[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CMB706Y6SP9D08E64MFJTK":3,"skill-same:01M7CMB706Y6SP9D08E64MFJTK":49},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":31,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M7CMB706Y6SP9D08E64MFJTK","n8n-mcp-tools-expert",null,"Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns.","YYC-Cube\u002FYYC3-Knowledge-Base","YYC-Cube","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235006543?v=4","01M79J2PH4SWD2X0825X6PN748","yyc3","01M79J2PHVK3F6ZBYT8K2SCZCW",1,"MIT","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-antigravity-awesome-skills\u002Fskills\u002Fn8n-mcp-tools-expert\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: n8n-mcp-tools-expert\ndescription: Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns.\nrisk: unknown\nsource: community\n---\n\n# n8n MCP Tools Expert\n\nMaster guide for using n8n-mcp MCP server tools to build workflows.\n\n## When to Use\n- You are using the `n8n-mcp` toolset to discover nodes, validate configs, or manage workflows.\n- The task involves choosing the right MCP tool or understanding its expected parameters and usage pattern.\n- You need guidance on workflow creation or editing through n8n MCP rather than through the n8n UI alone.\n\n---\n\n## Tool Categories\n\nn8n-mcp provides tools organized into categories:\n\n1. **Node Discovery** → SEARCH_GUIDE.md\n2. **Configuration Validation** → VALIDATION_GUIDE.md\n3. **Workflow Management** → WORKFLOW_GUIDE.md\n4. **Template Library** - Search and deploy 2,700+ real workflows\n5. **Documentation & Guides** - Tool docs, AI agent guide, Code node guides\n\n---\n\n## Quick Reference\n\n### Most Used Tools (by success rate)\n\n| Tool | Use When | Speed |\n|------|----------|-------|\n| `search_nodes` | Finding nodes by keyword | \u003C20ms |\n| `get_node` | Understanding node operations (detail=\"standard\") | \u003C10ms |\n| `validate_node` | Checking configurations (mode=\"full\") | \u003C100ms |\n| `n8n_create_workflow` | Creating workflows | 100-500ms |\n| `n8n_update_partial_workflow` | Editing workflows (MOST USED!) | 50-200ms |\n| `validate_workflow` | Checking complete workflow | 100-500ms |\n| `n8n_deploy_template` | Deploy template to n8n instance | 200-500ms |\n\n---\n\n## Tool Selection Guide\n\n### Finding the Right Node\n\n**Workflow**:\n```\n1. search_nodes({query: \"keyword\"})\n2. get_node({nodeType: \"nodes-base.name\"})\n3. [Optional] get_node({nodeType: \"nodes-base.name\", mode: \"docs\"})\n```\n\n**Example**:\n```javascript\n\u002F\u002F Step 1: Search\nsearch_nodes({query: \"slack\"})\n\u002F\u002F Returns: nodes-base.slack\n\n\u002F\u002F Step 2: Get details\nget_node({nodeType: \"nodes-base.slack\"})\n\u002F\u002F Returns: operations, properties, examples (standard detail)\n\n\u002F\u002F Step 3: Get readable documentation\nget_node({nodeType: \"nodes-base.slack\", mode: \"docs\"})\n\u002F\u002F Returns: markdown documentation\n```\n\n**Common pattern**: search → get_node (18s average)\n\n### Validating Configuration\n\n**Workflow**:\n```\n1. validate_node({nodeType, config: {}, mode: \"minimal\"}) - Check required fields\n2. validate_node({nodeType, config, profile: \"runtime\"}) - Full validation\n3. [Repeat] Fix errors, validate again\n```\n\n**Common pattern**: validate → fix → validate (23s thinking, 58s fixing per cycle)\n\n### Managing Workflows\n\n**Workflow**:\n```\n1. n8n_create_workflow({name, nodes, connections})\n2. n8n_validate_workflow({id})\n3. n8n_update_partial_workflow({id, operations: [...]})\n4. n8n_validate_workflow({id}) again\n5. n8n_update_partial_workflow({id, operations: [{type: \"activateWorkflow\"}]})\n```\n\n**Common pattern**: iterative updates (56s average between edits)\n\n---\n\n## Critical: nodeType Formats\n\n**Two different formats** for different tools!\n\n### Format 1: Search\u002FValidate Tools\n```javascript\n\u002F\u002F Use SHORT prefix\n\"nodes-base.slack\"\n\"nodes-base.httpRequest\"\n\"nodes-base.webhook\"\n\"nodes-langchain.agent\"\n```\n\n**Tools that use this**:\n- search_nodes (returns this format)\n- get_node\n- validate_node\n- validate_workflow\n\n### Format 2: Workflow Tools\n```javascript\n\u002F\u002F Use FULL prefix\n\"n8n-nodes-base.slack\"\n\"n8n-nodes-base.httpRequest\"\n\"n8n-nodes-base.webhook\"\n\"@n8n\u002Fn8n-nodes-langchain.agent\"\n```\n\n**Tools that use this**:\n- n8n_create_workflow\n- n8n_update_partial_workflow\n\n### Conversion\n\n```javascript\n\u002F\u002F search_nodes returns BOTH formats\n{\n  \"nodeType\": \"nodes-base.slack\",          \u002F\u002F For search\u002Fvalidate tools\n  \"workflowNodeType\": \"n8n-nodes-base.slack\"  \u002F\u002F For workflow tools\n}\n```\n\n---\n\n## Common Mistakes\n\n### Mistake 1: Wrong nodeType Format\n\n**Problem**: \"Node not found\" error\n\n```javascript\n\u002F\u002F WRONG\nget_node({nodeType: \"slack\"})  \u002F\u002F Missing prefix\nget_node({nodeType: \"n8n-nodes-base.slack\"})  \u002F\u002F Wrong prefix\n\n\u002F\u002F CORRECT\nget_node({nodeType: \"nodes-base.slack\"})\n```\n\n### Mistake 2: Using detail=\"full\" by Default\n\n**Problem**: Huge payload, slower response, token waste\n\n```javascript\n\u002F\u002F WRONG - Returns 3-8K tokens, use sparingly\nget_node({nodeType: \"nodes-base.slack\", detail: \"full\"})\n\n\u002F\u002F CORRECT - Returns 1-2K tokens, covers 95% of use cases\nget_node({nodeType: \"nodes-base.slack\"})  \u002F\u002F detail=\"standard\" is default\nget_node({nodeType: \"nodes-base.slack\", detail: \"standard\"})\n```\n\n**When to use detail=\"full\"**:\n- Debugging complex configuration issues\n- Need complete property schema with all nested options\n- Exploring advanced features\n\n**Better alternatives**:\n1. `get_node({detail: \"standard\"})` - for operations list (default)\n2. `get_node({mode: \"docs\"})` - for readable documentation\n3. `get_node({mode: \"search_properties\", propertyQuery: \"auth\"})` - for specific property\n\n### Mistake 3: Not Using Validation Profiles\n\n**Problem**: Too many false positives OR missing real errors\n\n**Profiles**:\n- `minimal` - Only required fields (fast, permissive)\n- `runtime` - Values + types (recommended for pre-deployment)\n- `ai-friendly` - Reduce false positives (for AI configuration)\n- `strict` - Maximum validation (for production)\n\n```javascript\n\u002F\u002F WRONG - Uses default profile\nvalidate_node({nodeType, config})\n\n\u002F\u002F CORRECT - Explicit profile\nvalidate_node({nodeType, config, profile: \"runtime\"})\n```\n\n### Mistake 4: Ignoring Auto-Sanitization\n\n**What happens**: ALL nodes sanitized on ANY workflow update\n\n**Auto-fixes**:\n- Binary operators (equals, contains) → removes singleValue\n- Unary operators (isEmpty, isNotEmpty) → adds singleValue: true\n- IF\u002FSwitch nodes → adds missing metadata\n\n**Cannot fix**:\n- Broken connections\n- Branch count mismatches\n- Paradoxical corrupt states\n\n```javascript\n\u002F\u002F After ANY update, auto-sanitization runs on ALL nodes\nn8n_update_partial_workflow({id, operations: [...]})\n\u002F\u002F → Automatically fixes operator structures\n```\n\n### Mistake 5: Not Using Smart Parameters\n\n**Problem**: Complex sourceIndex calculations for multi-output nodes\n\n**Old way** (manual):\n```javascript\n\u002F\u002F IF node connection\n{\n  type: \"addConnection\",\n  source: \"IF\",\n  target: \"Handler\",\n  sourceIndex: 0  \u002F\u002F Which output? Hard to remember!\n}\n```\n\n**New way** (smart parameters):\n```javascript\n\u002F\u002F IF node - semantic branch names\n{\n  type: \"addConnection\",\n  source: \"IF\",\n  target: \"True Handler\",\n  branch: \"true\"  \u002F\u002F Clear and readable!\n}\n\n{\n  type: \"addConnection\",\n  source: \"IF\",\n  target: \"False Handler\",\n  branch: \"false\"\n}\n\n\u002F\u002F Switch node - semantic case numbers\n{\n  type: \"addConnection\",\n  source: \"Switch\",\n  target: \"Handler A\",\n  case: 0\n}\n```\n\n### Mistake 6: Not Using intent Parameter\n\n**Problem**: Less helpful tool responses\n\n```javascript\n\u002F\u002F WRONG - No context for response\nn8n_update_partial_workflow({\n  id: \"abc\",\n  operations: [{type: \"addNode\", node: {...}}]\n})\n\n\u002F\u002F CORRECT - Better AI responses\nn8n_update_partial_workflow({\n  id: \"abc\",\n  intent: \"Add error handling for API failures\",\n  operations: [{type: \"addNode\", node: {...}}]\n})\n```\n\n---\n\n## Tool Usage Patterns\n\n### Pattern 1: Node Discovery (Most Common)\n\n**Common workflow**: 18s average between steps\n\n```javascript\n\u002F\u002F Step 1: Search (fast!)\nconst results = await search_nodes({\n  query: \"slack\",\n  mode: \"OR\",  \u002F\u002F Default: any word matches\n  limit: 20\n});\n\u002F\u002F → Returns: nodes-base.slack, nodes-base.slackTrigger\n\n\u002F\u002F Step 2: Get details (~18s later, user reviewing results)\nconst details = await get_node({\n  nodeType: \"nodes-base.slack\",\n  includeExamples: true  \u002F\u002F Get real template configs\n});\n\u002F\u002F → Returns: operations, properties, metadata\n```\n\n### Pattern 2: Validation Loop\n\n**Typical cycle**: 23s thinking, 58s fixing\n\n```javascript\n\u002F\u002F Step 1: Validate\nconst result = await validate_node({\n  nodeType: \"nodes-base.slack\",\n  config: {\n    resource: \"channel\",\n    operation: \"create\"\n  },\n  profile: \"runtime\"\n});\n\n\u002F\u002F Step 2: Check errors (~23s thinking)\nif (!result.valid) {\n  console.log(result.errors);  \u002F\u002F \"Missing required field: name\"\n}\n\n\u002F\u002F Step 3: Fix config (~58s fixing)\nconfig.name = \"general\";\n\n\u002F\u002F Step 4: Validate again\nawait validate_node({...});  \u002F\u002F Repeat until clean\n```\n\n### Pattern 3: Workflow Editing\n\n**Most used update tool**: 99.0% success rate, 56s average between edits\n\n```javascript\n\u002F\u002F Iterative workflow building (NOT one-shot!)