[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M752DW9JB3WVST3WWNEK7CBF":3,"skill-same:01M752DW9JB3WVST3WWNEK7CBF":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":29,"commitSha":30,"skillDirectory":5,"forksCount":14,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":6,"updatedAt":34,"install":35,"resources":48},"01M752DW9JB3WVST3WWNEK7CBF","langchain-incident-runbook",null,"Incident response procedures for LangChain production issues.\nUse when responding to production incidents, diagnosing outages,\nor implementing emergency procedures for LLM applications.\nTrigger with phrases like \"langchain incident\", \"langchain outage\",\n\"langchain production issue\", \"langchain emergency\", \"langchain down\".","SamuelChien\u002Fmega-skills-collection","SamuelChien","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F4652114?v=4","01M74KK34WVHA0P5ZYSJRDDFMG","Samuel Chien","01M74KK35FQN1N9VZ9EPTH3P2S",0,"MIT","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Flangchain-incident-runbook\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: langchain-incident-runbook\ndescription: |\n  Incident response procedures for LangChain production issues.\n  Use when responding to production incidents, diagnosing outages,\n  or implementing emergency procedures for LLM applications.\n  Trigger with phrases like \"langchain incident\", \"langchain outage\",\n  \"langchain production issue\", \"langchain emergency\", \"langchain down\".\nallowed-tools: Read, Write, Edit, Bash(curl:*), Grep\nversion: 1.0.0\nlicense: MIT\nauthor: Jeremy Longshore \u003Cjeremy@intentsolutions.io>\ncompatible-with: claude-code, codex, openclaw\n---\n# LangChain Incident Runbook\n\n## Overview\nStandard operating procedures for responding to LangChain production incidents with diagnosis, mitigation, and recovery steps.\n\n## Prerequisites\n- Access to production infrastructure\n- Monitoring dashboards configured\n- LangSmith or equivalent tracing\n- On-call rotation established\n\n## Incident Classification\n\n### Severity Levels\n| Level | Description | Response Time | Examples |\n|-------|-------------|---------------|----------|\n| SEV1 | Complete outage | 15 min | All LLM calls failing |\n| SEV2 | Major degradation | 30 min | 50%+ error rate, >10s latency |\n| SEV3 | Minor degradation | 2 hours | \u003C10% errors, slow responses |\n| SEV4 | Low impact | 24 hours | Intermittent issues |\n\n## Runbook: LLM Provider Outage\n\n### Detection\n```bash\nset -euo pipefail\n# Check if LLM provider is responding\ncurl -s https:\u002F\u002Fstatus.openai.com\u002Fapi\u002Fv2\u002Fstatus.json | jq '.status.indicator'\ncurl -s https:\u002F\u002Fstatus.anthropic.com\u002Fapi\u002Fv2\u002Fstatus.json | jq '.status.indicator'\n\n# Check your error rate\n# Prometheus query:\n# sum(rate(langchain_llm_requests_total{status=\"error\"}[5m])) \u002F sum(rate(langchain_llm_requests_total[5m]))\n```\n\n### Diagnosis\n```python\n# Quick diagnostic script\nimport asyncio\nfrom langchain_openai import ChatOpenAI\nfrom langchain_anthropic import ChatAnthropic\n\nasync def diagnose_providers():\n    \"\"\"Check all configured providers.\"\"\"\n    results = {}\n\n    # Test OpenAI\n    try:\n        llm = ChatOpenAI(model=\"gpt-4o-mini\", request_timeout=10)\n        await llm.ainvoke(\"test\")\n        results[\"openai\"] = \"OK\"\n    except Exception as e:\n        results[\"openai\"] = f\"FAIL: {e}\"\n\n    # Test Anthropic\n    try:\n        llm = ChatAnthropic(model=\"claude-3-5-sonnet-20241022\", timeout=10)  # 20241022 = date\u002Fversion stamp\n        await llm.ainvoke(\"test\")\n        results[\"anthropic\"] = \"OK\"\n    except Exception as e:\n        results[\"anthropic\"] = f\"FAIL: {e}\"\n\n    return results\n\n# Run\nprint(asyncio.run(diagnose_providers()))\n```\n\n### Mitigation: Enable Fallback\n```python\n# Emergency fallback configuration\nfrom langchain_openai import ChatOpenAI\nfrom langchain_anthropic import ChatAnthropic\n\n# Original\nllm = ChatOpenAI(model=\"gpt-4o-mini\")\n\n# With