[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79A6MCF0KGKESWJ45CC24NP":3,"skill-same:01M79A6MCF0KGKESWJ45CC24NP":140},{"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":50,"commitSha":51,"skillDirectory":52,"forksCount":14,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":55,"install":56,"resources":69},"01M79A6MCF0KGKESWJ45CC24NP","cloudflare-workflows",null,"Cloudflare Workflows for durable long-running execution. Use for multi-step workflows, retries, state persistence, or encountering NonRetryableError, execution failed errors.","Elogic360\u002Fsoftware-factory","Elogic360","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F156535519?v=4","01M74NH3F0RB13PWB7JZDE2V80","elogic360","01M74NH3FPC65082MDZVMFHDM3",0,"MIT","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fcloudflare-workflows\u002Fskills\u002Fcloudflare-workflows\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: cloudflare-workflows\ndescription: \"Cloudflare Workflows for durable long-running execution. Use for multi-step workflows, retries, state persistence, or encountering NonRetryableError, execution failed errors.\"\nlicense: MIT\nmetadata:\n  version: \"3.0.0\"\n  wrangler_version: \"4.50.0\"\n  workers_types_version: \"4.20251126.0\"\n  last_verified: \"2025-12-27\"\n  errors_prevented: 5\n  templates_included: 8\n  references_included: 8\n  agents_included: 3\n  commands_included: 4\n  scripts_included: 5\n  keywords:\n    - cloudflare workflows\n    - workflows workers\n    - durable execution\n    - workflow step\n    - WorkflowEntrypoint\n    - step.do\n    - step.sleep\n    - workflow retries\n    - NonRetryableError\n    - workflow state\n    - wrangler workflows\n    - workflow events\n    - long-running tasks\n    - step.sleepUntil\n    - step.waitForEvent\n    - workflow bindings\n---\n# Cloudflare Workflows\n\n**Status**: Production Ready ✅ | **Last Verified**: 2025-12-27 | **Version**: 3.0.0\n\n**Dependencies**: cloudflare-worker-base (for Worker setup)\n\n**Contents**: [Quick Start](#quick-start-10-minutes) • [Commands](#commands) • [Agents](#agents) • [Core Concepts](#core-concepts) • [Critical Rules](#critical-rules) • [Top Errors](#top-5-errors-critical) • [Common Patterns](#common-patterns) • [When to Load References](#when-to-load-references) • [Limits](#limits--pricing)\n\n---\n\n## Quick Start (10 Minutes)\n\n### 1. Create a Workflow\n\nUse the Cloudflare Workflows starter template:\n\n```bash\nnpm create cloudflare@latest my-workflow -- --template cloudflare\u002Fworkflows-starter --git --deploy false\ncd my-workflow\n```\n\n**What you get:**\n- WorkflowEntrypoint class template\n- Worker to trigger workflows\n- Complete wrangler.jsonc configuration\n\n### 2. Basic Workflow Structure\n\n**src\u002Findex.ts:**\n\n```typescript\nimport { WorkflowEntrypoint, WorkflowStep, WorkflowEvent } from 'cloudflare:workers';\n\ntype Env = {\n  MY_WORKFLOW: Workflow;\n};\n\ntype Params = {\n  userId: string;\n  email: string;\n};\n\nexport class MyWorkflow extends WorkflowEntrypoint\u003CEnv, Params> {\n  async run(event: WorkflowEvent\u003CParams>, step: WorkflowStep) {\n    const { userId, email } = event.payload;\n\n    \u002F\u002F Step 1: Do work with automatic retries\n    const result = await step.do('process user', async () => {\n      return { processed: true, userId };\n    });\n\n    \u002F\u002F Step 2: Wait before next step\n    await step.sleep('wait 1 hour', '1 hour');\n\n    \u002F\u002F Step 3: Continue workflow\n    await step.do('send email', async () => {\n      return { sent: true, email };\n    });\n\n    return { completed: true, userId };\n  }\n}\n\n\u002F\u002F Worker to trigger workflow\nexport default {\n  async fetch(req: Request, env: Env): Promise\u003CResponse> {\n    const instance = await env.MY_WORKFLOW.create({\n      params: { userId: '123', email: 'user@example.com' }\n    });\n\n    return Response.json({\n      id: instance.id,\n      status: await instance.status()\n    });\n  }\n};\n```\n\n**Template**: See `templates\u002Fbasic-workflow.ts` for complete example\n\n### 3. Configure wrangler.jsonc\n\n```jsonc\n{\n  \"name\": \"my-workflow\",\n  \"main\": \"src\u002Findex.ts\",\n  \"compatibility_date\": \"2025-10-22\",\n  \"workflows\": [\n    {\n      \"binding\": \"MY_WORKFLOW\",\n      \"name\": \"my-workflow\",\n      \"class_name\": \"MyWorkflow\"\n    }\n  ]\n}\n```\n\n**Template**: See `templates\u002Fwrangler-workflows-config.jsonc`\n\n### 4. Deploy\n\n```bash\nnpm run deploy\n```\n\n---\n\n## Commands\n\nInteractive slash commands for workflow development:\n\n| Command | Description | Use When |\n|---------|-------------|----------|\n| `\u002Fworkflow-setup` | Complete wizard for new workflow projects | Starting new project, need full setup |\n| `\u002Fworkflow-create` | Quick scaffolding for workflow classes | Adding workflow to existing project |\n| `\u002Fworkflow-debug` | Interactive debugging with error patterns | Troubleshooting workflow issues |\n| `\u002Fworkflow-test` | Test workflows locally and remotely | Validating workflow behavior |\n\n**Example Usage**:\n```\n\u002Fworkflow-setup   # Full guided setup wizard\n\u002Fworkflow-create  # Quick workflow scaffolding\n\u002Fworkflow-debug   # Debug workflow issues\n\u002Fworkflow-test    # Test workflow execution\n```\n\n---\n\n## Agents\n\nAutonomous agents for complex workflow tasks:\n\n| Agent | Description | Triggers |\n|-------|-------------|----------|\n| `workflow-debugger` | Auto-detects and fixes configuration\u002Fruntime errors | \"debug workflow\", \"fix workflow errors\" |\n| `workflow-optimizer` | Analyzes