[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6F8XNZHTK8KTMBP33ZKY667":3,"skill-same:01M6F8XNZHTK8KTMBP33ZKY667":84},{"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":26,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":61,"commitSha":62,"skillDirectory":63,"forksCount":64,"repositoryHtmlUrl":65,"repositoryHomepageUrl":66,"ownerHtmlUrl":67,"ownerBlogUrl":6,"ownerDescription":68,"updatedAt":69,"install":70,"resources":83},"01M6F8XNZHTK8KTMBP33ZKY667","cohere-cost-tuning",null,"Optimize Cohere costs through model selection, token budgets, and usage monitoring.\nUse when analyzing Cohere billing, reducing API costs,\nor implementing usage monitoring and budget alerts.\nTrigger with phrases like \"cohere cost\", \"cohere billing\",\n\"reduce cohere costs\", \"cohere pricing\", \"cohere expensive\", \"cohere budget\".","ComeOnOliver\u002Fskillshub","ComeOnOliver","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F43215937?v=4","01M6E5JNFECJAAVFE0W7SMWWD2","Haoran Shu","01M6E5JNNDQS7AJZDYFQ8TPZCK",67,"MIT","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fjeremylongshore\u002Fclaude-code-plugins-plus-skills\u002Fcohere-cost-tuning\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000040","财务",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"cost","cohere cost tuning","cohere","tuning","analyzing","monitoring","Budget","api","model","read","pricing","selection","optimize","alerts","token","io","trigger","billing","code","model selection","2026-11-10 10:12:30",false,"---\nname: cohere-cost-tuning\ndescription: |\n  Optimize Cohere costs through model selection, token budgets, and usage monitoring.\n  Use when analyzing Cohere billing, reducing API costs,\n  or implementing usage monitoring and budget alerts.\n  Trigger with phrases like \"cohere cost\", \"cohere billing\",\n  \"reduce cohere costs\", \"cohere pricing\", \"cohere expensive\", \"cohere budget\".\nallowed-tools: Read, Grep\nversion: 1.0.0\nlicense: MIT\nauthor: Jeremy Longshore \u003Cjeremy@intentsolutions.io>\ntags: [saas, ai, nlp, cohere]\ncompatible-with: claude-code\n---\n\n# Cohere Cost Tuning\n\n## Overview\nOptimize Cohere costs through model selection, token budgets, embedding compression, and usage monitoring. Cohere pricing is token-based with separate input\u002Foutput rates.\n\n## Prerequisites\n- Cohere production key (trial is free but limited)\n- Access to [dashboard.cohere.com](https:\u002F\u002Fdashboard.cohere.com) billing page\n\n## Cohere Pricing Model\n\n**Key principle:** Cohere charges per token. Input tokens and output tokens have different rates. Embed, Rerank, and Classify have separate pricing based on search units.\n\n| Tier | Access | Rate Limits | Cost |\n|------|--------|-------------|------|\n| Trial | Free | 5-20 calls\u002Fmin, 1000\u002Fmonth | $0 |\n| Production | Metered | 1000 calls\u002Fmin, unlimited | Per-token |\n\n### Model Cost Comparison\n\n| Model | Input (per 1M tokens) | Output (per 1M tokens) | Best For |\n|-------|----------------------|------------------------|----------|\n| `command-r7b-12-2024` | Lowest | Lowest | High-volume, simple tasks |\n| `command-r-08-2024` | Low | Low | RAG, cost-effective |\n| `command-r-plus-08-2024` | Medium | Medium | Complex reasoning |\n| `command-a-03-2025` | Higher | Higher | Best quality |\n\n### Non-Chat Pricing\n\n| Endpoint | Pricing Unit | Notes |\n|----------|-------------|-------|\n| Embed | Per input token | Batch 96 