fallback\nprimary = ChatOpenAI(model=\"gpt-4o-mini\", max_retries=1, request_timeout=5)\nfallback = ChatAnthropic(model=\"claude-3-haiku-20240307\")  # 20240307 = configured value\n\nllm = primary.with_fallbacks([fallback])\n```\n\n### Recovery\n1. Monitor provider status page\n2. Gradually remove fallback when primary recovers\n3. Document incident in post-mortem\n\n---\n\n## Runbook: High Error Rate\n\n### Detection\n```bash\n# Check recent errors in logs\ngrep -i \"error\" \u002Fvar\u002Flog\u002Flangchain\u002Fapp.log | tail -50\n\n# Check LangSmith for failed traces\n# Navigate to: https:\u002F\u002Fsmith.langchain.com\u002Fo\u002FYOUR_ORG\u002Fprojects\u002FYOUR_PROJECT\u002Fruns?filter=error%3Atrue\n```\n\n### Diagnosis\n```python\n# Analyze error distribution\nfrom collections import Counter\nimport json\n\ndef analyze_errors(log_file: str) -> dict:\n    \"\"\"Analyze error patterns from logs.\"\"\"\n    errors = []\n\n    with open(log_file) as f:\n        for line in f:\n            if \"error\" in line.lower():\n                try:\n                    log = json.loads(line)\n                    errors.append(log.get(\"error_type\", \"unknown\"))\n                except:\n                    pass\n\n    return dict(Counter(errors).most_common(10))\n\n# Common error types and causes\nERROR_CAUSES = {\n    \"RateLimitError\": \"Exceeded API quota - reduce load or increase limits\",\n    \"AuthenticationError\": \"Invalid API key - check secrets\",\n    \"Timeout\": \"Network issues or overloaded provider\",\n    \"OutputParserException\": \"LLM output format changed - check prompts\",\n    \"ValidationError\": \"Schema mismatch - update Pydantic models\",\n}\n```\n\n### Mitigation\n```python\n# 1. Reduce load\n# Scale down instances or enable circuit breaker\n\n# 2. Emergency rate limiting\nfrom functools import wraps\nimport time\n\ndef emergency_rate_limit(calls_per_minute: int = 10):\n    \"\"\"Emergency rate limiter decorator.\"\"\"\n    interval = 60.0 \u002F calls_per_minute\n    last_call = [0]\n\n    def decorator(func):\n        @wraps(func)\n        async def wrapper(*args, **kwargs):\n            elapsed = time.time() - last_call[0]\n            if elapsed \u003C interval:\n                await asyncio.sleep(interval - elapsed)\n            last_call[0] = time.time()\n            return await func(*args, **kwargs)\n        return wrapper\n    return decorator\n\n# 3. Enable caching for repeated queries\nfrom langchain_core.globals import set_llm_cache\nfrom langchain_community.cache import InMemoryCache\nset_llm_cache(InMemoryCache())\n```\n\n---\n\n## Runbook: Memory\u002FPerformance Issues\n\n### Detection\n```bash\n# Check memory usage\nps aux | grep python | head -5\n\n# Check for memory leaks\n# Prometheus: process_resident_memory_bytes\n```\n\n### Diagnosis\n```python\n# Memory profiling\nimport tracemalloc\n\ntracemalloc.start()\n\n# Run your chain\nchain.invoke({\"input\": \"test\"})\n\nsnapshot = tracemalloc.take_snapshot()\ntop_stats = snapshot.statistics('lineno')\n\nprint(\"Top 10 memory allocations:\")\nfor stat in top_stats[:10]:\n    print(stat)\n```\n\n### Mitigation\n```python\n# 1. Clear caches\nfrom langchain_core.globals import set_llm_cache\nset_llm_cache(None)\n\n# 2. Reduce batch sizes\n# Change from: chain.batch(inputs, config={\"max_concurrency\": 50})\n# To: chain.batch(inputs, config={\"max_concurrency\": 10})\n\n# 3. Restart pods gracefully\n# kubectl rollout restart deployment\u002Flangchain-api\n```\n\n---\n\n## Runbook: Cost Spike\n\n### Detection\n```bash\n# Check token usage\n# Prometheus: sum(increase(langchain_llm_tokens_total[1h]))\n\n# OpenAI usage dashboard\n# https:\u002F\u002Fplatform.openai.com\u002Fusage\n```\n\n### Diagnosis\n```python\n# Identify high-cost operations\ndef analyze_costs(traces: list) -> dict:\n    \"\"\"Analyze cost from trace data.