performance, cost, and reliability | \"optimize workflow\", \"improve performance\" |\n| `workflow-setup-assistant` | Autonomous project scaffolding | \"setup workflow\", \"create first workflow\" |\n\n**Key Capabilities**:\n- **Debugger**: 6-phase analysis, auto-fix for I\u002FO context, serialization, export issues\n- **Optimizer**: Cost analysis, reliability scoring, actionable recommendations\n- **Setup Assistant**: Project detection, automatic scaffolding, validation\n\n---\n\n## Scripts\n\nAutomation scripts in `scripts\u002F` directory:\n\n| Script | Purpose |\n|--------|---------|\n| `validate-workflow-config.sh` | Validate wrangler.jsonc configuration |\n| `test-workflow.sh` | Create and test workflow instances |\n| `benchmark-workflow.sh` | Measure performance and cost |\n| `generate-workflow.sh` | Scaffold new workflows from templates |\n| `check-workflow-limits.sh` | Validate against Cloudflare limits |\n\n**Usage**:\n```bash\n.\u002Fscripts\u002Fvalidate-workflow-config.sh           # Check config\n.\u002Fscripts\u002Ftest-workflow.sh my-workflow          # Test workflow\n.\u002Fscripts\u002Fbenchmark-workflow.sh my-workflow 10  # Benchmark 10 runs\n.\u002Fscripts\u002Fgenerate-workflow.sh MyWorkflow       # Generate scaffold\n.\u002Fscripts\u002Fcheck-workflow-limits.sh src\u002Fworkflows\u002Fmy-workflow.ts\n```\n\n---\n\n## Core Concepts\n\n### WorkflowEntrypoint\n\nEvery workflow must extend `WorkflowEntrypoint`:\n\n```typescript\nexport class MyWorkflow extends WorkflowEntrypoint\u003CEnv, Params> {\n  async run(event: WorkflowEvent\u003CParams>, step: WorkflowStep) {\n    \u002F\u002F Workflow logic here\n  }\n}\n```\n\n**Key Points**:\n- `Env`: Environment bindings (KV, D1, etc.)\n- `Params`: Typed payload passed when creating workflow instance\n- `event`: Contains `id`, `payload`, `timestamp`\n- `step`: Methods for durable execution\n\n### Step Methods\n\nAll workflow work MUST be done in steps for durability:\n\n```typescript\n\u002F\u002F step.do - Execute work with automatic retries\nawait step.do('step name', async () => {\n  return { result: 'data' };\n});\n\n\u002F\u002F step.sleep - Wait for duration\nawait step.sleep('wait', '1 hour');\n\n\u002F\u002F step.sleepUntil - Wait until timestamp\nawait step.sleepUntil('wait until', Date.now() + 3600000);\n\n\u002F\u002F step.waitForEvent - Wait for external event\nconst event = await step.waitForEvent('payment received', 'payment.completed', {\n  timeout: '30 minutes'\n});\n```\n\n**CRITICAL**: All I\u002FO (fetch, KV, D1, R2) must happen **inside** `step.do()` callbacks!\n\n**Reference**: See `references\u002Fworkflow-patterns.md` for all patterns\n\n---\n\n## Critical Rules\n\n### Always Do ✅\n\n✅ **Perform all I\u002FO inside step.do()** - Required for durability\n✅ **Use named steps** - Makes debugging easier\n✅ **Return JSON-serializable data from steps** - Required for state persistence\n✅ **Use step.sleep() for delays** - Don't use setTimeout()\n✅ **Handle errors explicitly** - Use try\u002Fcatch in step callbacks\n✅ **Use NonRetryableError for permanent failures** - Stops retries\n\n**Workflow Patterns**: See `references\u002Fworkflow-patterns.md` for:\n- Sequential workflows\n- Parallel execution\n- Event-driven workflows\n- Scheduled workflows\n- Human-in-the-loop workflows\n\n### Never Do ❌\n\n❌ **Never do I\u002FO outside step.do()** - Will fail with \"I\u002FO context\" error\n❌ **Never use setTimeout() or setInterval()** - Use step.sleep() instead\n❌ **Never return non-serializable data** - Functions, Promises, etc. will fail\n❌ **Never hardcode timeouts** - Use workflow config\n❌ **Never ignore NonRetryableError** - Indicates permanent failure\n\n---\n\n## Top 5 Critical Errors\n\n### Error #1: I\u002FO Context Error ⚠️\n\n**Error:**\n```\nCannot perform I\u002FO on behalf of a different request\n```\n\n**Cause:** Performing I\u002FO outside `step.do()` callback\n\n**Solution:**\n```typescript\n\u002F\u002F ❌ WRONG\nconst data = await fetch('https:\u002F\u002Fapi.example.com');\nawait step.do('use data', async () => {\n  return data; \u002F\u002F Error!\n});\n\n\u002F\u002F ✅ CORRECT\nconst data = await step.do('fetch data', async () => {\n  const response = await fetch('https:\u002F\u002Fapi.example.com');\n  return await response.json();\n});\n```\n\n### Error #2: Serialization Error\n\n**Error:**\n```\nCannot serialize workflow state\n```\n\n**Cause:** Returning non-JSON-serializable data from step\n\n**Solution:**\n```typescript\n\u002F\u002F ❌ WRONG\nawait step.do('process', async () => {\n  return { fn: () => {} }; \u002F\u002F Functions not serializable\n});\n\n\u002F\u002F ✅ CORRECT\nawait step.do('process', async () => {\n  return { result: 'data' }; \u002F\u002F JSON-serializable\n});\n```\n\n### Error #3: NonRetryableError Not Thrown\n\n**Error:** Workflow retries forever on permanent failures\n\n**Solution:**\n```typescript\nimport { NonRetryableError } from 'cloudflare:workers';\n\nawait step.do('validate', async () => {\n  if (!isValid) {\n    throw new NonRetryableError('Invalid input'); \u002F\u002F Stop retries\n  }\n  return { valid: true };\n});\n```\n\n### Error #4: WorkflowEvent Not Found\n\n**Error:**\n```\nWorkflowEvent 'payment.completed' not found\n```\n\n**Cause:** Event name mismatch between `waitForEvent` and trigger\n\n**Solution:**\n```typescript\n\u002F\u002F Workflow waits for event\nconst event = await step.waitForEvent('wait payment', 'payment.completed', {\n  timeout: '30 minutes'\n});\n\n\u002F\u002F Trigger event with EXACT same name\nawait instance.trigger('payment.completed', { amount: 100 });\n```\n\n### Error #5: Workflow Execution Failed\n\n**Error:**\n```\nWorkflow execution failed: Step timeout exceeded\n```\n\n**Cause:** Step exceeds maximum CPU time (30 seconds)\n\n**Solution:**\n```typescript\n\u002F\u002F ❌ WRONG\nawait step.do('long task', async () => {\n  for (let i = 0; i \u003C 1000000; i++) {\n    \u002F\u002F Long computation\n  }\n});\n\n\u002F\u002F ✅ CORRECT - Break into smaller steps\nfor (let i = 0; i \u003C 100; i++) {\n  await step.do(`batch ${i}`, async () => {\n    \u002F\u002F Process batch\n  });\n}\n```\n\n---\n\n**All Issues**: See `references\u002Fcommon-issues.md` for complete documentation\n\n---\n\n## Common Patterns\n\n### Sequential Workflow\n\nBasic workflow with steps executing in order. Each step completes before the next begins.