texts to minimize calls |\n| Rerank | Per search unit | 1 query + N docs = 1 search unit |\n| Classify | Per classification | Charges per input classified |\n\n## Instructions\n\n### Strategy 1: Model Tiering\n\n```typescript\ntype CostTier = 'economy' | 'standard' | 'premium';\n\nfunction selectModel(tier: CostTier): string {\n  switch (tier) {\n    case 'economy':  return 'command-r7b-12-2024';    \u002F\u002F ~5x cheaper\n    case 'standard': return 'command-r-08-2024';       \u002F\u002F Good balance\n    case 'premium':  return 'command-a-03-2025';       \u002F\u002F Best quality\n  }\n}\n\n\u002F\u002F Route by use case\nfunction routeModel(task: string): string {\n  \u002F\u002F High-volume, simple tasks → cheapest model\n  if (['classify', 'extract', 'summarize-short'].includes(task)) {\n    return selectModel('economy');\n  }\n  \u002F\u002F RAG, moderate complexity\n  if (['rag', 'search', 'qa'].includes(task)) {\n    return selectModel('standard');\n  }\n  \u002F\u002F Complex reasoning, user-facing\n  return selectModel('premium');\n}\n```\n\n### Strategy 2: Token Budget Controls\n\n```typescript\nimport { CohereClientV2 } from 'cohere-ai';\n\nconst cohere = new CohereClientV2();\n\n\u002F\u002F Set maxTokens to prevent runaway generation costs\nasync function budgetedChat(message: string, maxOutputTokens = 500) {\n  const response = await cohere.chat({\n    model: 'command-r-08-2024',\n    messages: [{ role: 'user', content: message }],\n    maxTokens: maxOutputTokens,  \u002F\u002F Hard limit on output tokens\n  });\n\n  \u002F\u002F Track actual usage\n  const usage = response.usage?.billedUnits;\n  console.log(`Tokens: in=${usage?.inputTokens} out=${usage?.outputTokens}`);\n\n  return response;\n}\n```\n\n### Strategy 3: Embedding Cost Reduction\n\n```typescript\n\u002F\u002F 1. Use int8 embeddings (same quality, cheaper storage)\nconst response = await cohere.embed({\n  model: 'embed-v4.0',\n  texts: documents,\n  inputType: 'search_document',\n  embeddingTypes: ['int8'],     \u002F\u002F 75% less storage than float\n});\n\n\u002F\u002F 2. Batch to 96 per call (minimize API calls)\n\u002F\u002F 3. Cache embeddings (they're deterministic — embed once, use forever)\n\u002F\u002F 4. Use embed-multilingual-v3.0 if you don't need v4 features\n```\n\n### Strategy 4: Usage Monitoring\n\n```typescript\nclass CohereUsageTracker {\n  private usage: Record\u003Cstring, { inputTokens: number; outputTokens: number; calls: number }> = {};\n  private dailyBudget: number;\n\n  constructor(dailyBudgetUSD: number) {\n    this.dailyBudget = dailyBudgetUSD;\n  }\n\n  track(endpoint: string, billedUnits: { inputTokens?: number; outputTokens?: number }) {\n    if (!this.usage[endpoint]) {\n      this.usage[endpoint] = { inputTokens: 0, outputTokens: 0, calls: 0 };\n    }\n    this.usage[endpoint].inputTokens += billedUnits.inputTokens ?? 0;\n    this.usage[endpoint].outputTokens += billedUnits.outputTokens ?? 0;\n    this.usage[endpoint].calls++;\n  }\n\n  getReport(): string {\n    return Object.entries(this.usage)\n      .map(([ep, u]) =>\n        `${ep}: ${u.calls} calls, ${u.inputTokens} in, ${u.outputTokens} out`\n      )\n      .join('\\n');\n  }\n\n  estimateDailyCost(): number {\n    \u002F\u002F Rough estimate — check cohere.com\u002Fpricing for exact rates\n    const chatIn = (this.usage['chat']?.inputTokens ?? 0) \u002F 1_000_000;\n    const chatOut = (this.usage['chat']?.outputTokens ?? 