\"\"\"\n    by_chain = {}\n\n    for trace in traces:\n        chain_name = trace.get(\"name\", \"unknown\")\n        tokens = trace.get(\"total_tokens\", 0)\n\n        if chain_name not in by_chain:\n            by_chain[chain_name] = {\"count\": 0, \"tokens\": 0}\n\n        by_chain[chain_name][\"count\"] += 1\n        by_chain[chain_name][\"tokens\"] += tokens\n\n    return sorted(by_chain.items(), key=lambda x: x[1][\"tokens\"], reverse=True)\n```\n\n### Mitigation\n```python\n# 1. Emergency budget limit\nclass BudgetExceeded(Exception):\n    pass\n\ndaily_spend = 0\nDAILY_LIMIT = 100.0  # $100\n\ndef check_budget(cost: float):\n    global daily_spend\n    daily_spend += cost\n    if daily_spend > DAILY_LIMIT:\n        raise BudgetExceeded(f\"Daily limit ${DAILY_LIMIT} exceeded\")\n\n# 2. Switch to cheaper model\n# gpt-4o -> gpt-4o-mini (30x cheaper)\n# claude-3-5-sonnet -> claude-3-haiku (12x cheaper)\n\n# 3. Enable aggressive caching\n```\n\n---\n\n## Incident Response Checklist\n\n### During Incident\n- [ ] Acknowledge incident in Slack\u002FPagerDuty\n- [ ] Identify severity level\n- [ ] Start incident channel\u002Fcall\n- [ ] Begin diagnosis\n- [ ] Implement mitigation\n- [ ] Communicate status to stakeholders\n- [ ] Document timeline\n\n### Post-Incident\n- [ ] Verify full recovery\n- [ ] Update status page\n- [ ] Schedule post-mortem\n- [ ] Write incident report\n- [ ] Create follow-up tickets\n- [ ] Update runbooks\n\n## Resources\n- [OpenAI Status](https:\u002F\u002Fstatus.openai.com)\n- [Anthropic Status](https:\u002F\u002Fstatus.anthropic.com)\n- [LangSmith](https:\u002F\u002Fsmith.langchain.com)\n- [PagerDuty Best Practices](https:\u002F\u002Fresponse.pagerduty.com\u002F)\n\n## Next Steps\nUse `langchain-debug-bundle` for detailed evidence collection.\n\n## Instructions\n\n1. Assess the current state of the Langchain Incident Runbook configuration\n2. Identify the specific requirements and constraints\n3. Apply the recommended patterns from this skill\n4. Validate the changes against expected behavior\n5. Document the configuration for team reference\n\n## Output\n\n- Configuration files or code changes applied to the project\n- Validation report confirming correct implementation\n- Summary of changes made and their rationale\n\n## Error Handling\n\n| Error | Cause | Resolution |\n|-------|-------|------------|\n| Authentication failure | Invalid or expired credentials | Refresh tokens or re-authenticate with Langchain Incident Runbook |\n| Configuration conflict | Incompatible settings detected | Review and resolve conflicting parameters |\n| Resource not found | Referenced resource missing | Verify resource exists and permissions are correct |\n\n## Examples\n\n**Basic usage**: Apply langchain incident runbook to a standard project setup with default configuration options.\n\n**Advanced scenario**: Customize langchain incident runbook for production environments with multiple constraints and team-specific requirements.","# LangChain Incident Runbook\n\n## Overview\nStandard operating procedures for responding to LangChain production incidents with diagnosis, mitigation, and recovery steps.\n\n## Prerequisites\n- Access to production infrastructure\n- Monitoring dashboards configured\n- LangSmith or equivalent tracing\n- On-call rotation established\n\n## Incident Classification\n\n### Severity Levels\n| Level | Description | Response Time | Examples |\n|-------|-------------|---------------|----------|\n| SEV1 | Complete outage | 15 min | All LLM calls failing |\n| SEV2 | Major degradation | 30 min | 50%+ error rate, >10s latency |\n| SEV3 | Minor degradation | 2 hours | \u003C10% errors, slow responses |\n| SEV4 | Low impact | 24 hours | Intermittent issues |\n\n## Runbook: LLM Provider Outage\n\n### Detection\n```bash\nset -euo pipefail\n# Check if LLM provider is responding\ncurl -s https:\u002F\u002Fstatus.openai.com\u002Fapi\u002Fv2\u002Fstatus.json | jq '.status.indicator'\ncurl -s https:\u002F\u002Fstatus.anthropic.com\u002Fapi\u002Fv2\u002Fstatus.json | jq '.status.indicator'\n\n# Check your error rate\n# Prometheus query:\n# sum(rate(langchain_llm_requests_total{status=\"error\"}[5m])) \u002F sum(rate(langchain_llm_requests_total[5m]))\n```\n\n### Diagnosis\n```python\n# Quick diagnostic script\nimport asyncio\nfrom langchain_openai import ChatOpenAI\nfrom langchain_anthropic import ChatAnthropic\n\nasync def diagnose_providers():\n    \"\"\"Check all configured providers.