\n\n**Use cases**: Order processing, user onboarding, data pipelines\n\n**Load `templates\u002Fbasic-workflow.ts` for complete example**\n\n### Scheduled Workflow\n\nWorkflow with time delays between steps using `step.sleep()` or `step.sleepUntil()`.\n\n**Use cases**: Reminder sequences, scheduled tasks, delayed notifications\n\n**Load `templates\u002Fscheduled-workflow.ts` for complete example**\n\n### Event-Driven Workflow\n\nWait for external events with `step.waitForEvent()`. Always set timeout and handle with `NonRetryableError`:\n\n```typescript\nconst payment = await step.waitForEvent('wait payment', 'payment.completed', {\n  timeout: '30 minutes'\n});\nif (!payment) throw new NonRetryableError('Payment timeout');\n```\n\n**Load `templates\u002Fworkflow-with-events.ts` for complete example**\n\n### Workflow with Retries\n\nUse `NonRetryableError` for permanent failures (404), regular `Error` for transient failures (5xx):\n\n```typescript\nconst data = await step.do('fetch', async () => {\n  const response = await fetch(url);\n  if (!response.ok) {\n    if (response.status === 404) throw new NonRetryableError('Not found');\n    throw new Error('Temporary failure'); \u002F\u002F Will retry\n  }\n  return await response.json();\n});\n```\n\n**Load `templates\u002Fworkflow-with-retries.ts` for complete example with retry configuration**\n\n---\n\n## Triggering Workflows\n\n**From Worker**: Create instances via `env.MY_WORKFLOW.create()`, get status with `instance.status()`, trigger events with `instance.trigger()`.\n\n**From Cron**: Use `scheduled()` handler to create workflow instances on schedule.\n\n**Load `templates\u002Fworker-trigger.ts` for complete Worker trigger example**\n**Load `templates\u002Fscheduled-workflow.ts` for complete Cron trigger example**\n\n---\n\n## When to Load References\n\n**`references\u002Fcommon-issues.md`**: Encountering I\u002FO context, serialization, NonRetryableError, event naming, or timeout errors; troubleshooting workflow failures.\n\n**`references\u002Fworkflow-patterns.md`**: Building complex orchestration, approval workflows, idempotency patterns, or circuit breaker patterns.\n\n**`references\u002Fwrangler-commands.md`**: Need CLI commands for managing workflow instances, debugging stuck workflows, or monitoring production.\n\n**`references\u002Fproduction-checklist.md`**: Preparing for deployment, need pre-deployment verification, setting up monitoring\u002Ferror handling.\n\n**`references\u002Flimits-quotas.md`**: Hitting instance\u002Fstep\u002Fpayload limits, optimizing for cost, designing high-volume workflows.\n\n**`references\u002F2025-features.md`**: Using events system, enhanced retries, instance lifecycle control, or latest Workflows features.\n\n**`references\u002Fmetrics-analytics.md`**: Setting up monitoring, custom metrics, external logging integration, or workflow dashboards.\n\n**`references\u002Ftroubleshooting.md`**: Complex debugging scenarios, stuck instances, systematic diagnosis, performance issues.\n\n**`templates\u002F`**: **basic-workflow.ts** (sequential), **scheduled-workflow.ts** (delays\u002Fsleep), **workflow-with-events.ts** (waitForEvent), **workflow-with-retries.ts** (custom retry), **worker-trigger.ts** (Worker triggers), **wrangler-workflows-config.jsonc** (Wrangler config), **parallel-execution-workflow.ts** (batched parallel processing), **circuit-breaker-workflow.ts** (resilient external calls)\n\n---\n\n## Wrangler Commands\n\n**Key Commands**: `wrangler workflows create`, `wrangler workflows instances list\u002Fdescribe\u002Fterminate`, `wrangler deploy`\n\n**Load `references\u002Fwrangler-commands.md` for complete CLI reference with all workflow management commands, monitoring workflows, and debugging stuck instances.**\n\n---\n\n## State Persistence\n\nWorkflows automatically persist state between steps. No manual state management needed:\n\n```typescript\nexport class StatefulWorkflow extends WorkflowEntrypoint {\n  async run(event, step) {\n    \u002F\u002F Step 1 result is automatically persisted\n    const result1 = await step.do('step 1', async () => {\n      return { data: 'value' };\n    });\n\n    \u002F\u002F Even if workflow crashes here, step 1 won't re-run\n    await step.sleep('wait', '1 hour');\n\n    \u002F\u002F Step 2 can use step 1's result (still available after sleep)\n    await step.do('step 2', async () => {\n      console.log(result1.data); \u002F\u002F 'value' - persisted!