[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77YJSG0HERAFPY39T4RRM08":3,"skill-same:01M77YJSG0HERAFPY39T4RRM08":52},{"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":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":34,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":36,"updatedAt":37,"install":38,"resources":51},"01M77YJSG0HERAFPY39T4RRM08","workflow-migrate",null,"Migrate N8N\u002FZapier\u002FMake workflows to production-grade Python or Node.js scripts. Given a workflow description or paste, rewrites automation logic with retry, backoff, logging, and self-healing. Billable migration deliverable.","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fw\u002Fworkflow-migrate\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\r\nname: workflow-migrate\r\ndescription: Migrate N8N\u002FZapier\u002FMake workflows to production-grade Python or Node.js scripts. Given a workflow description or paste, rewrites automation logic with retry, backoff, logging, and self-healing. Billable migration deliverable.\r\nargument-hint: [workflow description, or paste workflow JSON\u002Fsteps, or type \"paste\" to describe inline]\r\nallowed-tools: Read, Write, Edit, Bash, Glob, Grep, WebSearch\r\n---\r\n\r\n# Workflow Migrate — Automation Migration Tool\r\n\r\n## Why This Exists\r\nN8N\u002FZapier\u002FMake workflows break silently, can't be version-controlled, and cost $50-500\u002Fmonth in SaaS fees. This skill rewrites them as standalone scripts that run forever with zero subscription cost. Each migration is a $500-5000 billable deliverable.\r\n\r\n## Trigger\r\nUse when: \"migrate this workflow\", \"convert N8N to Python\", \"rewrite my Zapier\", \"turn this automation into a script\", \"get off N8N\"\r\n\r\nInvoked as: `\u002Fworkflow-migrate [workflow description or paste]`\r\n\r\n---\r\n\r\n## Process\r\n\r\n### Step 1: Parse the Workflow Input\r\n\r\nFrom `$ARGUMENTS`:\r\n- If it's a description (\"when a form is submitted, send email and update Airtable\"): parse directly\r\n- If it's N8N JSON: read and extract nodes\u002Fconnections\r\n- If it's Zapier steps: parse the trigger + action chain\r\n- If it's Make (formerly Integromat) scenario: parse modules\r\n\r\nExtract and document:\r\n\r\n**Triggers:**\r\n- Webhook (POST endpoint)\r\n- Cron\u002Fschedule (every X minutes\u002Fhours)\r\n- Form submission\r\n- Email received\r\n- File drop (S3, Google Drive, local folder)\r\n- DB row created\u002Fupdated\r\n\r\n**Actions:**\r\n- HTTP\u002FAPI calls (list each endpoint, method, payload)\r\n- Database reads\u002Fwrites\r\n- Email sends\r\n- File operations\r\n- Conditional logic (if\u002Felse branches)\r\n- Loops over arrays\r\n- Data transformations\r\n\r\n**Data flow:**\r\n- Input payload fields used\r\n- Intermediate computed values\r\n- Output destinations\r\n\r\nIf the workflow description is too vague, ask 2-3 targeted questions before proceeding:\r\n- \"What triggers it — webhook, schedule, or something else?\"\r\n- \"Which API endpoints does it call and with what data?\"\r\n- \"What counts as success? What should happen on failure?\"\r\n\r\n---\r\n\r\n### Step 2: Choose Language\r\n\r\n**Default to Python** unless:\r\n- The workflow is heavily async\u002Fevent-driven (prefer Node.js)\r\n- Existing codebase is Node.js\r\n- Kevin explicitly requests Node\r\n\r\nPython stack: `requests`, `schedule`, `logging`, `tenacity` (retry), `python-dotenv`\r\nNode.js stack: `axios`, `node-cron`, `winston`, `async-retry`, `dotenv`\r\n\r\n---\r\n\r\n### Step 3: Write the Script\r\n\r\nGenerate a complete, runnable script. Required elements:\r\n\r\n#### Python Template Structure:\r\n```python\r\n#!