\"\"\"\n    results = {}\n\n    # Test OpenAI\n    try:\n        llm = ChatOpenAI(model=\"gpt-4o-mini\", request_timeout=10)\n        await llm.ainvoke(\"test\")\n        results[\"openai\"] = \"OK\"\n    except Exception as e:\n        results[\"openai\"] = f\"FAIL: {e}\"\n\n    # Test Anthropic\n    try:\n        llm = ChatAnthropic(model=\"claude-3-5-sonnet-20241022\", timeout=10)  # 20241022 = date\u002Fversion stamp\n        await llm.ainvoke(\"test\")\n        results[\"anthropic\"] = \"OK\"\n    except Exception as e:\n        results[\"anthropic\"] = f\"FAIL: {e}\"\n\n    return results\n\n# Run\nprint(asyncio.run(diagnose_providers()))\n```\n\n### Mitigation: Enable Fallback\n```python\n# Emergency fallback configuration\nfrom langchain_openai import ChatOpenAI\nfrom langchain_anthropic import ChatAnthropic\n\n# Original\nllm = ChatOpenAI(model=\"gpt-4o-mini\")\n\n# With fallback\nprimary = ChatOpenAI(model=\"gpt-4o-mini\", max_retries=1, request_timeout=5)\nfallback = ChatAnthropic(model=\"claude-3-haiku-20240307\")  # 20240307 = configured value\n\nllm = primary.with_fallbacks([fallback])\n```\n\n### Recovery\n1. Monitor provider status page\n2. Gradually remove fallback when primary recovers\n3. Document incident in post-mortem\n\n---\n\n## Runbook: High Error Rate\n\n### Detection\n```bash\n# Check recent errors in logs\ngrep -i \"error\" \u002Fvar\u002Flog\u002Flangchain\u002Fapp.log | tail -50\n\n# Check LangSmith for failed traces\n# Navigate to: https:\u002F\u002Fsmith.langchain.com\u002Fo\u002FYOUR_ORG\u002Fprojects\u002FYOUR_PROJECT\u002Fruns?filter=error%3Atrue\n```\n\n### Diagnosis\n```python\n# Analyze error distribution\nfrom collections import Counter\nimport json\n\ndef analyze_errors(log_file: str) -> dict:\n    \"\"\"Analyze error patterns from logs.\"\"\"\n    errors = []\n\n    with open(log_file) as f:\n        for line in f:\n            if \"error\" in line.lower():\n                try:\n                    log = json.loads(line)\n                    errors.append(log.get(\"error_type\", \"unknown\"))\n                except:\n                    pass\n\n    return dict(Counter(errors).most_common(10))\n\n# Common error types and causes\nERROR_CAUSES = {\n    \"RateLimitError\": \"Exceeded API quota - reduce load or increase limits\",\n    \"AuthenticationError\": \"Invalid API key - check secrets\",\n    \"Timeout\": \"Network issues or overloaded provider\",\n    \"OutputParserException\": \"LLM output format changed - check prompts\",\n    \"ValidationError\": \"Schema mismatch - update Pydantic models\",\n}\n```\n\n### Mitigation\n```python\n# 1. Reduce load\n# Scale down instances or enable circuit breaker\n\n# 2. Emergency rate limiting\nfrom functools import wraps\nimport time\n\ndef emergency_rate_limit(calls_per_minute: int = 10):\n    \"\"\"Emergency rate limiter decorator.\"\"\"\n    interval = 60.0 \u002F calls_per_minute\n    last_call = [0]\n\n    def decorator(func):\n        @wraps(func)\n        async def wrapper(*args, **kwargs):\n            elapsed = time.time() - last_call[0]\n            if elapsed \u003C interval:\n                await asyncio.sleep(interval - elapsed)\n            last_call[0] = time.time()\n            return await func(*args, **kwargs)\n        return wrapper\n    return decorator\n\n# 3. Enable caching for repeated queries\nfrom langchain_core.globals import set_llm_cache\nfrom langchain_community.cache import InMemoryCache\nset_llm_cache(InMemoryCache())\n```\n\n---\n\n## Runbook: Memory\u002FPerformance Issues\n\n### Detection\n```bash\n# Check memory usage\nps aux | grep python | head -5\n\n# Check for memory leaks\n# Prometheus: process_resident_memory_bytes\n```\n\n### Diagnosis\n```python\n# Memory profiling\nimport tracemalloc\n\ntracemalloc.start()\n\n# Run