[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M752FWWTSSFNQWAMFKB5NBGA":3,"skill-same:01M752FWWTSSFNQWAMFKB5NBGA":55},{"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},"01M752FWWTSSFNQWAMFKB5NBGA","langfuse-cost-tuning",null,"Monitor and optimize LLM costs using Langfuse analytics and dashboards.\nUse when tracking LLM spending, identifying cost anomalies,\nor implementing cost controls for AI applications.\nTrigger with phrases like \"langfuse costs\", \"LLM spending\",\n\"track AI costs\", \"langfuse token usage\", \"optimize LLM budget\".","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\u002Flangfuse-cost-tuning\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: langfuse-cost-tuning\ndescription: |\n  Monitor and optimize LLM costs using Langfuse analytics and dashboards.\n  Use when tracking LLM spending, identifying cost anomalies,\n  or implementing cost controls for AI applications.\n  Trigger with phrases like \"langfuse costs\", \"LLM spending\",\n  \"track AI costs\", \"langfuse token usage\", \"optimize LLM budget\".\nallowed-tools: Read, Write, Edit\nversion: 1.0.0\nlicense: MIT\nauthor: Jeremy Longshore \u003Cjeremy@intentsolutions.io>\ncompatible-with: claude-code, codex, openclaw\n---\n# Langfuse Cost Tuning\n\n## Contents\n- [Overview](#overview)\n- [Prerequisites](#prerequisites)\n- [Instructions](#instructions)\n- [Output](#output)\n- [Error Handling](#error-handling)\n- [Examples](#examples)\n- [Resources](#resources)\n\n## Overview\nTrack, analyze, and optimize LLM costs using Langfuse observability data with token tracking, cost alerts, model selection optimization, and automated reporting.\n\n## Prerequisites\n- Langfuse tracing with token usage\n- Understanding of LLM pricing models\n- Access to Langfuse analytics dashboard\n\n## Instructions\n\n### Step 1: Track Token Usage in Generations\nRecord prompt and completion tokens on each `generation.end()` call. Calculate cost using per-model pricing tables and store as metadata.\n\n### Step 2: Create Cost Dashboard Queries\nFetch generations from Langfuse and aggregate costs by model, by day, and by token type. Calculate total cost and generation count.\n\n### Step 3: Implement Cost Alerts\nBuild a CostMonitor that tracks hourly and daily spend. Define thresholds (e.g., $100\u002Fday warn, $500\u002Fday notify, $1\u002Frequest warn). Send Slack\u002FPagerDuty notifications on breaches.\n\n### Step 4: Optimize Model Selection\nRoute simple tasks (summarize, classify, extract) and short inputs to cheaper models (GPT-4o-mini). Reserve expensive models for complex tasks (analyze, reason, code).\n\n### Step 5: Add Caching and Prompt Optimization\nCache LLM responses with TTL. Strip redundant whitespace and filler words from prompts to reduce token count.\n\nSee [detailed implementation](${CLAUDE_SKILL_DIR}\u002Freferences\u002Fimplementation.md) for advanced patterns.\n\n## Output\n- Token usage tracking per generation\n- Cost analytics aggregation\n- Real-time cost alerts\n- Smart model selection\n- Response caching and prompt optimization\n\n## Error Handling\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| Missing usage data | SDK not capturing | Verify generation.end() includes usage |\n| Inaccurate costs | Wrong pricing | Update MODEL_PRICING regularly |\n| Budget exceeded | No alerts | Implement cost alerts |\n| Report failures | API limits | Add pagination to fetchGenerations |\n\n## Examples\n\n### LLM Cost Reference\n| Model | Input (per 1M) | Output (per 1M) |\n|-------|----------------|-----------------|\n| GPT-4 Turbo | $10.00 | $30.00 |\n| GPT-4o | $5.00 | $15.00 |\n| GPT-4o-mini | $0.15 | $0.60 |\n| Claude 3 Opus | $15.00 | $75.00 |\n| Claude 3 Sonnet | $3.00 | $15.00 |\n| Claude 3 Haiku | $0.25 | $1.25 |\n\n### Cost Optimization Strategies\n| Strategy | Potential Savings | Effort |\n|----------|-------------------|--------|\n| Model downgrade | 50-90% | Low |\n| Prompt optimization | 10-30% | Low |\n| Response caching | 20-60% | Medium |\n| Batch processing | 10-20% | Medium |\n\n## Resources\n- [Langfuse Analytics](https:\u002F\u002Flangfuse.com\u002Fdocs\u002Fanalytics)\n- [OpenAI Pricing](https:\u002F\u002Fopenai.com\u002Fpricing)\n- [Anthropic Pricing](https:\u002F\u002Fwww.anthropic.com\u002Fpricing)","# Langfuse Cost Tuning\n\n## Contents\n- [Overview](#overview)\n- [Prerequisites](#prerequisites)\n- [Instructions](#instructions)\n- [Output](#output)\n- [Error Handling](#error-handling)\n- [Examples](#examples)\n- [Resources](#resources)\n\n## Overview\nTrack, analyze, and optimize LLM costs using Langfuse observability data with token tracking, cost alerts, model selection optimization, and automated reporting.