0) \u002F 1_000_000;\n    const embedIn = (this.usage['embed']?.inputTokens ?? 0) \u002F 1_000_000;\n    \u002F\u002F Multiply by per-million-token rates from pricing page\n    return (chatIn * 0.5) + (chatOut * 1.5) + (embedIn * 0.1); \u002F\u002F example rates\n  }\n}\n\n\u002F\u002F Wrap all API calls\nconst tracker = new CohereUsageTracker(10); \u002F\u002F $10\u002Fday budget\n\nasync function trackedChat(params: any) {\n  const response = await cohere.chat(params);\n  tracker.track('chat', response.usage?.billedUnits ?? {});\n\n  if (tracker.estimateDailyCost() > tracker['dailyBudget'] * 0.8) {\n    console.warn('WARNING: Approaching daily Cohere budget limit');\n  }\n\n  return response;\n}\n```\n\n### Strategy 5: Rerank Before RAG (Skip Embed for Small Corpora)\n\n```typescript\n\u002F\u002F If you have \u003C 1000 documents, skip embedding entirely\n\u002F\u002F Rerank is cheaper than Embed + vector search for small collections\n\nasync function cheapRAG(query: string, corpus: string[]) {\n  \u002F\u002F 1 search unit instead of N embed calls\n  const ranked = await cohere.rerank({\n    model: 'rerank-v3.5',\n    query,\n    documents: corpus,\n    topN: 3,\n  });\n\n  const docs = ranked.results.map((r, i) => ({\n    id: `doc-${i}`,\n    data: { text: corpus[r.index] },\n  }));\n\n  \u002F\u002F Use cheaper model for generation\n  return cohere.chat({\n    model: 'command-r-08-2024', \u002F\u002F Not command-a (cheaper)\n    messages: [{ role: 'user', content: query }],\n    documents: docs,\n    maxTokens: 300,\n  });\n}\n```\n\n## Cost Optimization Checklist\n\n- [ ] Use `command-r7b` for simple tasks, `command-a` only for complex ones\n- [ ] Set `maxTokens` on all chat calls\n- [ ] Batch embed calls (96 texts per request)\n- [ ] Cache embeddings (deterministic — compute once)\n- [ ] Use `int8` embeddings for storage\n- [ ] Monitor `usage.billedUnits` in every response\n- [ ] Set daily budget alerts\n- [ ] Use `rerank` instead of `embed` for small corpora (\u003C 1000 docs)\n\n## Output\n- Model tiering by cost\u002Fquality\n- Token budget controls preventing runaway costs\n- Usage tracking with daily budget alerts\n- Cost-effective RAG with rerank pre-filtering\n\n## Error Handling\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| Unexpected bill spike | No maxTokens | Set maxTokens on all chat calls |\n| High embed costs | Individual texts | Batch to 96 per call |\n| Budget exceeded | No monitoring | Track billedUnits per response |\n| Over-provisioned model | Using premium everywhere | Tier models by task complexity |\n\n## Resources\n- [Cohere Pricing](https:\u002F\u002Fcohere.com\u002Fpricing)\n- [Cohere Billing Dashboard](https:\u002F\u002Fdashboard.cohere.com\u002Fbilling)\n- [Cohere Token Counting](https:\u002F\u002Fdocs.cohere.com\u002Fdocs\u002Ftokens-and-tokenizers)\n\n## Next Steps\nFor architecture patterns, see `cohere-reference-architecture`.\n\n","# Cohere Cost Tuning\n\n## Overview\nOptimize Cohere costs through model selection, token budgets, embedding compression, and usage monitoring. Cohere pricing is token-based with separate input\u002Foutput rates.\n\n## Prerequisites\n- Cohere production key (trial is free but limited)\n- Access to [dashboard.cohere.com](https:\u002F\u002Fdashboard.cohere.com) billing page\n\n## Cohere Pricing Model\n\n**Key principle:** Cohere charges per token. Input tokens and output tokens have different rates. Embed, Rerank, and Classify have separate pricing based on search units.