\n\u002F\u002F Edit 1\nawait n8n_update_partial_workflow({\n  id: \"workflow-id\",\n  intent: \"Add webhook trigger\",\n  operations: [{type: \"addNode\", node: {...}}]\n});\n\n\u002F\u002F ~56s later...\n\n\u002F\u002F Edit 2\nawait n8n_update_partial_workflow({\n  id: \"workflow-id\",\n  intent: \"Connect webhook to processor\",\n  operations: [{type: \"addConnection\", source: \"...\", target: \"...\"}]\n});\n\n\u002F\u002F ~56s later...\n\n\u002F\u002F Edit 3 (validation)\nawait n8n_validate_workflow({id: \"workflow-id\"});\n\n\u002F\u002F Ready? Activate!\nawait n8n_update_partial_workflow({\n  id: \"workflow-id\",\n  intent: \"Activate workflow for production\",\n  operations: [{type: \"activateWorkflow\"}]\n});\n```\n\n---\n\n## Detailed Guides\n\n### Node Discovery Tools\nSee SEARCH_GUIDE.md for:\n- search_nodes\n- get_node with detail levels (minimal, standard, full)\n- get_node modes (info, docs, search_properties, versions)\n\n### Validation Tools\nSee VALIDATION_GUIDE.md for:\n- Validation profiles explained\n- validate_node with modes (minimal, full)\n- validate_workflow complete structure\n- Auto-sanitization system\n- Handling validation errors\n\n### Workflow Management\nSee WORKFLOW_GUIDE.md for:\n- n8n_create_workflow\n- n8n_update_partial_workflow (17 operation types!)\n- Smart parameters (branch, case)\n- AI connection types (8 types)\n- Workflow activation (activateWorkflow\u002FdeactivateWorkflow)\n- n8n_deploy_template\n- n8n_workflow_versions\n\n---\n\n## Template Usage\n\n### Search Templates\n\n```javascript\n\u002F\u002F Search by keyword (default mode)\nsearch_templates({\n  query: \"webhook slack\",\n  limit: 20\n});\n\n\u002F\u002F Search by node types\nsearch_templates({\n  searchMode: \"by_nodes\",\n  nodeTypes: [\"n8n-nodes-base.httpRequest\", \"n8n-nodes-base.slack\"]\n});\n\n\u002F\u002F Search by task type\nsearch_templates({\n  searchMode: \"by_task\",\n  task: \"webhook_processing\"\n});\n\n\u002F\u002F Search by metadata (complexity, setup time)\nsearch_templates({\n  searchMode: \"by_metadata\",\n  complexity: \"simple\",\n  maxSetupMinutes: 15\n});\n```\n\n### Get Template Details\n\n```javascript\nget_template({\n  templateId: 2947,\n  mode: \"structure\"  \u002F\u002F nodes+connections only\n});\n\nget_template({\n  templateId: 2947,\n  mode: \"full\"  \u002F\u002F complete workflow JSON\n});\n```\n\n### Deploy Template Directly\n\n```javascript\n\u002F\u002F Deploy template to your n8n instance\nn8n_deploy_template({\n  templateId: 2947,\n  name: \"My Weather to Slack\",  \u002F\u002F Custom name (optional)\n  autoFix: true,  \u002F\u002F Auto-fix common issues (default)\n  autoUpgradeVersions: true  \u002F\u002F Upgrade node versions (default)\n});\n\u002F\u002F Returns: workflow ID, required credentials, fixes applied\n```\n\n---\n\n## Self-Help Tools\n\n### Get Tool Documentation\n\n```javascript\n\u002F\u002F Overview of all tools\ntools_documentation()\n\n\u002F\u002F Specific tool details\ntools_documentation({\n  topic: \"search_nodes\",\n  depth: \"full\"\n})\n\n\u002F\u002F Code node guides\ntools_documentation({topic: \"javascript_code_node_guide\", depth: \"full\"})\ntools_documentation({topic: \"python_code_node_guide\", depth: \"full\"})\n```\n\n### AI Agent Guide\n\n```javascript\n\u002F\u002F Comprehensive AI workflow guide\nai_agents_guide()\n\u002F\u002F Returns: Architecture, connections, tools, validation, best practices\n```\n\n### Health Check\n\n```javascript\n\u002F\u002F Quick health check\nn8n_health_check()\n\n\u002F\u002F Detailed diagnostics\nn8n_health_check({mode: \"diagnostic\"})\n\u002F\u002F → Returns: status, env vars, tool status, API connectivity\n```\n\n---\n\n## Tool Availability\n\n**Always Available** (no n8n API needed):\n- search_nodes, get_node\n- validate_node, validate_workflow\n- search_templates, get_template\n- tools_documentation, ai_agents_guide\n\n**Requires n8n API** (N8N_API_URL + N8N_API_KEY):\n- n8n_create_workflow\n- n8n_update_partial_workflow\n- n8n_validate_workflow (by ID)\n- n8n_list_workflows, n8n_get_workflow\n- n8n_test_workflow\n- n8n_executions\n- n8n_deploy_template\n- n8n_workflow_versions\n- n8n_autofix_workflow\n\nIf API tools unavailable, use templates and validation-only workflows.