\u002Fusr\u002Fbin\u002Fenv python3\r\n\"\"\"\r\n[Workflow Name] — Migrated from [N8N\u002FZapier\u002FMake]\r\nOriginal: [brief description of what the workflow did]\r\nMigrated: [date]\r\n\r\nUsage:\r\n  python workflow_[name].py                    # run once\r\n  python workflow_[name].py --schedule         # run on schedule\r\n  python workflow_[name].py --dry-run          # test without side effects\r\n\"\"\"\r\n\r\nimport os\r\nimport sys\r\nimport logging\r\nimport time\r\nimport argparse\r\nfrom datetime import datetime\r\nfrom typing import Optional, Dict, Any\r\n\r\nimport requests\r\nfrom tenacity import retry, stop_after_attempt, wait_exponential, retry_if_exception_type\r\nfrom dotenv import load_dotenv\r\n\r\nload_dotenv()\r\n\r\n# ─── Logging ───────────────────────────────────────────────────────────────────\r\nlogging.basicConfig(\r\n    level=logging.INFO,\r\n    format=\"%(asctime)s [%(levelname)s] %(message)s\",\r\n    handlers=[\r\n        logging.StreamHandler(sys.stdout),\r\n        logging.FileHandler(f\"logs\u002Fworkflow_{datetime.now().strftime('%Y%m')}.log\"),\r\n    ]\r\n)\r\nlog = logging.getLogger(__name__)\r\n\r\n# ─── Config ────────────────────────────────────────────────────────────────────\r\nAPI_KEY = os.getenv(\"API_KEY\")         # from .env\r\nWEBHOOK_URL = os.getenv(\"WEBHOOK_URL\") # destination\r\nDRY_RUN = False\r\n\r\n# ─── Retry Decorator ───────────────────────────────────────────────────────────\r\n@retry(\r\n    stop=stop_after_attempt(3),\r\n    wait=wait_exponential(multiplier=1, min=2, max=30),\r\n    retry=retry_if_exception_type((requests.RequestException, ConnectionError)),\r\n    before_sleep=lambda rs: log.warning(f\"Retrying (attempt {rs.attempt_number})...\"),\r\n    reraise=True\r\n)\r\ndef api_call(method: str, url: str, **kwargs) -> Dict[str, Any]:\r\n    \"\"\"Make an HTTP call with automatic retry and exponential backoff.\"\"\"\r\n    if DRY_RUN:\r\n        log.info(f\"[DRY RUN] {method.upper()} {url} payload={kwargs.get('json', {})}\")\r\n        return {\"dry_run\": True}\r\n    resp = requests.request(method, url, timeout=30, **kwargs)\r\n    resp.raise_for_status()\r\n    return resp.json()\r\n```\r\n\r\n#### Node.js Template Structure:\r\n```javascript\r\n#!\u002Fusr\u002Fbin\u002Fenv node\r\n\u002F**\r\n * [Workflow Name] — Migrated from [N8N\u002FZapier\u002FMake]\r\n * Original: [brief description]\r\n * Migrated: [date]\r\n *\r\n * Usage:\r\n *   node workflow_[name].js            # run once\r\n *   node workflow_[name].js --schedule # run on schedule\r\n *   node workflow_[name].js --dry-run  # test without side effects\r\n *\u002F\r\n\r\nrequire('dotenv').config();\r\nconst axios = require('axios');\r\nconst retry = require('async-retry');\r\nconst cron = require('node-cron');\r\nconst winston = require('winston');\r\nconst fs = require('fs');\r\n\r\n\u002F\u002F ─── Logger ────────────────────────────────────────────────────────────────────\r\nconst logger = winston.createLogger({\r\n  level: 'info',\r\n  format: winston.format.combine(winston.format.timestamp(), winston.format.json()),\r\n  transports: [\r\n    new winston.transports.Console({ format: winston.format.simple() }),\r\n    new winston.transports.File({ filename: `logs\u002Fworkflow_${new Date().toISOString().slice(0,7)}.log` }),\r\n  ],\r\n});\r\n\r\n\u002F\u002F ─── Config ────────────────────────────────────────────────────────────────────\r\nconst