\n\n| Tier | Access | Rate Limits | Cost |\n|------|--------|-------------|------|\n| Trial | Free | 5-20 calls\u002Fmin, 1000\u002Fmonth | $0 |\n| Production | Metered | 1000 calls\u002Fmin, unlimited | Per-token |\n\n### Model Cost Comparison\n\n| Model | Input (per 1M tokens) | Output (per 1M tokens) | Best For |\n|-------|----------------------|------------------------|----------|\n| `command-r7b-12-2024` | Lowest | Lowest | High-volume, simple tasks |\n| `command-r-08-2024` | Low | Low | RAG, cost-effective |\n| `command-r-plus-08-2024` | Medium | Medium | Complex reasoning |\n| `command-a-03-2025` | Higher | Higher | Best quality |\n\n### Non-Chat Pricing\n\n| Endpoint | Pricing Unit | Notes |\n|----------|-------------|-------|\n| Embed | Per input token | Batch 96 texts to minimize calls |\n| Rerank | Per search unit | 1 query + N docs = 1 search unit |\n| Classify | Per classification | Charges per input classified |\n\n## Instructions\n\n### Strategy 1: Model Tiering\n\n```typescript\ntype CostTier = 'economy' | 'standard' | 'premium';\n\nfunction selectModel(tier: CostTier): string {\n  switch (tier) {\n    case 'economy':  return 'command-r7b-12-2024';    \u002F\u002F ~5x cheaper\n    case 'standard': return 'command-r-08-2024';       \u002F\u002F Good balance\n    case 'premium':  return 'command-a-03-2025';       \u002F\u002F Best quality\n  }\n}\n\n\u002F\u002F Route by use case\nfunction routeModel(task: string): string {\n  \u002F\u002F High-volume, simple tasks → cheapest model\n  if (['classify', 'extract', 'summarize-short'].includes(task)) {\n    return selectModel('economy');\n  }\n  \u002F\u002F RAG, moderate complexity\n  if (['rag', 'search', 'qa'].includes(task)) {\n    return selectModel('standard');\n  }\n  \u002F\u002F Complex reasoning, user-facing\n  return selectModel('premium');\n}\n```\n\n### Strategy 2: Token Budget Controls\n\n```typescript\nimport { CohereClientV2 } from 'cohere-ai';\n\nconst cohere = new CohereClientV2();\n\n\u002F\u002F Set maxTokens to prevent runaway generation costs\nasync function budgetedChat(message: string, maxOutputTokens = 500) {\n  const response = await cohere.chat({\n    model: 'command-r-08-2024',\n    messages: [{ role: 'user', content: message }],\n    maxTokens: maxOutputTokens,  \u002F\u002F Hard limit on output tokens\n  });\n\n  \u002F\u002F Track actual usage\n  const usage = response.usage?.billedUnits;\n  console.log(`Tokens: in=${usage?.inputTokens} out=${usage?.outputTokens}`);\n\n  return response;\n}\n```\n\n### Strategy 3: Embedding Cost Reduction\n\n```typescript\n\u002F\u002F 1. Use int8 embeddings (same quality, cheaper storage)\nconst response = await cohere.embed({\n  model: 'embed-v4.0',\n  texts: documents,\n  inputType: 'search_document',\n  embeddingTypes: ['int8'],     \u002F\u002F 75% less storage than float\n});\n\n\u002F\u002F 2. Batch to 96 per call (minimize API calls)\n\u002F\u002F 3. Cache embeddings (they're deterministic — embed once, use forever)\n\u002F\u002F 4. Use embed-multilingual-v3.0 if you don't need v4 features\n```\n\n### Strategy 4: Usage Monitoring\n\n```typescript\nclass CohereUsageTracker {\n  private usage: Record\u003Cstring, { inputTokens: number; outputTokens: number; calls: number }> = {};\n  private dailyBudget: number;\n\n  constructor(dailyBudgetUSD: number) {\n    this.dailyBudget = dailyBudgetUSD;\n  }\n\n  track(endpoint: string, billedUnits: { inputTokens?: number; outputTokens?: number }) {\n    if (!this.usage[endpoint]) {\n      this.usage[endpoint] = { inputTokens: 0, outputTokens: 0, calls: 0 };\n    }\n    this.usage[endpoint].inputTokens += billedUnits.inputTokens ?? 