\n\n---\n\n## Unified Tool Reference\n\n### get_node (Unified Node Information)\n\n**Detail Levels** (mode=\"info\", default):\n- `minimal` (~200 tokens) - Basic metadata only\n- `standard` (~1-2K tokens) - Essential properties + operations (RECOMMENDED)\n- `full` (~3-8K tokens) - Complete schema (use sparingly)\n\n**Operation Modes**:\n- `info` (default) - Node schema with detail level\n- `docs` - Readable markdown documentation\n- `search_properties` - Find specific properties (use with propertyQuery)\n- `versions` - List all versions with breaking changes\n- `compare` - Compare two versions\n- `breaking` - Show only breaking changes\n- `migrations` - Show auto-migratable changes\n\n```javascript\n\u002F\u002F Standard (recommended)\nget_node({nodeType: \"nodes-base.httpRequest\"})\n\n\u002F\u002F Get documentation\nget_node({nodeType: \"nodes-base.webhook\", mode: \"docs\"})\n\n\u002F\u002F Search for properties\nget_node({nodeType: \"nodes-base.httpRequest\", mode: \"search_properties\", propertyQuery: \"auth\"})\n\n\u002F\u002F Check versions\nget_node({nodeType: \"nodes-base.executeWorkflow\", mode: \"versions\"})\n```\n\n### validate_node (Unified Validation)\n\n**Modes**:\n- `full` (default) - Comprehensive validation with errors\u002Fwarnings\u002Fsuggestions\n- `minimal` - Quick required fields check only\n\n**Profiles** (for mode=\"full\"):\n- `minimal` - Very lenient\n- `runtime` - Standard (default, recommended)\n- `ai-friendly` - Balanced for AI workflows\n- `strict` - Most thorough (production)\n\n```javascript\n\u002F\u002F Full validation with runtime profile\nvalidate_node({nodeType: \"nodes-base.slack\", config: {...}, profile: \"runtime\"})\n\n\u002F\u002F Quick required fields check\nvalidate_node({nodeType: \"nodes-base.webhook\", config: {}, mode: \"minimal\"})\n```\n\n---\n\n## Performance Characteristics\n\n| Tool | Response Time | Payload Size |\n|------|---------------|--------------|\n| search_nodes | \u003C20ms | Small |\n| get_node (standard) | \u003C10ms | ~1-2KB |\n| get_node (full) | \u003C100ms | 3-8KB |\n| validate_node (minimal) | \u003C50ms | Small |\n| validate_node (full) | \u003C100ms | Medium |\n| validate_workflow | 100-500ms | Medium |\n| n8n_create_workflow | 100-500ms | Medium |\n| n8n_update_partial_workflow | 50-200ms | Small |\n| n8n_deploy_template | 200-500ms | Medium |\n\n---\n\n## Best Practices\n\n### Do\n- Use `get_node({detail: \"standard\"})` for most use cases\n- Specify validation profile explicitly (`profile: \"runtime\"`)\n- Use smart parameters (`branch`, `case`) for clarity\n- Include `intent` parameter in workflow updates\n- Follow search → get_node → validate workflow\n- Iterate workflows (avg 56s between edits)\n- Validate after every significant change\n- Use `includeExamples: true` for real configs\n- Use `n8n_deploy_template` for quick starts\n\n### Don't\n- Use `detail: \"full\"` unless necessary (wastes tokens)\n- Forget nodeType prefix (`nodes-base.*`)\n- Skip validation profiles\n- Try to build workflows in one shot (iterate!)\n- Ignore auto-sanitization behavior\n- Use full prefix (`n8n-nodes-base.*`) with search\u002Fvalidate tools\n- Forget to activate workflows after building\n\n---\n\n## Summary\n\n**Most Important**:\n1. Use **get_node** with `detail: \"standard\"` (default) - covers 95% of use cases\n2. nodeType formats differ: `nodes-base.*` (search\u002Fvalidate) vs `n8n-nodes-base.*` (workflows)\n3. Specify **validation profiles** (`runtime` recommended)\n4. Use **smart parameters** (`branch=\"true\"`, `case=0`)\n5. Include **intent parameter** in workflow updates\n6. **Auto-sanitization** runs on ALL nodes during updates\n7. Workflows can be **activated via API** (`activateWorkflow` operation)\n8. Workflows are built **iteratively** (56s avg between edits)\n\n**Common Workflow**:\n1. search_nodes → find node\n2. get_node → understand config\n3. validate_node → check config\n4. n8n_create_workflow → build\n5. n8n_validate_workflow → verify\n6. n8n_update_partial_workflow → iterate\n7. activateWorkflow → go live!\n\nFor details, see:\n- SEARCH_GUIDE.md - Node discovery\n- VALIDATION_GUIDE.md - Configuration validation\n- WORKFLOW_GUIDE.md - Workflow management\n\n---\n\n**Related Skills**:\n- n8n Expression Syntax - Write expressions in workflow fields\n- n8n Workflow Patterns - Architectural patterns from templates\n- n8n Validation Expert - Interpret validation errors\n- n8n Node Configuration - Operation-specific requirements\n- n8n Code JavaScript - Write JavaScript in Code nodes\n- n8n Code Python - Write Python in Code nodes\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n","# n8n MCP Tools Expert\n\nMaster guide for using n8n-mcp MCP server tools to build workflows.\n\n## When to Use\n- You are using the `n8n-mcp` toolset to discover nodes, validate configs, or manage workflows.\n- The task involves choosing the right MCP tool or understanding its expected parameters and usage pattern.\n- You need guidance on workflow creation or editing through n8n MCP rather than through the n8n UI alone.