your chain\nchain.invoke({\"input\": \"test\"})\n\nsnapshot = tracemalloc.take_snapshot()\ntop_stats = snapshot.statistics('lineno')\n\nprint(\"Top 10 memory allocations:\")\nfor stat in top_stats[:10]:\n    print(stat)\n```\n\n### Mitigation\n```python\n# 1. Clear caches\nfrom langchain_core.globals import set_llm_cache\nset_llm_cache(None)\n\n# 2. Reduce batch sizes\n# Change from: chain.batch(inputs, config={\"max_concurrency\": 50})\n# To: chain.batch(inputs, config={\"max_concurrency\": 10})\n\n# 3. Restart pods gracefully\n# kubectl rollout restart deployment\u002Flangchain-api\n```\n\n---\n\n## Runbook: Cost Spike\n\n### Detection\n```bash\n# Check token usage\n# Prometheus: sum(increase(langchain_llm_tokens_total[1h]))\n\n# OpenAI usage dashboard\n# https:\u002F\u002Fplatform.openai.com\u002Fusage\n```\n\n### Diagnosis\n```python\n# Identify high-cost operations\ndef analyze_costs(traces: list) -> dict:\n    \"\"\"Analyze cost from trace data.\"\"\"\n    by_chain = {}\n\n    for trace in traces:\n        chain_name = trace.get(\"name\", \"unknown\")\n        tokens = trace.get(\"total_tokens\", 0)\n\n        if chain_name not in by_chain:\n            by_chain[chain_name] = {\"count\": 0, \"tokens\": 0}\n\n        by_chain[chain_name][\"count\"] += 1\n        by_chain[chain_name][\"tokens\"] += tokens\n\n    return sorted(by_chain.items(), key=lambda x: x[1][\"tokens\"], reverse=True)\n```\n\n### Mitigation\n```python\n# 1. Emergency budget limit\nclass BudgetExceeded(Exception):\n    pass\n\ndaily_spend = 0\nDAILY_LIMIT = 100.0  # $100\n\ndef check_budget(cost: float):\n    global daily_spend\n    daily_spend += cost\n    if daily_spend > DAILY_LIMIT:\n        raise BudgetExceeded(f\"Daily limit ${DAILY_LIMIT} exceeded\")\n\n# 2. Switch to cheaper model\n# gpt-4o -> gpt-4o-mini (30x cheaper)\n# claude-3-5-sonnet -> claude-3-haiku (12x cheaper)\n\n# 3. Enable aggressive caching\n```\n\n---\n\n## Incident Response Checklist\n\n### During Incident\n- [ ] Acknowledge incident in Slack\u002FPagerDuty\n- [ ] Identify severity level\n- [ ] Start incident channel\u002Fcall\n- [ ] Begin diagnosis\n- [ ] Implement mitigation\n- [ ] Communicate status to stakeholders\n- [ ] Document timeline\n\n### Post-Incident\n- [ ] Verify full recovery\n- [ ] Update status page\n- [ ] Schedule post-mortem\n- [ ] Write incident report\n- [ ] Create follow-up tickets\n- [ ] Update runbooks\n\n## Resources\n- [OpenAI Status](https:\u002F\u002Fstatus.openai.com)\n- [Anthropic Status](https:\u002F\u002Fstatus.anthropic.com)\n- [LangSmith](https:\u002F\u002Fsmith.langchain.com)\n- [PagerDuty Best Practices](https:\u002F\u002Fresponse.pagerduty.com\u002F)\n\n## Next Steps\nUse `langchain-debug-bundle` for detailed evidence collection.\n\n## Instructions\n\n1. Assess the current state of the Langchain Incident Runbook configuration\n2. Identify the specific requirements and constraints\n3. Apply the recommended patterns from this skill\n4. Validate the changes against expected behavior\n5. Document the configuration for team reference\n\n## Output\n\n- Configuration files or code changes applied to the project\n- Validation report confirming correct implementation\n- Summary of changes made and their rationale\n\n## Error Handling\n\n| Error | Cause | Resolution |\n|-------|-------|------------|\n| Authentication failure | Invalid or expired credentials | Refresh tokens or re-authenticate with Langchain Incident Runbook |\n| Configuration conflict | Incompatible settings detected | Review and resolve conflicting parameters |\n| Resource not found | Referenced resource missing | Verify resource exists and permissions are correct |\n\n## Examples\n\n**Basic usage**: Apply langchain incident runbook to a standard project setup with default configuration options.\n\n**Advanced scenario**: Customize langchain incident runbook for production environments with multiple constraints and team-specific requirements.",{"name":5,"author":24,"license":15,"version":25,"description":26,"allowed-tools":27,"compatible-with":28},"Jeremy Longshore \u003Cjeremy@intentsolutions.io>","1.0.0","Incident response procedures for LangChain production issues.