0;\n    this.usage[endpoint].outputTokens += billedUnits.outputTokens ?? 0;\n    this.usage[endpoint].calls++;\n  }\n\n  getReport(): string {\n    return Object.entries(this.usage)\n      .map(([ep, u]) =>\n        `${ep}: ${u.calls} calls, ${u.inputTokens} in, ${u.outputTokens} out`\n      )\n      .join('\\n');\n  }\n\n  estimateDailyCost(): number {\n    \u002F\u002F Rough estimate — check cohere.com\u002Fpricing for exact rates\n    const chatIn = (this.usage['chat']?.inputTokens ?? 0) \u002F 1_000_000;\n    const chatOut = (this.usage['chat']?.outputTokens ?? 0) \u002F 1_000_000;\n    const embedIn = (this.usage['embed']?.inputTokens ?? 0) \u002F 1_000_000;\n    \u002F\u002F Multiply by per-million-token rates from pricing page\n    return (chatIn * 0.5) + (chatOut * 1.5) + (embedIn * 0.1); \u002F\u002F example rates\n  }\n}\n\n\u002F\u002F Wrap all API calls\nconst tracker = new CohereUsageTracker(10); \u002F\u002F $10\u002Fday budget\n\nasync function trackedChat(params: any) {\n  const response = await cohere.chat(params);\n  tracker.track('chat', response.usage?.billedUnits ?? {});\n\n  if (tracker.estimateDailyCost() > tracker['dailyBudget'] * 0.8) {\n    console.warn('WARNING: Approaching daily Cohere budget limit');\n  }\n\n  return response;\n}\n```\n\n### Strategy 5: Rerank Before RAG (Skip Embed for Small Corpora)\n\n```typescript\n\u002F\u002F If you have \u003C 1000 documents, skip embedding entirely\n\u002F\u002F Rerank is cheaper than Embed + vector search for small collections\n\nasync function cheapRAG(query: string, corpus: string[]) {\n  \u002F\u002F 1 search unit instead of N embed calls\n  const ranked = await cohere.rerank({\n    model: 'rerank-v3.5',\n    query,\n    documents: corpus,\n    topN: 3,\n  });\n\n  const docs = ranked.results.map((r, i) => ({\n    id: `doc-${i}`,\n    data: { text: corpus[r.index] },\n  }));\n\n  \u002F\u002F Use cheaper model for generation\n  return cohere.chat({\n    model: 'command-r-08-2024', \u002F\u002F Not command-a (cheaper)\n    messages: [{ role: 'user', content: query }],\n    documents: docs,\n    maxTokens: 300,\n  });\n}\n```\n\n## Cost Optimization Checklist\n\n- [ ] Use `command-r7b` for simple tasks, `command-a` only for complex ones\n- [ ] Set `maxTokens` on all chat calls\n- [ ] Batch embed calls (96 texts per request)\n- [ ] Cache embeddings (deterministic — compute once)\n- [ ] Use `int8` embeddings for storage\n- [ ] Monitor `usage.billedUnits` in every response\n- [ ] Set daily budget alerts\n- [ ] Use `rerank` instead of `embed` for small corpora (\u003C 1000 docs)\n\n## Output\n- Model tiering by cost\u002Fquality\n- Token budget controls preventing runaway costs\n- Usage tracking with daily budget alerts\n- Cost-effective RAG with rerank pre-filtering\n\n## Error Handling\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| Unexpected bill spike | No maxTokens | Set maxTokens on all chat calls |\n| High embed costs | Individual texts | Batch to 96 per call |\n| Budget exceeded | No monitoring | Track billedUnits per response |\n| Over-provisioned model | Using premium everywhere | Tier models by task complexity |\n\n## Resources\n- [Cohere Pricing](https:\u002F\u002Fcohere.com\u002Fpricing)\n- [Cohere Billing Dashboard](https:\u002F\u002Fdashboard.cohere.com\u002Fbilling)\n- [Cohere Token Counting](https:\u002F\u002Fdocs.cohere.com\u002Fdocs\u002Ftokens-and-tokenizers)\n\n## Next Steps\nFor architecture patterns, see `cohere-reference-architecture`.