\n\n---\n\n## Tool Categories\n\nn8n-mcp provides tools organized into categories:\n\n1. **Node Discovery** → SEARCH_GUIDE.md\n2. **Configuration Validation** → VALIDATION_GUIDE.md\n3. **Workflow Management** → WORKFLOW_GUIDE.md\n4. **Template Library** - Search and deploy 2,700+ real workflows\n5. **Documentation & Guides** - Tool docs, AI agent guide, Code node guides\n\n---\n\n## Quick Reference\n\n### Most Used Tools (by success rate)\n\n| Tool | Use When | Speed |\n|------|----------|-------|\n| `search_nodes` | Finding nodes by keyword | \u003C20ms |\n| `get_node` | Understanding node operations (detail=\"standard\") | \u003C10ms |\n| `validate_node` | Checking configurations (mode=\"full\") | \u003C100ms |\n| `n8n_create_workflow` | Creating workflows | 100-500ms |\n| `n8n_update_partial_workflow` | Editing workflows (MOST USED!) | 50-200ms |\n| `validate_workflow` | Checking complete workflow | 100-500ms |\n| `n8n_deploy_template` | Deploy template to n8n instance | 200-500ms |\n\n---\n\n## Tool Selection Guide\n\n### Finding the Right Node\n\n**Workflow**:\n```\n1. search_nodes({query: \"keyword\"})\n2. get_node({nodeType: \"nodes-base.name\"})\n3. [Optional] get_node({nodeType: \"nodes-base.name\", mode: \"docs\"})\n```\n\n**Example**:\n```javascript\n\u002F\u002F Step 1: Search\nsearch_nodes({query: \"slack\"})\n\u002F\u002F Returns: nodes-base.slack\n\n\u002F\u002F Step 2: Get details\nget_node({nodeType: \"nodes-base.slack\"})\n\u002F\u002F Returns: operations, properties, examples (standard detail)\n\n\u002F\u002F Step 3: Get readable documentation\nget_node({nodeType: \"nodes-base.slack\", mode: \"docs\"})\n\u002F\u002F Returns: markdown documentation\n```\n\n**Common pattern**: search → get_node (18s average)\n\n### Validating Configuration\n\n**Workflow**:\n```\n1. validate_node({nodeType, config: {}, mode: \"minimal\"}) - Check required fields\n2. validate_node({nodeType, config, profile: \"runtime\"}) - Full validation\n3. [Repeat] Fix errors, validate again\n```\n\n**Common pattern**: validate → fix → validate (23s thinking, 58s fixing per cycle)\n\n### Managing Workflows\n\n**Workflow**:\n```\n1. n8n_create_workflow({name, nodes, connections})\n2. n8n_validate_workflow({id})\n3. n8n_update_partial_workflow({id, operations: [...]})\n4. n8n_validate_workflow({id}) again\n5. n8n_update_partial_workflow({id, operations: [{type: \"activateWorkflow\"}]})\n```\n\n**Common pattern**: iterative updates (56s average between edits)\n\n---\n\n## Critical: nodeType Formats\n\n**Two different formats** for different tools!\n\n### Format 1: Search\u002FValidate Tools\n```javascript\n\u002F\u002F Use SHORT prefix\n\"nodes-base.slack\"\n\"nodes-base.httpRequest\"\n\"nodes-base.webhook\"\n\"nodes-langchain.agent\"\n```\n\n**Tools that use this**:\n- search_nodes (returns this format)\n- get_node\n- validate_node\n- validate_workflow\n\n### Format 2: Workflow Tools\n```javascript\n\u002F\u002F Use FULL prefix\n\"n8n-nodes-base.slack\"\n\"n8n-nodes-base.httpRequest\"\n\"n8n-nodes-base.webhook\"\n\"@n8n\u002Fn8n-nodes-langchain.agent\"\n```\n\n**Tools that use this**:\n- n8n_create_workflow\n- n8n_update_partial_workflow\n\n### Conversion\n\n```javascript\n\u002F\u002F search_nodes returns BOTH formats\n{\n  \"nodeType\": \"nodes-base.slack\",          \u002F\u002F For search\u002Fvalidate tools\n  \"workflowNodeType\": \"n8n-nodes-base.slack\"  \u002F\u002F For workflow tools\n}\n```\n\n---\n\n## Common Mistakes\n\n### Mistake 1: Wrong nodeType Format\n\n**Problem**: \"Node not found\" error\n\n```javascript\n\u002F\u002F WRONG\nget_node({nodeType: \"slack\"})  \u002F\u002F Missing prefix\nget_node({nodeType: \"n8n-nodes-base.slack\"})  \u002F\u002F Wrong prefix\n\n\u002F\u002F CORRECT\nget_node({nodeType: \"nodes-base.slack\"})\n```\n\n### Mistake 2: Using detail=\"full\" by Default\n\n**Problem**: Huge payload, slower response, token waste\n\n```javascript\n\u002F\u002F WRONG - Returns 3-8K tokens, use sparingly\nget_node({nodeType: \"nodes-base.slack\", detail: \"full\"})\n\n\u002F\u002F CORRECT - Returns 1-2K tokens, covers 95% of use cases\nget_node({nodeType: \"nodes-base.slack\"})  \u002F\u002F detail=\"standard\" is default\nget_node({nodeType: \"nodes-base.slack\", detail: \"standard\"})\n```\n\n**When to use detail=\"full\"**:\n- Debugging complex configuration issues\n- Need complete property schema with all nested options\n- Exploring advanced features\n\n**Better alternatives**:\n1. `get_node({detail: \"standard\"})` - for operations list (default)\n2. `get_node({mode: \"docs\"})` - for readable documentation\n3. `get_node({mode: \"search_properties\", propertyQuery: \"auth\"})` - for specific property\n\n### Mistake 3: Not Using Validation Profiles\n\n**Problem**: Too many false positives OR missing real errors\n\n**Profiles**:\n- `minimal` - Only required fields (fast, permissive)\n- `runtime` - Values + types (recommended for pre-deployment)\n- `ai-friendly` - Reduce false positives (for AI configuration)\n- `strict` - Maximum validation (for production)\n\n```javascript\n\u002F\u002F WRONG - Uses default profile\nvalidate_node({nodeType, config})\n\n\u002F\u002F CORRECT - Explicit profile\nvalidate_node({nodeType, config, profile: \"runtime\"})\n```\n\n### Mistake 4: Ignoring Auto-Sanitization\n\n**What happens**: ALL nodes sanitized on ANY workflow update\n\n**Auto-fixes**:\n- Binary operators (equals, contains) → removes singleValue\n- Unary operators (isEmpty, isNotEmpty) → adds singleValue: true\n- IF\u002FSwitch nodes → adds missing metadata\n\n**Cannot fix**:\n- Broken connections\n- Branch count mismatches\n- Paradoxical corrupt states\n\n```javascript\n\u002F\u002F After ANY update, auto-sanitization runs on ALL nodes\nn8n_update_partial_workflow({id, operations: [...]