reference with all flags\n- [EXAMPLES.md](references\u002FEXAMPLES.md) - Detailed usage examples and workflows\n","# ToolHive CLI User Guide\n\n## Prerequisites\n\n- **Container Runtime**: Docker, Podman, Colima, or Rancher Desktop (with dockerd\u002Fmoby)\n- **ToolHive CLI**: Install with `brew install stacklok\u002Ftap\u002Fthv` (macOS\u002FLinux) or `winget install stacklok.thv` (Windows)\n\nVerify: `thv version`\n\n## Quick Start\n\n```bash\nthv run filesystem      # Run server from registry\nthv list                # List running servers\nthv status filesystem   # Detailed server info\nthv logs filesystem     # View logs\nthv stop filesystem     # Stop server\nthv rm filesystem       # Remove server\n```\n\n## Running MCP Servers\n\nFive input methods: registry name, container image, protocol scheme (`uvx:\u002F\u002F`, `npx:\u002F\u002F`, `go:\u002F\u002F`), exported config (`--from-config`), or remote URL.\n\n```bash\nthv run filesystem                                          # Registry\nthv run ghcr.io\u002Fgithub\u002Fgithub-mcp-server:latest -- \u003Cargs>   # Container image\nthv run uvx:\u002F\u002Fmcp-server-git                                # Python (uvx)\nthv run npx:\u002F\u002F@modelcontextprotocol\u002Fserver-filesystem       # Node.js (npx)\nthv run go:\u002F\u002Fgithub.com\u002Fexample\u002Fmcp-server                  # Go\nthv run --from-config .\u002Fconfig.json                         # Exported config\nthv run https:\u002F\u002Fapi.example.com\u002Fmcp --name my-remote        # Remote URL\n```\n\nFor all flags, authentication options, and telemetry configuration, see [COMMANDS.md](references\u002FCOMMANDS.md#thv-run).\nFor detailed usage patterns, see [EXAMPLES.md](references\u002FEXAMPLES.md).\n\n## Managing Servers\n\n```bash\nthv list                          # Running servers\nthv list --all                    # Include stopped\nthv list --format json            # JSON output\nthv list --format mcpservers      # MCP client config format\nthv list --group production       # Filter by group\n\nthv status filesystem             # Detailed server info (URL, port, transport, uptime)\nthv status filesystem --format json\n\nthv stop filesystem github        # Stop specific servers\nthv stop --all                    # Stop all\n\nthv start filesystem              # Resume stopped server\nthv start --all                   # Start all stopped servers\nthv start --group development     # Start all in group\nthv restart filesystem            # Alias for start (backward compat)\n\nthv rm filesystem github          # Remove servers\nthv rm --all                      # Remove all\n\nthv logs filesystem               # Container logs\nthv logs filesystem --follow      # Real-time\nthv logs filesystem --proxy       # Proxy logs\nthv logs prune                    # Clean orphaned logs\n```\n\nNote: Remote servers trigger fresh OAuth authentication on start.\n\n## Registry Operations\n\n```bash\nthv registry list                    # List all servers\nthv registry list --format json      # JSON output\nthv search github                    # Search by keyword\nthv registry info github             # Detailed server info\n```\n\nCustom registry:\n```bash\nthv config set-registry https:\u002F\u002Fmy-registry.example.com  # Remote\nthv config set-registry \u002Fpath\u002Fto\u002Flocal\u002Fregistry          # Local\nthv config get-registry                                   # View current\nthv config unset-registry                                 # Reset to default\n```\n\n## Group Management\n\nAll servers are assigned to `default` group unless specified.\n\n```bash\nthv group create development           # Create group\nthv group list                         # List groups\nthv run fetch --group development      # Assign server to group\nthv group run kubernetes               # Run all servers from registry group\nthv group rm development               # Remove group (servers move to default)\nthv group rm development --with-workloads  # Remove group AND its servers\n```\n\nEach server belongs to one group. To run same server in multiple groups, create uniquely named instances.\n\n## Secrets Management\n\nSetup is required before use: `thv secret setup` (interactive provider selection).\n\n**Providers:** Encrypted (AES-256-GCM, password in OS keyring) or 1Password (read-only, requires `OP_SERVICE_ACCOUNT_TOKEN`).