\n    });\n  }\n}\n```\n\n**Key Points**:\n- Step results automatically persisted\n- Completed steps never re-run (even after crash\u002Frestart)\n- State available throughout workflow lifetime\n\n---\n\n## Limits\n\n| Resource | Limit |\n|----------|-------|\n| **Step CPU Time** | 30 seconds |\n| **Workflow Duration** | 30 days |\n| **Step Payload Size** | 128 KB |\n| **Workflow Payload Size** | 128 KB |\n| **Steps per Workflow** | 1,000 |\n| **Concurrent Instances** | 1,000 per workflow |\n| **Event Payload Size** | 128 KB |\n\n**Workarounds**:\n- Large data: Store in KV\u002FR2, pass key in step\n- Long CPU: Break into smaller steps\n- Many steps: Consider sub-workflows\n\n## Pricing\n\n- **Duration**: $0.02 per million GB-s (same as Workers)\n- **Requests**: $0.15 per million (workflow creation + step execution)\n- **State Storage**: Included (no additional cost)\n- **Sleep**: Free (no CPU usage during sleep)\n\n**Example Cost** (1M workflow runs):\n- 5 steps each = 5M requests = $0.75\n- 10ms per step = 50GB-s = $0.001\n- **Total**: ~$0.75 per million workflows\n\n---\n\n## Troubleshooting\n\n### \"I\u002FO context\" error\n**Solution**: Move all I\u002FO into `step.do()` callbacks → See `references\u002Fcommon-issues.md` #1\n\n### \"Serialization error\"\n**Solution**: Return only JSON-serializable data from steps → See `references\u002Fcommon-issues.md` #2\n\n### Workflow retries forever\n**Solution**: Throw `NonRetryableError` for permanent failures → See `references\u002Fcommon-issues.md` #3\n\n### \"WorkflowEvent not found\"\n**Solution**: Ensure event names match exactly → See `references\u002Fcommon-issues.md` #4\n\n### \"Step timeout exceeded\"\n**Solution**: Break long computations into smaller steps → See `references\u002Fcommon-issues.md` #5\n\n---\n\n## Production Checklist\n\n**10-Point Pre-Deployment Checklist**: I\u002FO context isolation, JSON serialization, NonRetryableError usage, event name consistency, step duration limits, error handling, retry configuration, timeouts, workflow naming, and monitoring.\n\n**Load `references\u002Fproduction-checklist.md` for complete checklist with detailed explanations, code examples, verification steps, and deployment workflow.**\n\n---\n\n## Official Documentation\n\n**Workflows**: https:\u002F\u002Fdevelopers.cloudflare.com\u002Fworkflows\u002F • **API Reference**: https:\u002F\u002Fdevelopers.cloudflare.com\u002Fworkflows\u002Freference\u002F • **Examples**: https:\u002F\u002Fdevelopers.cloudflare.com\u002Fworkflows\u002Fexamples\u002F • **Blog**: https:\u002F\u002Fblog.cloudflare.com\u002Fcloudflare-workflows\u002F\n","# Cloudflare Workflows\n\n**Status**: Production Ready ✅ | **Last Verified**: 2025-12-27 | **Version**: 3.0.0\n\n**Dependencies**: cloudflare-worker-base (for Worker setup)\n\n**Contents**: [Quick Start](#quick-start-10-minutes) • [Commands](#commands) • [Agents](#agents) • [Core Concepts](#core-concepts) • [Critical Rules](#critical-rules) • [Top Errors](#top-5-errors-critical) • [Common Patterns](#common-patterns) • [When to Load References](#when-to-load-references) • [Limits](#limits--pricing)\n\n---\n\n## Quick Start (10 Minutes)\n\n### 1. Create a Workflow\n\nUse the Cloudflare Workflows starter template:\n\n```bash\nnpm create cloudflare@latest my-workflow -- --template cloudflare\u002Fworkflows-starter --git --deploy false\ncd my-workflow\n```\n\n**What you get:**\n- WorkflowEntrypoint class template\n- Worker to trigger workflows\n- Complete wrangler.jsonc configuration\n\n### 2. Basic Workflow Structure\n\n**src\u002Findex.ts:**\n\n```typescript\nimport { WorkflowEntrypoint, WorkflowStep, WorkflowEvent } from 'cloudflare:workers';\n\ntype Env = {\n  MY_WORKFLOW: Workflow;\n};\n\ntype Params = {\n  userId: string;\n  email: string;\n};\n\nexport class MyWorkflow extends WorkflowEntrypoint\u003CEnv, Params> {\n  async run(event: WorkflowEvent\u003CParams>, step: WorkflowStep) {\n    const { userId, email } = event.payload;\n\n    \u002F\u002F Step 1: Do work with automatic retries\n    const result = await step.do('process user', async () => {\n      return { processed: true, userId };\n    });\n\n    \u002F\u002F Step 2: Wait before next step\n    await step.sleep('wait 1 hour', '1 hour');\n\n    \u002F\u002F Step 3: Continue workflow\n    await step.do('send email', async () => {\n      return { sent: true, email };\n    });\n\n    return { completed: true, userId };\n  }\n}\n\n\u002F\u002F Worker to trigger workflow\nexport default {\n  async fetch(req: Request, env: Env): Promise\u003CResponse> {\n    const instance = await env.MY_WORKFLOW.create({\n      params: { userId: '123', email: 'user@example.com' }\n    });\n\n    return Response.json({\n      id: instance.id,\n      status: await instance.status()\n    });\n  }\n};\n```\n\n**Template**: See `templates\u002Fbasic-workflow.ts` for complete example\n\n### 3. Configure wrangler.jsonc\n\n```jsonc\n{\n  \"name\": \"my-workflow\",\n  \"main\": \"src\u002Findex.ts\",\n  \"compatibility_date\": \"2025-10-22\",\n  \"workflows\": [\n    {\n      \"binding\": \"MY_WORKFLOW\",\n      \"name\": \"my-workflow\",\n      \"class_name\": \"MyWorkflow\"\n    }\n  ]\n}\n```\n\n**Template**: See `templates\u002Fwrangler-workflows-config.jsonc`\n\n### 4. Deploy\n\n```bash\nnpm run deploy\n```\n\n---\n\n## Commands\n\nInteractive slash commands for workflow development:\n\n| Command | Description | Use When |\n|---------|-------------|----------|\n| `\u002Fworkflow-setup` | Complete wizard for new workflow projects | Starting new project, need full setup |\n| `\u002Fworkflow-create` | Quick scaffolding for workflow classes | Adding workflow to existing project |\n| `\u002Fworkflow-debug` | Interactive debugging with error patterns | Troubleshooting workflow issues |\n| `\u002Fworkflow-test` | Test workflows locally and remotely | Validating workflow behavior |\n\n**Example Usage**:\n```\n\u002Fworkflow-setup   # Full guided setup wizard\n\u002Fworkflow-create  # Quick workflow scaffolding\n\u002Fworkflow-debug   # Debug workflow issues\n\u002Fworkflow-test    # Test workflow execution\n```\n\n---\n\n## Agents\n\nAutonomous agents for complex workflow tasks:\n\n| Agent | Description | Triggers |\n|-------|-------------|----------|\n| `workflow-debugger` | Auto-detects and fixes configuration\u002Fruntime errors | \"debug workflow\", \"fix workflow errors\" |\n| `workflow-optimizer` | Analyzes performance, cost, and reliability | \"optimize workflow\", \"improve performance\" |\n| `workflow-setup-assistant` | Autonomous project scaffolding | \"setup workflow\", \"create first workflow\" |\n\n**Key Capabilities**:\n- **Debugger**: 6-phase analysis, auto-fix for I\u002FO context, serialization, export issues\n- **Optimizer**: Cost analysis, reliability scoring, actionable recommendations\n- **Setup Assistant**: Project detection, automatic scaffolding, validation\n\n---\n\n## Scripts\n\nAutomation scripts in `scripts\u002F` directory:\n\n| Script | Purpose |\n|--------|---------|\n| `validate-workflow-config.sh` | Validate wrangler.jsonc configuration |\n| `test-workflow.sh` | Create and test workflow instances |\n| `benchmark-workflow.sh` | Measure performance and cost |\n| `generate-workflow.sh` | Scaffold new workflows from templates |\n| `check-workflow-limits.sh` | Validate against Cloudflare limits |\n\n**Usage**:\n```bash\n.\u002Fscripts\u002Fvalidate-workflow-config.sh           # Check config\n.\u002Fscripts\u002Ftest-workflow.sh my-workflow          # Test workflow\n.\u002Fscripts\u002Fbenchmark-workflow.sh my-workflow 10  # Benchmark 10 runs\n.\u002Fscripts\u002Fgenerate-workflow.sh MyWorkflow       # Generate scaffold\n.\u002Fscripts\u002Fcheck-workflow-limits.sh src\u002Fworkflows\u002Fmy-workflow.ts\n```\n\n---\n\n## Core Concepts\n\n### WorkflowEntrypoint\n\nEvery workflow must extend `WorkflowEntrypoint`:\n\n```typescript\nexport class MyWorkflow extends WorkflowEntrypoint\u003CEnv, Params> {\n  async run(event: WorkflowEvent\u003CParams>, step: WorkflowStep) {\n    \u002F\u002F Workflow logic here\n  }\n}\n```\n\n**Key Points**:\n- `Env`: Environment bindings (KV, D1, etc.)\n- `Params`: Typed payload passed when creating workflow instance\n- `event`: Contains `id`, `payload`, `timestamp`\n- `step`: Methods for durable execution\n\n### Step Methods\n\nAll workflow work MUST be done in steps for durability:\n\n```typescript\n\u002F\u002F step.do - Execute work with automatic retries\nawait step.do('step name', async () => {\n  return { result: 'data' };\n});\n\n\u002F\u002F step.sleep - Wait for duration\nawait step.sleep('wait', '1 hour');\n\n\u002F\u002F step.sleepUntil - Wait until timestamp\nawait step.sleepUntil('wait until', Date.now() + 3600000);\n\n\u002F\u002F step.waitForEvent - Wait for external event\nconst event = await step.waitForEvent('payment received', 'payment.completed', {\n  timeout: '30 minutes'\n});\n```\n\n**CRITICAL**: All I\u002FO (fetch, KV, D1, R2) must happen **inside** `step.do()` callbacks!\n\n**Reference**: See `references\u002Fworkflow-patterns.md` for all patterns\n\n---\n\n## Critical Rules\n\n### Always Do ✅\n\n✅ **Perform all I\u002FO inside step.do()** - Required for durability\n✅ **Use named steps** - Makes debugging easier\n✅ **Return JSON-serializable data from steps** - Required for state persistence\n✅ **Use step.sleep() for delays** - Don't use setTimeout()\n✅ **Handle errors explicitly** - Use try\u002Fcatch in step callbacks\n✅ **Use NonRetryableError for permanent failures** - Stops retries\n\n**Workflow Patterns**: See `references\u002Fworkflow-patterns.md` for:\n- Sequential workflows\n- Parallel execution\n- Event-driven workflows\n- Scheduled workflows\n- Human-in-the-loop workflows\n\n### Never Do ❌\n\n❌ **Never do I\u002FO outside step.do()** - Will fail with \"I\u002FO context\" error\n❌ **Never use setTimeout() or setInterval()** - Use step.sleep() instead\n❌ **Never return non-serializable data** - Functions, Promises, etc. will fail\n❌ **Never hardcode timeouts** - Use workflow config\n❌ **Never ignore NonRetryableError** - Indicates permanent failure\n\n---\n\n## Top 5 Critical Errors\n\n### Error #1: I\u002FO Context Error ⚠️\n\n**Error:**\n```\nCannot perform I\u002FO on behalf of a different request\n```\n\n**Cause:** Performing I\u002FO outside `step.do()` callback\n\n**Solution:**\n```typescript\n\u002F\u002F ❌ WRONG\nconst data = await fetch('https:\u002F\u002Fapi.example.com');\nawait step.do('use data', async () => {\n  return data; \u002F\u002F Error!\n});\n\n\u002F\u002F ✅ CORRECT\nconst data = await step.do('fetch data', async () => {\n  const response = await fetch('https:\u002F\u002Fapi.example.com');\n  return await response.json();\n});\n```\n\n### Error #2: Serialization Error\n\n**Error:**\n```\nCannot serialize workflow state\n```\n\n**Cause:** Returning non-JSON-serializable data from step\n\n**Solution:**\n```typescript\n\u002F\u002F ❌ WRONG\nawait step.do('process', async () => {\n  return { fn: () => {} }; \u002F\u002F Functions not serializable\n});\n\n\u002F\u002F ✅ CORRECT\nawait step.do('process', async () => {\n  return { result: 'data' }; \u002F\u002F JSON-serializable\n});\n```\n\n### Error #3: NonRetryableError Not Thrown\n\n**Error:** Workflow retries forever on permanent failures\n\n**Solution:**\n```typescript\nimport { NonRetryableError } from 'cloudflare:workers';\n\nawait step.do('validate', async () => {\n  if (!isValid) {\n    throw new NonRetryableError('Invalid input'); \u002F\u002F Stop retries\n  }\n  return { valid: true };\n});\n```\n\n### Error #4: WorkflowEvent Not Found\n\n**Error:**\n```\nWorkflowEvent 'payment.completed' not