\n\n## Prerequisites\n- Langfuse tracing with token usage\n- Understanding of LLM pricing models\n- Access to Langfuse analytics dashboard\n\n## Instructions\n\n### Step 1: Track Token Usage in Generations\nRecord prompt and completion tokens on each `generation.end()` call. Calculate cost using per-model pricing tables and store as metadata.\n\n### Step 2: Create Cost Dashboard Queries\nFetch generations from Langfuse and aggregate costs by model, by day, and by token type. Calculate total cost and generation count.\n\n### Step 3: Implement Cost Alerts\nBuild a CostMonitor that tracks hourly and daily spend. Define thresholds (e.g., $100\u002Fday warn, $500\u002Fday notify, $1\u002Frequest warn). Send Slack\u002FPagerDuty notifications on breaches.\n\n### Step 4: Optimize Model Selection\nRoute simple tasks (summarize, classify, extract) and short inputs to cheaper models (GPT-4o-mini). Reserve expensive models for complex tasks (analyze, reason, code).\n\n### Step 5: Add Caching and Prompt Optimization\nCache LLM responses with TTL. Strip redundant whitespace and filler words from prompts to reduce token count.\n\nSee [detailed implementation](${CLAUDE_SKILL_DIR}\u002Freferences\u002Fimplementation.md) for advanced patterns.\n\n## Output\n- Token usage tracking per generation\n- Cost analytics aggregation\n- Real-time cost alerts\n- Smart model selection\n- Response caching and prompt optimization\n\n## Error Handling\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| Missing usage data | SDK not capturing | Verify generation.end() includes usage |\n| Inaccurate costs | Wrong pricing | Update MODEL_PRICING regularly |\n| Budget exceeded | No alerts | Implement cost alerts |\n| Report failures | API limits | Add pagination to fetchGenerations |\n\n## Examples\n\n### LLM Cost Reference\n| Model | Input (per 1M) | Output (per 1M) |\n|-------|----------------|-----------------|\n| GPT-4 Turbo | $10.00 | $30.00 |\n| GPT-4o | $5.00 | $15.00 |\n| GPT-4o-mini | $0.15 | $0.60 |\n| Claude 3 Opus | $15.00 | $75.00 |\n| Claude 3 Sonnet | $3.00 | $15.00 |\n| Claude 3 Haiku | $0.25 | $1.25 |\n\n### Cost Optimization Strategies\n| Strategy | Potential Savings | Effort |\n|----------|-------------------|--------|\n| Model downgrade | 50-90% | Low |\n| Prompt optimization | 10-30% | Low |\n| Response caching | 20-60% | Medium |\n| Batch processing | 10-20% | Medium |\n\n## Resources\n- [Langfuse Analytics](https:\u002F\u002Flangfuse.com\u002Fdocs\u002Fanalytics)\n- [OpenAI Pricing](https:\u002F\u002Fopenai.com\u002Fpricing)\n- [Anthropic Pricing](https:\u002F\u002Fwww.anthropic.com\u002Fpricing)",{"name":5,"author":24,"license":15,"version":25,"description":26,"allowed-tools":27,"compatible-with":28},"Jeremy Longshore \u003Cjeremy@intentsolutions.io>","1.0.0","Monitor and optimize LLM costs using Langfuse analytics and dashboards.\nUse when tracking LLM spending, identifying cost anomalies,\nor implementing cost controls for AI applications.\nTrigger with phrases like \"langfuse costs\", \"LLM spending\",\n\"track AI costs\", \"langfuse token usage\", \"optimize LLM budget\".\n","Read, Write, Edit","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 langfuse-cost-tuning",{"tool":41,"command":42},"bunx","bunx skills add SamuelChien\u002Fmega-skills-collection --skill langfuse-cost-tuning",{"tool":44,"command":45},"pnpm","pnpm dlx skills add SamuelChien\u002Fmega-skills-collection --skill langfuse-cost-tuning","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Flangfuse-cost-tuning\u002FSKILL.md",true,[49],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fimplementation.md","REFERENCE","参考文档",7056,"https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Flangfuse-cost-tuning\u002Freferences\u002Fimplementation.md",[56,63,70,77,84,92],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"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":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"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":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"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":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"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":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":88,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"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",[],[]]