\nUse when responding to production incidents, diagnosing outages,\nor implementing emergency procedures for LLM applications.\nTrigger with phrases like \"langchain incident\", \"langchain outage\",\n\"langchain production issue\", \"langchain emergency\", \"langchain down\".\n","Read, Write, Edit, Bash(curl:*), Grep","claude-code, codex, openclaw","main","c2b1fdccc779e99ac814e55fb69ca8d71215dd0f","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection","https:\u002F\u002Fgithub.com\u002FSamuelChien","http:\u002F\u002Fsamuelchien.com\u002F","2026-05-26 08:27:14",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add SamuelChien\u002Fmega-skills-collection --skill langchain-incident-runbook",{"tool":41,"command":42},"bunx","bunx skills add SamuelChien\u002Fmega-skills-collection --skill langchain-incident-runbook",{"tool":44,"command":45},"pnpm","pnpm dlx skills add SamuelChien\u002Fmega-skills-collection --skill langchain-incident-runbook","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Flangchain-incident-runbook\u002FSKILL.md",true,[],[50,57,64,71,78,86],{"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},"01M76R4WZQZAXGGXMQCA0FZ716","zustand-store-ts","Create Zustand stores with TypeScript, subscribeWithSelector middleware, and proper state\u002Faction separation. Use when building React state management, creating global stores, or implementing reactive state patterns with Zustand.","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fzustand-store-ts\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},"01M76R4T9KENDH7FENGZQHBW4G","zustand-store-creator","Zustand Store Creator - Auto-activating skill for Frontend Development.\nTriggers on: zustand store creator, zustand store creator\nPart of the Frontend Development skill category.","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fzustand-store-creator\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},"01M76R3YWN84B7SANJ52X799ZE","zero-trust-config-helper","Zero Trust Config Helper - Auto-activating skill for Security Advanced.\nTriggers on: zero trust config helper, zero trust config helper\nPart of the Security Advanced skill category.","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fzero-trust-config-helper\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},"01M76R3HNSV2AEYSKHM915GJ58","zapier-integration-helper","Zapier Integration Helper - Auto-activating skill for Business Automation.\nTriggers on: zapier integration helper, zapier integration helper\nPart of the Business Automation skill category.","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fzapier-integration-helper\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":82,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M76R3DJSKAT4FA7DV4BF3GCE","zai-cli","Execute z.AI CLI providing vision, search, reader, and GitHub exploration via CLI and MCP.\nUse when user needs image\u002Fvideo analysis, OCR, UI-to-code conversion, error diagnosis,\nreal-time web search, web page to markdown extraction, or GitHub code exploration.\nTrigger with phrases like \"analyze this image\", \"search the web for\", \"read this page\",\n\"explore this repo\", or \"use zai\". Requires Z_AI_API_KEY.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fzai-cli\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M76R2KAM699XE9AJVAWE4H2E","yt-research","Research competitor YouTube channels, niches, and trending topics for your content strategy.\nUse this skill whenever the user says \"research channels\", \"analyze competitors\", \"find trending topics\",\n\"niche analysis\", \"competitive research\", \"what are other creators doing\", \"scrape YouTube channels\",\nor wants to understand the competitive landscape for a specific tool or topic area. Use when working with yt research. Trigger with 'yt', 'research'.","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fyt-research\u002FSKILL.md",[],[]]