found\n```\n\n**Cause:** Event name mismatch between `waitForEvent` and trigger\n\n**Solution:**\n```typescript\n\u002F\u002F Workflow waits for event\nconst event = await step.waitForEvent('wait payment', 'payment.completed', {\n  timeout: '30 minutes'\n});\n\n\u002F\u002F Trigger event with EXACT same name\nawait instance.trigger('payment.completed', { amount: 100 });\n```\n\n### Error #5: Workflow Execution Failed\n\n**Error:**\n```\nWorkflow execution failed: Step timeout exceeded\n```\n\n**Cause:** Step exceeds maximum CPU time (30 seconds)\n\n**Solution:**\n```typescript\n\u002F\u002F ❌ WRONG\nawait step.do('long task', async () => {\n  for (let i = 0; i \u003C 1000000; i++) {\n    \u002F\u002F Long computation\n  }\n});\n\n\u002F\u002F ✅ CORRECT - Break into smaller steps\nfor (let i = 0; i \u003C 100; i++) {\n  await step.do(`batch ${i}`, async () => {\n    \u002F\u002F Process batch\n  });\n}\n```\n\n---\n\n**All Issues**: See `references\u002Fcommon-issues.md` for complete documentation\n\n---\n\n## Common Patterns\n\n### Sequential Workflow\n\nBasic workflow with steps executing in order. Each step completes before the next begins.\n\n**Use cases**: Order processing, user onboarding, data pipelines\n\n**Load `templates\u002Fbasic-workflow.ts` for complete example**\n\n### Scheduled Workflow\n\nWorkflow with time delays between steps using `step.sleep()` or `step.sleepUntil()`.\n\n**Use cases**: Reminder sequences, scheduled tasks, delayed notifications\n\n**Load `templates\u002Fscheduled-workflow.ts` for complete example**\n\n### Event-Driven Workflow\n\nWait for external events with `step.waitForEvent()`. Always set timeout and handle with `NonRetryableError`:\n\n```typescript\nconst payment = await step.waitForEvent('wait payment', 'payment.completed', {\n  timeout: '30 minutes'\n});\nif (!payment) throw new NonRetryableError('Payment timeout');\n```\n\n**Load `templates\u002Fworkflow-with-events.ts` for complete example**\n\n### Workflow with Retries\n\nUse `NonRetryableError` for permanent failures (404), regular `Error` for transient failures (5xx):\n\n```typescript\nconst data = await step.do('fetch', async () => {\n  const response = await fetch(url);\n  if (!response.ok) {\n    if (response.status === 404) throw new NonRetryableError('Not found');\n    throw new Error('Temporary failure'); \u002F\u002F Will retry\n  }\n  return await response.json();\n});\n```\n\n**Load `templates\u002Fworkflow-with-retries.ts` for complete example with retry configuration**\n\n---\n\n## Triggering Workflows\n\n**From Worker**: Create instances via `env.MY_WORKFLOW.create()`, get status with `instance.status()`, trigger events with `instance.trigger()`.\n\n**From Cron**: Use `scheduled()` handler to create workflow instances on schedule.\n\n**Load `templates\u002Fworker-trigger.ts` for complete Worker trigger example**\n**Load `templates\u002Fscheduled-workflow.ts` for complete Cron trigger example**\n\n---\n\n## When to Load References\n\n**`references\u002Fcommon-issues.md`**: Encountering I\u002FO context, serialization, NonRetryableError, event naming, or timeout errors; troubleshooting workflow failures.\n\n**`references\u002Fworkflow-patterns.md`**: Building complex orchestration, approval workflows, idempotency patterns, or circuit breaker patterns.\n\n**`references\u002Fwrangler-commands.md`**: Need CLI commands for managing workflow instances, debugging stuck workflows, or monitoring production.\n\n**`references\u002Fproduction-checklist.md`**: Preparing for deployment, need pre-deployment verification, setting up monitoring\u002Ferror handling.\n\n**`references\u002Flimits-quotas.md`**: Hitting instance\u002Fstep\u002Fpayload limits, optimizing for cost, designing high-volume workflows.\n\n**`references\u002F2025-features.md`**: Using events system, enhanced retries, instance lifecycle control, or latest Workflows features.\n\n**`references\u002Fmetrics-analytics.md`**: Setting up monitoring, custom metrics, external logging integration, or workflow dashboards.\n\n**`references\u002Ftroubleshooting.md`**: Complex debugging scenarios, stuck instances, systematic diagnosis, performance issues.\n\n**`templates\u002F`**: **basic-workflow.ts** (sequential), **scheduled-workflow.ts** (delays\u002Fsleep), **workflow-with-events.ts** (waitForEvent), **workflow-with-retries.ts** (custom retry), **worker-trigger.ts** (Worker triggers), **wrangler-workflows-config.jsonc** (Wrangler config), **parallel-execution-workflow.ts** (batched parallel processing), **circuit-breaker-workflow.ts** (resilient external calls)\n\n---\n\n## Wrangler Commands\n\n**Key Commands**: `wrangler workflows create`, `wrangler workflows instances list\u002Fdescribe\u002Fterminate`, `wrangler deploy`\n\n**Load `references\u002Fwrangler-commands.md` for complete CLI reference with all workflow management commands, monitoring workflows, and debugging stuck instances.**\n\n---\n\n## State Persistence\n\nWorkflows automatically persist state between steps. No manual state management needed:\n\n```typescript\nexport class StatefulWorkflow extends WorkflowEntrypoint {\n  async run(event, step) {\n    \u002F\u002F Step 1 result is automatically persisted\n    const result1 = await step.do('step 1', async () => {\n      return { data: 'value' };\n    });\n\n    \u002F\u002F Even if workflow crashes here, step 1 won't re-run\n    await step.sleep('wait', '1 hour');\n\n    \u002F\u002F Step 2 can use step 1's result (still available after sleep)\n    await step.do('step 2', async () => {\n      console.log(result1.data); \u002F\u002F 'value' - persisted!