API_KEY = process.env.API_KEY;\r\nconst DRY_RUN = process.argv.includes('--dry-run');\r\n\r\n\u002F\u002F ─── Retry Wrapper ─────────────────────────────────────────────────────────────\r\nasync function apiCall(method, url, data = {}, headers = {}) {\r\n  return retry(async (bail, attempt) => {\r\n    if (DRY_RUN) {\r\n      logger.info(`[DRY RUN] ${method.toUpperCase()} ${url}`, { data });\r\n      return { dry_run: true };\r\n    }\r\n    try {\r\n      const resp = await axios({ method, url, data, headers, timeout: 30000 });\r\n      return resp.data;\r\n    } catch (err) {\r\n      if (err.response && err.response.status \u003C 500) bail(err); \u002F\u002F 4xx = don't retry\r\n      logger.warn(`Retrying attempt ${attempt}...`, { error: err.message });\r\n      throw err;\r\n    }\r\n  }, { retries: 3, minTimeout: 2000, maxTimeout: 30000, factor: 2 });\r\n}\r\n```\r\n\r\n**For each action in the workflow, write a dedicated function:**\r\n- One function per logical action (e.g., `fetch_leads()`, `send_notification()`, `update_database()`)\r\n- Functions are composable and testable in isolation\r\n- Every function logs what it's doing: start, result, any errors\r\n\r\n**Main orchestrator:**\r\n```python\r\ndef run(dry_run: bool = False):\r\n    global DRY_RUN\r\n    DRY_RUN = dry_run\r\n    log.info(\"=== Workflow started ===\")\r\n    try:\r\n        # Step 1: [action name]\r\n        data = fetch_source_data()\r\n        log.info(f\"Fetched {len(data)} records\")\r\n\r\n        # Step 2: [action name]\r\n        for item in data:\r\n            result = process_item(item)\r\n            if result:\r\n                send_to_destination(result)\r\n\r\n        log.info(\"=== Workflow completed successfully ===\")\r\n    except Exception as e:\r\n        log.error(f\"Workflow failed: {e}\", exc_info=True)\r\n        send_alert(f\"Workflow [name] failed: {e}\")  # self-healing alert\r\n        raise\r\n```\r\n\r\n**Self-healing patterns to include:**\r\n- Alert on failure (Telegram message via Kevin's bot token if available, else log to file)\r\n- Idempotency: skip already-processed records (use a state file or DB flag)\r\n- Dead-letter queue: failed items saved to `failed_[date].json` for manual review\r\n- Heartbeat: log \"still alive\" every N runs for scheduled workflows\r\n\r\n---\r\n\r\n### Step 4: Generate .env.example\r\n\r\n```bash\r\n# [Workflow Name] — Environment Variables\r\n# Copy to .env and fill in values\r\n\r\nAPI_KEY=your_api_key_here\r\nWEBHOOK_URL=https:\u002F\u002F...\r\nDATABASE_URL=...\r\n\r\n# Optional: Telegram alerts on failure\r\nTELEGRAM_BOT_TOKEN=\r\nTELEGRAM_CHAT_ID=8062428674\r\n```\r\n\r\n---\r\n\r\n### Step 5: Generate requirements.txt or package.json\r\n\r\n**Python:**\r\n```\r\nrequests>=2.31.0\r\ntenacity>=8.2.0\r\npython-dotenv>=1.0.0\r\nschedule>=1.2.0  # only if cron-triggered\r\n```\r\n\r\n**Node.js:**\r\n```json\r\n{\r\n  \"dependencies\": {\r\n    \"axios\": \"^1.6.0\",\r\n    \"async-retry\": \"^1.3.3\",\r\n    \"node-cron\": \"^3.0.3\",\r\n    \"winston\": \"^3.11.0\",\r\n    \"dotenv\": \"^16.3.1\"\r\n  }\r\n}\r\n```\r\n\r\n---\r\n\r\n### Step 6: If the Workflow is Recurring — Generate a SKILL.md\r\n\r\nIf the workflow runs on a schedule or will be reused:\r\n- Generate a `SKILL.md` in the same output directory\r\n- Name it after the workflow function\r\n- Description: \"Run [workflow name] — [what it does in 10 words]\"\r\n- Instructions: path to script, how to run it, what env vars are needed\r\n\r\n---\r\n\r\n### Step 7: Save Outputs and Print Migration Summary\r\n\r\n**Output location:** Ask Kevin where to save, default to `.