})\n\u002F\u002F → Automatically fixes operator structures\n```\n\n### Mistake 5: Not Using Smart Parameters\n\n**Problem**: Complex sourceIndex calculations for multi-output nodes\n\n**Old way** (manual):\n```javascript\n\u002F\u002F IF node connection\n{\n  type: \"addConnection\",\n  source: \"IF\",\n  target: \"Handler\",\n  sourceIndex: 0  \u002F\u002F Which output? Hard to remember!\n}\n```\n\n**New way** (smart parameters):\n```javascript\n\u002F\u002F IF node - semantic branch names\n{\n  type: \"addConnection\",\n  source: \"IF\",\n  target: \"True Handler\",\n  branch: \"true\"  \u002F\u002F Clear and readable!\n}\n\n{\n  type: \"addConnection\",\n  source: \"IF\",\n  target: \"False Handler\",\n  branch: \"false\"\n}\n\n\u002F\u002F Switch node - semantic case numbers\n{\n  type: \"addConnection\",\n  source: \"Switch\",\n  target: \"Handler A\",\n  case: 0\n}\n```\n\n### Mistake 6: Not Using intent Parameter\n\n**Problem**: Less helpful tool responses\n\n```javascript\n\u002F\u002F WRONG - No context for response\nn8n_update_partial_workflow({\n  id: \"abc\",\n  operations: [{type: \"addNode\", node: {...}}]\n})\n\n\u002F\u002F CORRECT - Better AI responses\nn8n_update_partial_workflow({\n  id: \"abc\",\n  intent: \"Add error handling for API failures\",\n  operations: [{type: \"addNode\", node: {...}}]\n})\n```\n\n---\n\n## Tool Usage Patterns\n\n### Pattern 1: Node Discovery (Most Common)\n\n**Common workflow**: 18s average between steps\n\n```javascript\n\u002F\u002F Step 1: Search (fast!)\nconst results = await search_nodes({\n  query: \"slack\",\n  mode: \"OR\",  \u002F\u002F Default: any word matches\n  limit: 20\n});\n\u002F\u002F → Returns: nodes-base.slack, nodes-base.slackTrigger\n\n\u002F\u002F Step 2: Get details (~18s later, user reviewing results)\nconst details = await get_node({\n  nodeType: \"nodes-base.slack\",\n  includeExamples: true  \u002F\u002F Get real template configs\n});\n\u002F\u002F → Returns: operations, properties, metadata\n```\n\n### Pattern 2: Validation Loop\n\n**Typical cycle**: 23s thinking, 58s fixing\n\n```javascript\n\u002F\u002F Step 1: Validate\nconst result = await validate_node({\n  nodeType: \"nodes-base.slack\",\n  config: {\n    resource: \"channel\",\n    operation: \"create\"\n  },\n  profile: \"runtime\"\n});\n\n\u002F\u002F Step 2: Check errors (~23s thinking)\nif (!result.valid) {\n  console.log(result.errors);  \u002F\u002F \"Missing required field: name\"\n}\n\n\u002F\u002F Step 3: Fix config (~58s fixing)\nconfig.name = \"general\";\n\n\u002F\u002F Step 4: Validate again\nawait validate_node({...});  \u002F\u002F Repeat until clean\n```\n\n### Pattern 3: Workflow Editing\n\n**Most used update tool**: 99.0% success rate, 56s average between edits\n\n```javascript\n\u002F\u002F Iterative workflow building (NOT one-shot!)\n\u002F\u002F Edit 1\nawait n8n_update_partial_workflow({\n  id: \"workflow-id\",\n  intent: \"Add webhook trigger\",\n  operations: [{type: \"addNode\", node: {...}}]\n});\n\n\u002F\u002F ~56s later...\n\n\u002F\u002F Edit 2\nawait n8n_update_partial_workflow({\n  id: \"workflow-id\",\n  intent: \"Connect webhook to processor\",\n  operations: [{type: \"addConnection\", source: \"...\", target: \"...\"}]\n});\n\n\u002F\u002F ~56s later...\n\n\u002F\u002F Edit 3 (validation)\nawait n8n_validate_workflow({id: \"workflow-id\"});\n\n\u002F\u002F Ready? Activate!\nawait n8n_update_partial_workflow({\n  id: \"workflow-id\",\n  intent: \"Activate workflow for production\",\n  operations: [{type: \"activateWorkflow\"}]\n});\n```\n\n---\n\n## Detailed Guides\n\n### Node Discovery Tools\nSee SEARCH_GUIDE.md for:\n- search_nodes\n- get_node with detail levels (minimal, standard, full)\n- get_node modes (info, docs, search_properties, versions)\n\n### Validation Tools\nSee VALIDATION_GUIDE.md for:\n- Validation profiles explained\n- validate_node with modes (minimal, full)\n- validate_workflow complete structure\n- Auto-sanitization system\n- Handling validation errors\n\n### Workflow Management\nSee WORKFLOW_GUIDE.md for:\n- n8n_create_workflow\n- n8n_update_partial_workflow (17 operation types!)