\n    });\n  }\n}\n```\n\n**Key Points**:\n- Step results automatically persisted\n- Completed steps never re-run (even after crash\u002Frestart)\n- State available throughout workflow lifetime\n\n---\n\n## Limits\n\n| Resource | Limit |\n|----------|-------|\n| **Step CPU Time** | 30 seconds |\n| **Workflow Duration** | 30 days |\n| **Step Payload Size** | 128 KB |\n| **Workflow Payload Size** | 128 KB |\n| **Steps per Workflow** | 1,000 |\n| **Concurrent Instances** | 1,000 per workflow |\n| **Event Payload Size** | 128 KB |\n\n**Workarounds**:\n- Large data: Store in KV\u002FR2, pass key in step\n- Long CPU: Break into smaller steps\n- Many steps: Consider sub-workflows\n\n## Pricing\n\n- **Duration**: $0.02 per million GB-s (same as Workers)\n- **Requests**: $0.15 per million (workflow creation + step execution)\n- **State Storage**: Included (no additional cost)\n- **Sleep**: Free (no CPU usage during sleep)\n\n**Example Cost** (1M workflow runs):\n- 5 steps each = 5M requests = $0.75\n- 10ms per step = 50GB-s = $0.001\n- **Total**: ~$0.75 per million workflows\n\n---\n\n## Troubleshooting\n\n### \"I\u002FO context\" error\n**Solution**: Move all I\u002FO into `step.do()` callbacks → See `references\u002Fcommon-issues.md` #1\n\n### \"Serialization error\"\n**Solution**: Return only JSON-serializable data from steps → See `references\u002Fcommon-issues.md` #2\n\n### Workflow retries forever\n**Solution**: Throw `NonRetryableError` for permanent failures → See `references\u002Fcommon-issues.md` #3\n\n### \"WorkflowEvent not found\"\n**Solution**: Ensure event names match exactly → See `references\u002Fcommon-issues.md` #4\n\n### \"Step timeout exceeded\"\n**Solution**: Break long computations into smaller steps → See `references\u002Fcommon-issues.md` #5\n\n---\n\n## Production Checklist\n\n**10-Point Pre-Deployment Checklist**: I\u002FO context isolation, JSON serialization, NonRetryableError usage, event name consistency, step duration limits, error handling, retry configuration, timeouts, workflow naming, and monitoring.\n\n**Load `references\u002Fproduction-checklist.md` for complete checklist with detailed explanations, code examples, verification steps, and deployment workflow.**\n\n---\n\n## Official Documentation\n\n**Workflows**: https:\u002F\u002Fdevelopers.cloudflare.com\u002Fworkflows\u002F • **API Reference**: https:\u002F\u002Fdevelopers.cloudflare.com\u002Fworkflows\u002Freference\u002F • **Examples**: https:\u002F\u002Fdevelopers.cloudflare.com\u002Fworkflows\u002Fexamples\u002F • **Blog**: https:\u002F\u002Fblog.cloudflare.com\u002Fcloudflare-workflows\u002F\n",{"name":5,"license":15,"metadata":24,"description":7},{"version":25,"keywords":26,"last_verified":43,"agents_included":44,"errors_prevented":45,"scripts_included":45,"wrangler_version":46,"commands_included":47,"templates_included":48,"references_included":48,"workers_types_version":49},"3.0.0",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"cloudflare workflows","workflows workers","durable execution","workflow step","WorkflowEntrypoint","step.do","step.sleep","workflow retries","NonRetryableError","workflow state","wrangler workflows","workflow events","long-running tasks","step.sleepUntil","step.waitForEvent","workflow bindings","2025-12-27",3,5,"4.50.0",4,8,"4.20251126.0","main","c475fc64e94e803b50d14a791dfee8853fbb2c5c","integrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fcloudflare-workflows\u002Fskills\u002Fcloudflare-workflows","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory","https:\u002F\u002Fgithub.com\u002FElogic360","2026-11-08 22:21:22",{"source":8,"skillName":5,"commands":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add Elogic360\u002Fsoftware-factory --skill cloudflare-workflows",{"tool":62,"command":63},"bunx","bunx skills add Elogic360\u002Fsoftware-factory --skill cloudflare-workflows",{"tool":65,"command":66},"pnpm","pnpm dlx skills add Elogic360\u002Fsoftware-factory --skill cloudflare-workflows","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fcloudflare-workflows\u002Fskills\u002Fcloudflare-workflows\u002FSKILL.md",true,[70,76,80,84,88,92,96,100,104,110,114,118,122,126,130,134],{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002F2025-features.md","REFERENCE","参考文档",8096,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fcloudflare-workflows\u002Fskills\u002Fcloudflare-workflows\u002Freferences\u002F2025-features.md",{"path":77,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fcommon-issues.md",10088,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fcloudflare-workflows\u002Fskills\u002Fcloudflare-workflows\u002Freferences\u002Fcommon-issues.md",{"path":81,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Flimits-quotas.md",8899,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fcloudflare-workflows\u002Fskills\u002Fcloudflare-workflows\u002Freferences\u002Flimits-quotas.md",{"path":85,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fmetrics-analytics.md",11931,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fcloudflare-workflows\u002Fskills\u002Fcloudflare-workflows\u002Freferences\u002Fmetrics-analytics.md",{"path":89,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fproduction-checklist.md",12048,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fcloudflare-workflows\u002Fskills\u002Fcloudflare-workflows\u002Freferences\u002Fproduction-checklist.md",{"path":93,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Ftroubleshooting.md",15492,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fcloudflare-workflows\u002Fskills\u002Fcloudflare-workflows\u002Freferences\u002Ftroubleshooting.