\u002Fworkflow_[name]\u002F`\r\n\r\nCreate:\r\n- `workflow_[name].py` (or `.js`)\r\n- `.env.example`\r\n- `requirements.txt` (or `package.json`)\r\n- `SKILL.md` (if recurring)\r\n- `README.md` (quick usage guide — 20 lines max)\r\n\r\n**Print migration summary:**\r\n```\r\nMigration complete.\r\n\r\nOriginal: [N8N\u002FZapier\u002FMake] workflow — [X] nodes\u002Fsteps\r\nOutput:   .\u002Fworkflow_[name]\u002Fworkflow_[name].py\r\n\r\nWhat changed:\r\n  - [X] N8N nodes → [Y] lines of Python\r\n  - Added: retry with exponential backoff (3 attempts, 2s-30s)\r\n  - Added: rotating log file (monthly)\r\n  - Added: dry-run mode (--dry-run flag)\r\n  - Added: failure alerts via [Telegram\u002Flog]\r\n  - Removed: $XX\u002Fmonth SaaS subscription\r\n\r\nTo run:\r\n  cd workflow_[name]\u002F\r\n  cp .env.example .env   # fill in your keys\r\n  pip install -r requirements.txt\r\n  python workflow_[name].py --dry-run   # test first\r\n  python workflow_[name].py             # run for real\r\n```\r\n\r\n---\r\n\r\n## Error Handling\r\n\r\n- **Ambiguous workflow**: ask 2-3 targeted questions, don't guess at API endpoints\r\n- **Proprietary N8N nodes** (e.g., OpenAI node): rewrite using the raw API — include API docs link in comments\r\n- **Very complex workflow (>15 nodes)**: break into multiple scripts with a coordinator, document the dependency order\r\n- **No credentials visible**: generate .env.example with clear placeholders, add comments explaining where each key comes from\r\n- **Webhook trigger**: generate a Flask\u002FExpress endpoint stub that receives the webhook and calls the workflow function\r\n\r\n## Notes\r\n- Always test with `--dry-run` before running for real\r\n- State file for idempotency: `.\u002Fstate\u002Fprocessed_ids.json` — create `state\u002F` dir if it doesn't exist\r\n- For scheduled runs, prefer `cron` \u002F `schedule` over external task runners (fewer dependencies)\r\n","# Workflow Migrate — Automation Migration Tool\r\n\r\n## Why This Exists\r\nN8N\u002FZapier\u002FMake workflows break silently, can't be version-controlled, and cost $50-500\u002Fmonth in SaaS fees. This skill rewrites them as standalone scripts that run forever with zero subscription cost. Each migration is a $500-5000 billable deliverable.\r\n\r\n## Trigger\r\nUse when: \"migrate this workflow\", \"convert N8N to Python\", \"rewrite my Zapier\", \"turn this automation into a script\", \"get off N8N\"\r\n\r\nInvoked as: `\u002Fworkflow-migrate [workflow description or paste]`\r\n\r\n---\r\n\r\n## Process\r\n\r\n### Step 1: Parse the Workflow Input\r\n\r\nFrom `$ARGUMENTS`:\r\n- If it's a description (\"when a form is submitted, send email and update Airtable\"): parse directly\r\n- If it's N8N JSON: read and extract nodes\u002Fconnections\r\n- If it's Zapier steps: parse the trigger + action chain\r\n- If it's Make (formerly Integromat) scenario: parse modules\r\n\r\nExtract and document:\r\n\r\n**Triggers:**\r\n- Webhook (POST endpoint)\r\n- Cron\u002Fschedule (every X minutes\u002Fhours)\r\n- Form submission\r\n- Email received\r\n- File drop (S3, Google Drive, local folder)\r\n- DB row created\u002Fupdated\r\n\r\n**Actions:**\r\n- HTTP\u002FAPI calls (list each endpoint, method, payload)\r\n- Database reads\u002Fwrites\r\n- Email sends\r\n- File operations\r\n- Conditional logic (if\u002Felse branches)\r\n- Loops over arrays\r\n- Data transformations\r\n\r\n**Data flow:**\r\n- Input payload fields used\r\n- Intermediate computed values\r\n- Output destinations\r\n\r\nIf the workflow description is too vague, ask 2-3 targeted questions before proceeding:\r\n- \"What triggers it — webhook, schedule, or something else?