\n- Smart parameters (branch, case)\n- AI connection types (8 types)\n- Workflow activation (activateWorkflow\u002FdeactivateWorkflow)\n- n8n_deploy_template\n- n8n_workflow_versions\n\n---\n\n## Template Usage\n\n### Search Templates\n\n```javascript\n\u002F\u002F Search by keyword (default mode)\nsearch_templates({\n  query: \"webhook slack\",\n  limit: 20\n});\n\n\u002F\u002F Search by node types\nsearch_templates({\n  searchMode: \"by_nodes\",\n  nodeTypes: [\"n8n-nodes-base.httpRequest\", \"n8n-nodes-base.slack\"]\n});\n\n\u002F\u002F Search by task type\nsearch_templates({\n  searchMode: \"by_task\",\n  task: \"webhook_processing\"\n});\n\n\u002F\u002F Search by metadata (complexity, setup time)\nsearch_templates({\n  searchMode: \"by_metadata\",\n  complexity: \"simple\",\n  maxSetupMinutes: 15\n});\n```\n\n### Get Template Details\n\n```javascript\nget_template({\n  templateId: 2947,\n  mode: \"structure\"  \u002F\u002F nodes+connections only\n});\n\nget_template({\n  templateId: 2947,\n  mode: \"full\"  \u002F\u002F complete workflow JSON\n});\n```\n\n### Deploy Template Directly\n\n```javascript\n\u002F\u002F Deploy template to your n8n instance\nn8n_deploy_template({\n  templateId: 2947,\n  name: \"My Weather to Slack\",  \u002F\u002F Custom name (optional)\n  autoFix: true,  \u002F\u002F Auto-fix common issues (default)\n  autoUpgradeVersions: true  \u002F\u002F Upgrade node versions (default)\n});\n\u002F\u002F Returns: workflow ID, required credentials, fixes applied\n```\n\n---\n\n## Self-Help Tools\n\n### Get Tool Documentation\n\n```javascript\n\u002F\u002F Overview of all tools\ntools_documentation()\n\n\u002F\u002F Specific tool details\ntools_documentation({\n  topic: \"search_nodes\",\n  depth: \"full\"\n})\n\n\u002F\u002F Code node guides\ntools_documentation({topic: \"javascript_code_node_guide\", depth: \"full\"})\ntools_documentation({topic: \"python_code_node_guide\", depth: \"full\"})\n```\n\n### AI Agent Guide\n\n```javascript\n\u002F\u002F Comprehensive AI workflow guide\nai_agents_guide()\n\u002F\u002F Returns: Architecture, connections, tools, validation, best practices\n```\n\n### Health Check\n\n```javascript\n\u002F\u002F Quick health check\nn8n_health_check()\n\n\u002F\u002F Detailed diagnostics\nn8n_health_check({mode: \"diagnostic\"})\n\u002F\u002F → Returns: status, env vars, tool status, API connectivity\n```\n\n---\n\n## Tool Availability\n\n**Always Available** (no n8n API needed):\n- search_nodes, get_node\n- validate_node, validate_workflow\n- search_templates, get_template\n- tools_documentation, ai_agents_guide\n\n**Requires n8n API** (N8N_API_URL + N8N_API_KEY):\n- n8n_create_workflow\n- n8n_update_partial_workflow\n- n8n_validate_workflow (by ID)\n- n8n_list_workflows, n8n_get_workflow\n- n8n_test_workflow\n- n8n_executions\n- n8n_deploy_template\n- n8n_workflow_versions\n- n8n_autofix_workflow\n\nIf API tools unavailable, use templates and validation-only workflows.\n\n---\n\n## Unified Tool Reference\n\n### get_node (Unified Node Information)\n\n**Detail Levels** (mode=\"info\", default):\n- `minimal` (~200 tokens) - Basic metadata only\n- `standard` (~1-2K tokens) - Essential properties + operations (RECOMMENDED)\n- `full` (~3-8K tokens) - Complete schema (use sparingly)\n\n**Operation Modes**:\n- `info` (default) - Node schema with detail level\n- `docs` - Readable markdown documentation\n- `search_properties` - Find specific properties (use with propertyQuery)\n- `versions` - List all versions with breaking changes\n- `compare` - Compare two versions\n- `breaking` - Show only breaking changes\n- `migrations` - Show auto-migratable changes\n\n```javascript\n\u002F\u002F Standard (recommended)\nget_node({nodeType: \"nodes-base.httpRequest\"})\n\n\u002F\u002F Get documentation\nget_node({nodeType: \"nodes-base.webhook\", mode: \"docs\"})\n\n\u002F\u002F Search for properties\nget_node({nodeType: \"nodes-base.httpRequest\", mode: \"search_properties\", propertyQuery: \"auth\"})\n\n\u002F\u002F Check versions\nget_node({nodeType: \"nodes-base.executeWorkflow\", mode: \"versions\"})\n```\n\n### validate_node (Unified Validation)\n\n**Modes**:\n- `full` (default) - Comprehensive validation with errors\u002Fwarnings\u002Fsuggestions\n- `minimal` - Quick required fields check only\n\n**Profiles** (for mode=\"full\"):\n- `minimal` - Very lenient\n- `runtime` - Standard (default, recommended)\n- `ai-friendly` - Balanced for AI workflows\n- `strict` - Most thorough (production)\n\n```javascript\n\u002F\u002F Full validation with runtime profile\nvalidate_node({nodeType: \"nodes-base.slack\", config: {...}, profile: \"runtime\"})\n\n\u002F\u002F Quick required fields check\nvalidate_node({nodeType: \"nodes-base.webhook\", config: {}, mode: \"minimal\"})\n```\n\n---\n\n## Performance Characteristics\n\n| Tool | Response Time | Payload Size |\n|------|---------------|--------------|\n| search_nodes | \u003C20ms | Small |\n| get_node (standard) | \u003C10ms | ~1-2KB |\n| get_node (full) | \u003C100ms | 3-8KB |\n| validate_node (minimal) | \u003C50ms | Small |\n| validate_node (full) | \u003C100ms | Medium |\n| validate_workflow | 100-500ms | Medium |\n| n8n_create_workflow | 100-500ms | Medium |\n| n8n_update_partial_workflow | 50-200ms | Small |\n| n8n_deploy_template | 200-500ms | Medium |\n\n---\n\n## Best Practices\n\n### Do\n- Use `get_node({detail: \"standard\"})` for most use cases\n- Specify validation profile explicitly (`profile: \"runtime\"`)\n- Use smart parameters (`branch`, `case`) for clarity\n- Include `intent` parameter in workflow updates\n- Follow search → get_node → validate workflow\n- Iterate workflows (avg 56s between edits)\n- Validate after every significant change\n- Use `includeExamples: true` for real configs\n- Use `n8n_deploy_template` for quick starts\n\n### Don't\n- Use `detail: \"full\"` unless necessary (wastes tokens)\n- Forget nodeType prefix (`nodes-base.