md",{"path":97,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Fworkflow-patterns.md",15573,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fcloudflare-workflows\u002Fskills\u002Fcloudflare-workflows\u002Freferences\u002Fworkflow-patterns.md",{"path":101,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Fwrangler-commands.md",6805,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fcloudflare-workflows\u002Fskills\u002Fcloudflare-workflows\u002Freferences\u002Fwrangler-commands.md",{"path":105,"resourceType":106,"resourceTypeDesc":107,"sizeBytes":108,"sourceHtmlUrl":109},"templates\u002Fbasic-workflow.ts","SCRIPT","脚本",3484,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fcloudflare-workflows\u002Fskills\u002Fcloudflare-workflows\u002Ftemplates\u002Fbasic-workflow.ts",{"path":111,"resourceType":106,"resourceTypeDesc":107,"sizeBytes":112,"sourceHtmlUrl":113},"templates\u002Fcircuit-breaker-workflow.ts",12873,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fcloudflare-workflows\u002Fskills\u002Fcloudflare-workflows\u002Ftemplates\u002Fcircuit-breaker-workflow.ts",{"path":115,"resourceType":106,"resourceTypeDesc":107,"sizeBytes":116,"sourceHtmlUrl":117},"templates\u002Fparallel-execution-workflow.ts",8784,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fcloudflare-workflows\u002Fskills\u002Fcloudflare-workflows\u002Ftemplates\u002Fparallel-execution-workflow.ts",{"path":119,"resourceType":106,"resourceTypeDesc":107,"sizeBytes":120,"sourceHtmlUrl":121},"templates\u002Fscheduled-workflow.ts",7403,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fcloudflare-workflows\u002Fskills\u002Fcloudflare-workflows\u002Ftemplates\u002Fscheduled-workflow.ts",{"path":123,"resourceType":106,"resourceTypeDesc":107,"sizeBytes":124,"sourceHtmlUrl":125},"templates\u002Fworker-trigger.ts",6761,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fcloudflare-workflows\u002Fskills\u002Fcloudflare-workflows\u002Ftemplates\u002Fworker-trigger.ts",{"path":127,"resourceType":106,"resourceTypeDesc":107,"sizeBytes":128,"sourceHtmlUrl":129},"templates\u002Fworkflow-with-events.ts",9382,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fcloudflare-workflows\u002Fskills\u002Fcloudflare-workflows\u002Ftemplates\u002Fworkflow-with-events.ts",{"path":131,"resourceType":106,"resourceTypeDesc":107,"sizeBytes":132,"sourceHtmlUrl":133},"templates\u002Fworkflow-with-retries.ts",6355,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fcloudflare-workflows\u002Fskills\u002Fcloudflare-workflows\u002Ftemplates\u002Fworkflow-with-retries.ts",{"path":135,"resourceType":136,"resourceTypeDesc":137,"sizeBytes":138,"sourceHtmlUrl":139},"templates\u002Fwrangler-workflows-config.jsonc","OTHER","其他",3842,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fcloudflare-workflows\u002Fskills\u002Fcloudflare-workflows\u002Ftemplates\u002Fwrangler-workflows-config.jsonc",[141,149,156,163,170,177],{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":145,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":148,"publishedAt":19},"01M79G206MT3J6S0GY3C45P2KV","vss-summarize-video","Use to summarize a recorded video via the LVS summarization microservice (HITL-gated) with a VLM fallback. Not for report generation or live RTSP captioning.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-summarize-video\u002FSKILL.md",[],[],{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":145,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":155,"publishedAt":19},"01M79G1WN63PGRE8CKD47WEBQ5","vss-setup-video-analytics-api","Use to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optional Kafka). Not for full warehouse deploy.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-setup-video-analytics-api\u002FSKILL.md",[],[],{"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":145,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":162,"publishedAt":19},"01M79G1S9F7VY3EF6H53PRP5AN","vss-setup-behavior-analytics","Use to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). Not for the full warehouse deploy.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-setup-behavior-analytics\u002FSKILL.md",[],[],{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":145,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":169,"publishedAt":19},"01M79G1N1S1Y27PFZPYMNK1MTQ","vss-search-archive","Use this skill to run top-level VSS fusion search on archived video, or to ingest video files \u002F RTSP streams for search. Do NOT use for ad-hoc visual Q&A (use vss-ask-video), live captioning (use vss-deploy-dense-captioning), or video summarization and reports (use vss-summarize-video).","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-search-archive\u002FSKILL.md",[],[],{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":145,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":176,"publishedAt":19},"01M79G1H6WN0Q6C0VCAXCZX6B7","vss-query-analytics","Use this skill when reading video-analytics metrics, incidents, alerts, and sensor data via the VA-MCP server (port 9901). Not for live VLM or incident-range narrative reports.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-query-analytics\u002FSKILL.md",[],[],{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":145,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":183,"publishedAt":19},"01M79G1DYPNXQS7QHZ0AAF5FX5","vss-manage-video-io-storage","Use to call the VIOS REST API (sensor list, timelines, clip extraction, snapshots, add\u002Fdelete sensors and streams). Not for VLM inference or search.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-manage-video-io-storage\u002FSKILL.md",[],[]]