\"\r\n- \"Which API endpoints does it call and with what data?\"\r\n- \"What counts as success? What should happen on failure?\"\r\n\r\n---\r\n\r\n### Step 2: Choose Language\r\n\r\n**Default to Python** unless:\r\n- The workflow is heavily async\u002Fevent-driven (prefer Node.js)\r\n- Existing codebase is Node.js\r\n- Kevin explicitly requests Node\r\n\r\nPython stack: `requests`, `schedule`, `logging`, `tenacity` (retry), `python-dotenv`\r\nNode.js stack: `axios`, `node-cron`, `winston`, `async-retry`, `dotenv`\r\n\r\n---\r\n\r\n### Step 3: Write the Script\r\n\r\nGenerate a complete, runnable script. Required elements:\r\n\r\n#### Python Template Structure:\r\n```python\r\n#!\u002Fusr\u002Fbin\u002Fenv python3\r\n\"\"\"\r\n[Workflow Name] — Migrated from [N8N\u002FZapier\u002FMake]\r\nOriginal: [brief description of what the workflow did]\r\nMigrated: [date]\r\n\r\nUsage:\r\n  python workflow_[name].py                    # run once\r\n  python workflow_[name].py --schedule         # run on schedule\r\n  python workflow_[name].py --dry-run          # test without side effects\r\n\"\"\"\r\n\r\nimport os\r\nimport sys\r\nimport logging\r\nimport time\r\nimport argparse\r\nfrom datetime import datetime\r\nfrom typing import Optional, Dict, Any\r\n\r\nimport requests\r\nfrom tenacity import retry, stop_after_attempt, wait_exponential, retry_if_exception_type\r\nfrom dotenv import load_dotenv\r\n\r\nload_dotenv()\r\n\r\n# ─── Logging ───────────────────────────────────────────────────────────────────\r\nlogging.basicConfig(\r\n    level=logging.INFO,\r\n    format=\"%(asctime)s [%(levelname)s] %(message)s\",\r\n    handlers=[\r\n        logging.StreamHandler(sys.stdout),\r\n        logging.FileHandler(f\"logs\u002Fworkflow_{datetime.now().strftime('%Y%m')}.log\"),\r\n    ]\r\n)\r\nlog = logging.getLogger(__name__)\r\n\r\n# ─── Config ────────────────────────────────────────────────────────────────────\r\nAPI_KEY = os.getenv(\"API_KEY\")         # from .env\r\nWEBHOOK_URL = os.getenv(\"WEBHOOK_URL\") # destination\r\nDRY_RUN = False\r\n\r\n# ─── Retry Decorator ───────────────────────────────────────────────────────────\r\n@retry(\r\n    stop=stop_after_attempt(3),\r\n    wait=wait_exponential(multiplier=1, min=2, max=30),\r\n    retry=retry_if_exception_type((requests.RequestException, ConnectionError)),\r\n    before_sleep=lambda rs: log.warning(f\"Retrying (attempt {rs.attempt_number})...\"),\r\n    reraise=True\r\n)\r\ndef api_call(method: str, url: str, **kwargs) -> Dict[str, Any]:\r\n    \"\"\"Make an HTTP call with automatic retry and exponential backoff.\"\"\"\r\n    if DRY_RUN:\r\n        log.info(f\"[DRY RUN] {method.upper()} {url} payload={kwargs.get('json', {})}\")\r\n        return {\"dry_run\": True}\r\n    resp = requests.request(method, url, timeout=30, **kwargs)\r\n    resp.raise_for_status()\r\n    return resp.json()\r\n```\r\n\r\n#### Node.js Template Structure:\r\n```javascript\r\n#!