*`)\n- Skip validation profiles\n- Try to build workflows in one shot (iterate!)\n- Ignore auto-sanitization behavior\n- Use full prefix (`n8n-nodes-base.*`) with search\u002Fvalidate tools\n- Forget to activate workflows after building\n\n---\n\n## Summary\n\n**Most Important**:\n1. Use **get_node** with `detail: \"standard\"` (default) - covers 95% of use cases\n2. nodeType formats differ: `nodes-base.*` (search\u002Fvalidate) vs `n8n-nodes-base.*` (workflows)\n3. Specify **validation profiles** (`runtime` recommended)\n4. Use **smart parameters** (`branch=\"true\"`, `case=0`)\n5. Include **intent parameter** in workflow updates\n6. **Auto-sanitization** runs on ALL nodes during updates\n7. Workflows can be **activated via API** (`activateWorkflow` operation)\n8. Workflows are built **iteratively** (56s avg between edits)\n\n**Common Workflow**:\n1. search_nodes → find node\n2. get_node → understand config\n3. validate_node → check config\n4. n8n_create_workflow → build\n5. n8n_validate_workflow → verify\n6. n8n_update_partial_workflow → iterate\n7. activateWorkflow → go live!\n\nFor details, see:\n- SEARCH_GUIDE.md - Node discovery\n- VALIDATION_GUIDE.md - Configuration validation\n- WORKFLOW_GUIDE.md - Workflow management\n\n---\n\n**Related Skills**:\n- n8n Expression Syntax - Write expressions in workflow fields\n- n8n Workflow Patterns - Architectural patterns from templates\n- n8n Validation Expert - Interpret validation errors\n- n8n Node Configuration - Operation-specific requirements\n- n8n Code JavaScript - Write JavaScript in Code nodes\n- n8n Code Python - Write Python in Code nodes\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n",{"name":5,"risk":24,"source":25,"description":7},"unknown","community","main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-Skills-技能包\u002FYYC3-Skills-技能包-antigravity-awesome-skills\u002Fskills\u002Fn8n-mcp-tools-expert",0,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base","https:\u002F\u002Fkb.yyc3.top\u002F","https:\u002F\u002Fgithub.com\u002FYYC-Cube","万象归元于云枢 | 深栈智启新纪元","2026-11-10 10:37:32",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill n8n-mcp-tools-expert",{"tool":41,"command":42},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill n8n-mcp-tools-expert",{"tool":44,"command":45},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill n8n-mcp-tools-expert","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-antigravity-awesome-skills\u002Fskills\u002Fn8n-mcp-tools-expert\u002FSKILL.md",true,[],[50,57,64,71,78,85],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M7CTDWHERCXPQCP0K03A86AS","vercel-sandbox","Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include \"Vercel Sandbox browser\", \"microVM Chrome\", \"agent-browser in sandbox\", \"browser automation on Vercel\", or any task requiring Chrome in a Vercel Sandbox.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fvercel-sandbox\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M7CTD8D2BNJY54S65M47HEJA","slack","Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include \"check my Slack\", \"what channels have unreads\", \"send a message to\", \"search Slack for\", \"extract from Slack\", \"find who said\", or any task requiring programmatic Slack interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fslack\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M7CTCSSB8ZP3Q58C3YZDZK1W","electron","Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include \"automate Slack app\", \"control VS Code\", \"interact with Discord app\", \"test this Electron app\", \"connect to desktop app\", or any task requiring automation of a native Electron application.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Felectron\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7CTCBJY76688V4DCZGWFHGQ","dogfood","Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", \"test this app\u002Fsite\u002Fplatform\", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fdogfood\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7CTC4H0FFGVEAQR9PA4GA1A","agent-browser","Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fagent-browser\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7CTBKVFYBG78FDSABSDJTTQ","shadcn","Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn\u002Fui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for \"shadcn init\", \"create an app with --preset\", \"switch to --preset\", and for building a design system or applying a DESIGN.md or brand spec to shadcn\u002Fui.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-UI-界面组件\u002FYYC3-UI-界面组件-ui\u002Fskills\u002Fshadcn\u002FSKILL.md",[],[]]