\n\n",{"name":5,"tags":52,"author":56,"license":15,"version":57,"description":58,"allowed-tools":59,"compatible-with":60},[53,54,55,29],"saas","ai","nlp","Jeremy Longshore \u003Cjeremy@intentsolutions.io>","1.0.0","Optimize Cohere costs through model selection, token budgets, and usage monitoring.\nUse when analyzing Cohere billing, reducing API costs,\nor implementing usage monitoring and budget alerts.\nTrigger with phrases like \"cohere cost\", \"cohere billing\",\n\"reduce cohere costs\", \"cohere pricing\", \"cohere expensive\", \"cohere budget\".\n","Read, Grep","claude-code","main","def8531e65114c0fca8fb8551c1871ee0eed705c","skills\u002Fjeremylongshore\u002Fclaude-code-plugins-plus-skills\u002Fcohere-cost-tuning",24,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub","https:\u002F\u002Fskillshub.wtf","https:\u002F\u002Fgithub.com\u002FComeOnOliver","AI & Blockchain Engineer\r\n","2026-06-24 22:07:19",{"source":8,"skillName":5,"commands":71,"prompt":81,"zipAvailable":82},[72,75,78],{"tool":73,"command":74},"npx","npx skills add ComeOnOliver\u002Fskillshub --skill cohere-cost-tuning",{"tool":76,"command":77},"bunx","bunx skills add ComeOnOliver\u002Fskillshub --skill cohere-cost-tuning",{"tool":79,"command":80},"pnpm","pnpm dlx skills add ComeOnOliver\u002Fskillshub --skill cohere-cost-tuning","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fjeremylongshore\u002Fclaude-code-plugins-plus-skills\u002Fcohere-cost-tuning\u002FSKILL.md",true,[],[85,98,108,117,123,130],{"skillNo":86,"name":87,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":95,"publishedAt":47},"01M6FKJN13GMG4KY57J3QD8GY5","model-hierarchy-skill","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzscole\u002Fmodel-hierarchy-skill\u002Fmodel-hierarchy-skill\u002FSKILL.md",[90],{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[35,96,97],"model hierarchy","model hierarchy skill",{"skillNo":99,"name":100,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":104,"publishedAt":47},"01M6FKJJJ6GCAMR4PPPRD12M5X","zoom-mcp","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fzoom-mcp\u002FSKILL.md",[103],{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},[105,106,107],"MCP","zoom","zoom mcp",{"skillNo":109,"name":110,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":47},"01M6FKJE3KYT3KPEZMEEHYKA6K","zoom-apps-sdk","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fzoom-apps-sdk\u002FSKILL.md",[],[114,115,116,106],"sdk","zoom apps sdk","apps",{"skillNo":118,"name":119,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":47},"01M6FKJ9EDH9Q5VWDF8HAJRSP0","windows","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwindows\u002FSKILL.md",[],[119],{"skillNo":124,"name":125,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":129,"publishedAt":47},"01M6FKJ666BEEFC3AE9GJ72Q93","whiteboard","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwhiteboard\u002FSKILL.md",[128],{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},[125],{"skillNo":131,"name":132,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":47},"01M6FKJ21WFCDGTJQ2Q91T9DVW","websockets","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwebsockets\u002FSKILL.md",[],[132]]