\u002Fusr\u002Fbin\u002Fenv node\r\n\u002F**\r\n * [Workflow Name] — Migrated from [N8N\u002FZapier\u002FMake]\r\n * Original: [brief description]\r\n * Migrated: [date]\r\n *\r\n * Usage:\r\n *   node workflow_[name].js            # run once\r\n *   node workflow_[name].js --schedule # run on schedule\r\n *   node workflow_[name].js --dry-run  # test without side effects\r\n *\u002F\r\n\r\nrequire('dotenv').config();\r\nconst axios = require('axios');\r\nconst retry = require('async-retry');\r\nconst cron = require('node-cron');\r\nconst winston = require('winston');\r\nconst fs = require('fs');\r\n\r\n\u002F\u002F ─── Logger ────────────────────────────────────────────────────────────────────\r\nconst logger = winston.createLogger({\r\n  level: 'info',\r\n  format: winston.format.combine(winston.format.timestamp(), winston.format.json()),\r\n  transports: [\r\n    new winston.transports.Console({ format: winston.format.simple() }),\r\n    new winston.transports.File({ filename: `logs\u002Fworkflow_${new Date().toISOString().slice(0,7)}.log` }),\r\n  ],\r\n});\r\n\r\n\u002F\u002F ─── Config ────────────────────────────────────────────────────────────────────\r\nconst API_KEY = process.env.API_KEY;\r\nconst DRY_RUN = process.argv.includes('--dry-run');\r\n\r\n\u002F\u002F ─── Retry Wrapper ─────────────────────────────────────────────────────────────\r\nasync function apiCall(method, url, data = {}, headers = {}) {\r\n  return retry(async (bail, attempt) => {\r\n    if (DRY_RUN) {\r\n      logger.info(`[DRY RUN] ${method.toUpperCase()} ${url}`, { data });\r\n      return { dry_run: true };\r\n    }\r\n    try {\r\n      const resp = await axios({ method, url, data, headers, timeout: 30000 });\r\n      return resp.data;\r\n    } catch (err) {\r\n      if (err.response && err.response.status \u003C 500) bail(err); \u002F\u002F 4xx = don't retry\r\n      logger.warn(`Retrying attempt ${attempt}...`, { error: err.message });\r\n      throw err;\r\n    }\r\n  }, { retries: 3, minTimeout: 2000, maxTimeout: 30000, factor: 2 });\r\n}\r\n```\r\n\r\n**For each action in the workflow, write a dedicated function:**\r\n- One function per logical action (e.g., `fetch_leads()`, `send_notification()`, `update_database()`)\r\n- Functions are composable and testable in isolation\r\n- Every function logs what it's doing: start, result, any errors\r\n\r\n**Main orchestrator:**\r\n```python\r\ndef run(dry_run: bool = False):\r\n    global DRY_RUN\r\n    DRY_RUN = dry_run\r\n    log.info(\"=== Workflow started ===\")\r\n    try:\r\n        # Step 1: [action name]\r\n        data = fetch_source_data()\r\n        log.info(f\"Fetched {len(data)} records\")\r\n\r\n        # Step 2: [action name]\r\n        for item in data:\r\n            result = process_item(item)\r\n            if result:\r\n                send_to_destination(result)\r\n\r\n        log.info(\"=== Workflow completed successfully ===\")\r\n    except Exception as e:\r\n        log.error(f\"Workflow failed: {e}\", exc_info=True)\r\n        send_alert(f\"Workflow [name] failed: {e}\")  # self-healing alert\r\n        raise\r\n```\r\n\r\n**Self-healing patterns to include:**\r\n- Alert on failure (Telegram message via Kevin's bot token if available, else log to file)\r\n- Idempotency: skip already-processed records (use a state file or DB flag)\r\n- Dead-letter queue: failed items saved to `failed_[date].json` for manual review\r\n- Heartbeat: log \"still alive\" every N runs for scheduled workflows\r\n\r\n---\r\n\r\n### Step 4: Generate .env.example\r\n\r\n```bash\r\n# [Workflow Name] — Environment Variables\r\n# Copy to .env and fill in values\r\n\r\nAPI_KEY=your_api_key_here\r\nWEBHOOK_URL=https:\u002F\u002F...\r\nDATABASE_URL=...