\n\n```bash\nthv secret set MY_API_KEY              # Interactive input\necho \"value\" | thv secret set MY_KEY   # Piped input\nthv secret list                        # List all\nthv secret get MY_API_KEY              # Retrieve\nthv secret delete MY_API_KEY           # Remove\n```\n\nUsing secrets with servers:\n```bash\nthv run github --secret GITHUB_TOKEN,target=GITHUB_PERSONAL_ACCESS_TOKEN\nthv run server --secret KEY1,target=ENV1 --secret KEY2,target=ENV2\n```\n\n## Client Configuration\n\n```bash\nthv client status              # Check all supported clients\nthv client setup               # Interactive setup\nthv client register claude-code --group development  # Register with group\nthv client list-registered     # List registered\nthv client remove              # Remove client\n```\n\n## Permissions and Network Isolation\n\n**Permission profiles** control what a container can access (filesystem, network):\n\n```bash\nthv run myserver --permission-profile network          # Network access only\nthv run myserver --permission-profile none             # No extra permissions\nthv run myserver --permission-profile .\u002Fcustom.json    # Custom profile (JSON)\n```\n\nRegistry servers include a default profile. Without registry info, default is `network`.\n\n**Network isolation** restricts outbound traffic to an allowlist via an egress proxy:\n\n```bash\nthv run myserver --isolate-network    # Block all outbound except allowlisted hosts\n```\n\n**Volume mounts** for filesystem access:\n\n```bash\nthv run filesystem -v \u002Fhome\u002Fuser\u002Fprojects:\u002Fworkspace:ro    # Read-only mount\n```\n\n**.thvignore** hides sensitive files from volume mounts using gitignore-style patterns. Place `.thvignore` in mounted directories or globally at `~\u002F.config\u002Ftoolhive\u002Fthvignore`. Disable global patterns with `--ignore-globally=false`.\n\nFor detailed examples, see [EXAMPLES.md](references\u002FEXAMPLES.md#permissions-and-network-isolation).\n\n## Building, Export, and Tool Overrides\n\n```bash\nthv build uvx:\u002F\u002Fmcp-server-git                                      # Build container\nthv build --tag my-registry\u002Fserver:v1.0 npx:\u002F\u002Fpackage               # Custom tag\nthv build --dry-run --output Dockerfile.mcp uvx:\u002F\u002Fmcp-server-git    # Dockerfile only\n\nthv export my-server .\u002Fconfig.json              # Export JSON\nthv export my-server .\u002Fserver.yaml --format k8s # Export Kubernetes YAML\nthv run --from-config .\u002Fconfig.json             # Import config\n```\n\nFor tool overrides, see [EXAMPLES.md](references\u002FEXAMPLES.md#tool-filtering-and-overrides).\n\n## Skills Management\n\nRequires `thv serve` to be running. Skills have two scopes: `user` (global, default) and `project` (local to a project root).\n\n```bash\nthv skill install my-skill                              # Install from registry\nthv skill install ghcr.io\u002Forg\u002Fskill:v1.0                # Install by OCI reference\nthv skill install my-skill --clients claude-code          # Target specific client(s)\nthv skill install my-skill --scope project --project-root .  # Project-scoped\nthv skill install my-skill --group development           # Add to group\nthv skill install my-skill --force                       # Overwrite existing\n\nthv skill list                                           # List all installed\nthv skill ls --scope user --format json                  # Filter and format\nthv skill ls --client claude-code --group dev            # Filter by client\u002Fgroup\n\nthv skill info my-skill                                  # Show details\nthv skill info my-skill --format json                    # JSON output\n\nthv skill uninstall my-skill                             # Remove skill\nthv skill uninstall my-skill --scope project --project-root .\n\nthv skill validate .\u002Fmy-skill-dir                        # Check skill definition\nthv skill build .\u002Fmy-skill-dir                           # Build OCI artifact\nthv skill build .\u002Fmy-skill-dir --tag ghcr.io\u002Forg\u002Fskill:v1.0\nthv skill push ghcr.io\u002Forg\u002Fskill:v1.0                   # Push to registry\n```\n\nFor all flags and detailed examples, see [COMMANDS.md](references\u002FCOMMANDS.md#skill-commands) and [EXAMPLES.md](references\u002FEXAMPLES.md#skills-management-examples).\n\n## Debugging\n\n```bash\nthv inspector filesystem                        # MCP Inspector UI\nthv mcp list tools --server filesystem\nthv mcp list resources --server filesystem\nthv mcp list prompts --server filesystem\nthv mcp call read_file --server filesystem --args '{\"path\":\"\u002Fetc\u002Fhosts\"}'  # Invoke a tool\nthv runtime check                               # Verify container runtime\n```\n\nFor tool invocation patterns (file args, stdin, JSON output, error handling), see [EXAMPLES.md](references\u002FEXAMPLES.md#invoke-a-tool).