\r\n\r\n# Optional: Telegram alerts on failure\r\nTELEGRAM_BOT_TOKEN=\r\nTELEGRAM_CHAT_ID=8062428674\r\n```\r\n\r\n---\r\n\r\n### Step 5: Generate requirements.txt or package.json\r\n\r\n**Python:**\r\n```\r\nrequests>=2.31.0\r\ntenacity>=8.2.0\r\npython-dotenv>=1.0.0\r\nschedule>=1.2.0  # only if cron-triggered\r\n```\r\n\r\n**Node.js:**\r\n```json\r\n{\r\n  \"dependencies\": {\r\n    \"axios\": \"^1.6.0\",\r\n    \"async-retry\": \"^1.3.3\",\r\n    \"node-cron\": \"^3.0.3\",\r\n    \"winston\": \"^3.11.0\",\r\n    \"dotenv\": \"^16.3.1\"\r\n  }\r\n}\r\n```\r\n\r\n---\r\n\r\n### Step 6: If the Workflow is Recurring — Generate a SKILL.md\r\n\r\nIf the workflow runs on a schedule or will be reused:\r\n- Generate a `SKILL.md` in the same output directory\r\n- Name it after the workflow function\r\n- Description: \"Run [workflow name] — [what it does in 10 words]\"\r\n- Instructions: path to script, how to run it, what env vars are needed\r\n\r\n---\r\n\r\n### Step 7: Save Outputs and Print Migration Summary\r\n\r\n**Output location:** Ask Kevin where to save, default to `.\u002Fworkflow_[name]\u002F`\r\n\r\nCreate:\r\n- `workflow_[name].py` (or `.js`)\r\n- `.env.example`\r\n- `requirements.txt` (or `package.json`)\r\n- `SKILL.md` (if recurring)\r\n- `README.md` (quick usage guide — 20 lines max)\r\n\r\n**Print migration summary:**\r\n```\r\nMigration complete.\r\n\r\nOriginal: [N8N\u002FZapier\u002FMake] workflow — [X] nodes\u002Fsteps\r\nOutput:   .\u002Fworkflow_[name]\u002Fworkflow_[name].py\r\n\r\nWhat changed:\r\n  - [X] N8N nodes → [Y] lines of Python\r\n  - Added: retry with exponential backoff (3 attempts, 2s-30s)\r\n  - Added: rotating log file (monthly)\r\n  - Added: dry-run mode (--dry-run flag)\r\n  - Added: failure alerts via [Telegram\u002Flog]\r\n  - Removed: $XX\u002Fmonth SaaS subscription\r\n\r\nTo run:\r\n  cd workflow_[name]\u002F\r\n  cp .env.example .env   # fill in your keys\r\n  pip install -r requirements.txt\r\n  python workflow_[name].py --dry-run   # test first\r\n  python workflow_[name].py             # run for real\r\n```\r\n\r\n---\r\n\r\n## Error Handling\r\n\r\n- **Ambiguous workflow**: ask 2-3 targeted questions, don't guess at API endpoints\r\n- **Proprietary N8N nodes** (e.g., OpenAI node): rewrite using the raw API — include API docs link in comments\r\n- **Very complex workflow (>15 nodes)**: break into multiple scripts with a coordinator, document the dependency order\r\n- **No credentials visible**: generate .env.example with clear placeholders, add comments explaining where each key comes from\r\n- **Webhook trigger**: generate a Flask\u002FExpress endpoint stub that receives the webhook and calls the workflow function\r\n\r\n## Notes\r\n- Always test with `--dry-run` before running for real\r\n- State file for idempotency: `.\u002Fstate\u002Fprocessed_ids.json` — create `state\u002F` dir if it doesn't exist\r\n- For scheduled runs, prefer `cron` \u002F `schedule` over external task runners (fewer dependencies)\r\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":25},"Read, Write, Edit, Bash, Glob, Grep, WebSearch",[26,27,28],"workflow description","or paste workflow JSON\u002Fsteps","or type \"paste\" to describe inline","master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fw\u002Fworkflow-migrate",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill workflow-migrate",{"tool":44,"command":45},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill workflow-migrate",{"tool":47,"command":48},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill workflow-migrate","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fw\u002Fworkflow-migrate\u002FSKILL.md",true,[],[53,60,67,74,81,88],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]