\n\n## Guardrails\n\n- NEVER use `docker rm` or `podman rm` on ToolHive-managed containers -- always use `thv rm` for proper cleanup.\n- NEVER pass secrets as `-e SECRET=value` -- use `--secret` with managed secrets instead.\n- Confirm destructive operations (`thv rm --all`, `thv stop --all`, `thv group rm --with-workloads`) with the user before running.\n- Skill commands require `thv serve` to be running. If a skill command fails with a connection error, suggest starting `thv serve` first.\n- If the user asks about Kubernetes deployment, this skill does not cover the operator -- direct them accordingly.\n\n## Error Handling\n\n| Symptom | Cause | Recovery |\n|---------|-------|----------|\n| Container can't reach localhost | Bridge network isolation | Use `host.docker.internal` (Docker Desktop), `host.containers.internal` (Podman), `172.17.0.1` (Linux) |\n| Port already in use | Another server on same port | Use `--proxy-port \u003Cdifferent-port>` |\n| Permission denied on volume | Mount path or profile issue | Check volume mount paths and permission profiles (`--permission-profile`) |\n| Container runtime not found | No runtime or socket issue | Run `thv runtime check`; override socket with `TOOLHIVE_PODMAN_SOCKET`, `TOOLHIVE_COLIMA_SOCKET`, or `TOOLHIVE_DOCKER_SOCKET` |\n| Secret operation fails | Provider not configured | Run `thv secret setup` first |\n| Image pull fails | Network or auth issue | Check network connectivity; for private registries, ensure credentials are configured |\n| Remote auth token expired | OAuth token lifetime exceeded | Restart the server (`thv restart`) to trigger fresh authentication |\n| Sensitive files exposed in mount | No `.thvignore` configured | Add `.thvignore` in mounted directory or globally at `~\u002F.config\u002Ftoolhive\u002Fthvignore` |\n| Skill command fails with connection error | `thv serve` not running | Start `thv serve` before using skill commands |\n| Skill validation fails | Invalid SKILL.md or directory structure | Run `thv skill validate .\u002Fpath` and fix reported errors |\n\n## Global Options\n\n- `--debug`: Verbose output\n- `-h, --help`: Command help\n\nContainer runtime auto-detected: Podman -> Colima -> Docker.\n\n## See Also\n\n- [COMMANDS.md](references\u002FCOMMANDS.md) - Complete command reference with all flags\n- [EXAMPLES.md](references\u002FEXAMPLES.md) - Detailed usage examples and workflows\n",{"name":5,"license":14,"version":23,"description":7},"0.3.0","main","e0ec177d00f087cb04e90206b2f7d3aa2f5a1350","References\u002FAgent\u002FGateway\u002Ftoolhive\u002Fskills\u002Ftoolhive-cli-user","https:\u002F\u002Fgithub.com\u002Flzy18001500226\u002FMoSim","https:\u002F\u002Fgithub.com\u002Flzy18001500226","2026-08-31 23:29:00",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add lzy18001500226\u002FMoSim --skill toolhive-cli-user",{"tool":36,"command":37},"bunx","bunx skills add lzy18001500226\u002FMoSim --skill toolhive-cli-user",{"tool":39,"command":40},"pnpm","pnpm dlx skills add lzy18001500226\u002FMoSim --skill toolhive-cli-user","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flzy18001500226\u002FMoSim\u002Fblob\u002Fmain\u002FReferences\u002FAgent\u002FGateway\u002Ftoolhive\u002Fskills\u002Ftoolhive-cli-user\u002FSKILL.md",true,[44,50],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"references\u002FCOMMANDS.md","REFERENCE","参考文档",12294,"https:\u002F\u002Fgithub.com\u002Flzy18001500226\u002FMoSim\u002Fblob\u002Fmain\u002FReferences\u002FAgent\u002FGateway\u002Ftoolhive\u002Fskills\u002Ftoolhive-cli-user\u002Freferences\u002FCOMMANDS.md",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002FEXAMPLES.md",12352,"https:\u002F\u002Fgithub.com\u002Flzy18001500226\u002FMoSim\u002Fblob\u002Fmain\u002FReferences\u002FAgent\u002FGateway\u002Ftoolhive\u002Fskills\u002Ftoolhive-cli-user\u002Freferences\u002FEXAMPLES.md",[55,64,72,80,88,96],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":59,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":63},"01M78RK6JGRPTD3TDSMTQWDQ9P","skill-installer","Install Codex skills into $CODEX_HOME\u002Fskills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).","https:\u002F\u002Fgithub.com\u002Flzy18001500226\u002FMoSim\u002Fblob\u002Fmain\u002Fsrc\u002FAgent\u002Fcodex-main\u002Fcodex-rs\u002Fskills\u002Fsrc\u002Fassets\u002Fsamples\u002Fskill-installer\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Flzy18001500226\u002FMoSim\u002Fblob\u002Fmain\u002Fsrc\u002FAgent\u002Fcodex-main\u002Fcodex-rs\u002Fskills\u002Fsrc\u002Fassets\u002Fsamples\u002Fskill-installer\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":68,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":63},"01M78RK29KVRDQXSMVZX1GQTJN","skill-creator","Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.","https:\u002F\u002Fgithub.com\u002Flzy18001500226\u002FMoSim\u002Fblob\u002Fmain\u002Fsrc\u002FAgent\u002Fcodex-main\u002Fcodex-rs\u002Fskills\u002Fsrc\u002Fassets\u002Fsamples\u002Fskill-creator\u002Flicense.txt","https:\u002F\u002Fgithub.com\u002Flzy18001500226\u002FMoSim\u002Fblob\u002Fmain\u002Fsrc\u002FAgent\u002Fcodex-main\u002Fcodex-rs\u002Fskills\u002Fsrc\u002Fassets\u002Fsamples\u002Fskill-creator\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":76,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":63},"01M78RJPF3210Y5DA9VJ6JMMG6","openai-docs","Use for Codex models\u002Fpricing, scheduled tasks, skills, settings, setup, troubleshooting, customization, automations, and self-knowledge—including 'you,' 'your,' 'this app,' or 'this coding agent' when they refer to Codex—and for OpenAI APIs\u002Fproducts and ChatGPT Work. Also use for model choice\u002Fmigration, prompting, SDKs, Responses, Realtime, agents, evals, and Chat\u002FWork\u002FCodex comparisons. Do not use for generic app\u002Fsoftware tasks that merely mention Codex.","https:\u002F\u002Fgithub.com\u002Flzy18001500226\u002FMoSim\u002Fblob\u002Fmain\u002Fsrc\u002FAgent\u002Fcodex-main\u002Fcodex-rs\u002Fskills\u002Fsrc\u002Fassets\u002Fsamples\u002Fopenai-docs\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Flzy18001500226\u002FMoSim\u002Fblob\u002Fmain\u002Fsrc\u002FAgent\u002Fcodex-main\u002Fcodex-rs\u002Fskills\u002Fsrc\u002Fassets\u002Fsamples\u002Fopenai-docs\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":84,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":63},"01M78RJH7X67C5AY8ZVS7RQNWJ","imagegen","Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG\u002Fvector\u002Fcode-native assets, extending an established icon or logo system, or building the visual directly in HTML\u002FCSS\u002Fcanvas.","https:\u002F\u002Fgithub.com\u002Flzy18001500226\u002FMoSim\u002Fblob\u002Fmain\u002Fsrc\u002FAgent\u002Fcodex-main\u002Fcodex-rs\u002Fskills\u002Fsrc\u002Fassets\u002Fsamples\u002Fimagegen\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Flzy18001500226\u002FMoSim\u002Fblob\u002Fmain\u002Fsrc\u002FAgent\u002Fcodex-main\u002Fcodex-rs\u002Fskills\u002Fsrc\u002Fassets\u002Fsamples\u002Fimagegen\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":92,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":63},"01M78RBBAYMJ6T3ZMAYHCFM6G7","skill-creator-cc","Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.","https:\u002F\u002Fgithub.com\u002Flzy18001500226\u002FMoSim\u002Fblob\u002Fmain\u002FReferences\u002FAgent\u002FWorkflow\u002Fokwinds\u002Fmiscellany\u002Fagent\u002Fskills\u002Fskill-creator-cc\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Flzy18001500226\u002FMoSim\u002Fblob\u002Fmain\u002FReferences\u002FAgent\u002FWorkflow\u002Fokwinds\u002Fmiscellany\u002Fagent\u002Fskills\u002Fskill-creator-cc\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":100,"licenseFileUrl":101,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":105},"01M76VV9V2R9FZTVGMJZV7Y996","prd-writing-guide","Write complete, unambiguous PRDs that development teams can implement without guesswork. Includes requirement discovery framework, structured documentation methodology, completeness checklists, and common pitfall avoidance. Use when: writing new PRDs, reviewing PRD drafts, validating requirement completeness, preparing for engineering handoff. Triggers: 'write PRD', '写PRD', '产品需求文档', '需求文档', '需求规格', '需求评审', '完善需求', 'create requirements doc', 'product requirements', 'feature spec', 'requirements document'. Anti-triggers: 'technical design doc', 'architecture design', 'implementation plan', 'API design', '架构设计', '技术方案', '实现方案', '接口设计'.","MIT","https:\u002F\u002Fgithub.com\u002Flzy18001500226\u002FMoSim\u002Fblob\u002Fmain\u002FReferences\u002FAgent\u002FWorkflow\u002Fokwinds\u002Fmiscellany\u002Fagent\u002Fskills\u002Fprd-writing-guide\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Flzy18001500226\u002FMoSim\u002Fblob\u002Fmain\u002FReferences\u002FAgent\u002FWorkflow\u002Fokwinds\u002Fmiscellany\u002Fagent\u002Fskills\u002Fprd-writing-guide\u002FSKILL.md",[],[],"2026-11-12 13:55:43"]