[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M754V7F6R81AH1NRZGYQQQ9S":3,"skill-same:01M754V7F6R81AH1NRZGYQQQ9S":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},"01M754V7F6R81AH1NRZGYQQQ9S","openevidence-rate-limits",null,"Implement OpenEvidence rate limiting, backoff, and request optimization.\nUse when handling rate limit errors, implementing retry logic,\nor optimizing API request throughput for clinical queries.\nTrigger with phrases like \"openevidence rate limit\", \"openevidence throttling\",\n\"openevidence 429\", \"openevidence retry\", \"openevidence backoff\".","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\u002Fopenevidence-rate-limits\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: openevidence-rate-limits\ndescription: |\n  Implement OpenEvidence rate limiting, backoff, and request optimization.\n  Use when handling rate limit errors, implementing retry logic,\n  or optimizing API request throughput for clinical queries.\n  Trigger with phrases like \"openevidence rate limit\", \"openevidence throttling\",\n  \"openevidence 429\", \"openevidence retry\", \"openevidence backoff\".\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# OpenEvidence Rate Limits\n\n## Overview\nRate limit management for OpenEvidence clinical query API. Clinical decision support queries are latency-sensitive but also expensive (web-scale medical literature search per query), requiring careful throughput management.\n\n## Prerequisites\n- OpenEvidence API access\n- Understanding of clinical workflow request patterns\n- Redis for rate tracking (recommended)\n\n## OpenEvidence Rate Limits\n\n| Endpoint | Limit | Window | Burst |\n|----------|-------|--------|-------|\n| Clinical Query | 60\u002Fmin | Per API key | 10 concurrent |\n| DeepConsult | 10\u002Fmin | Per API key | 2 concurrent |\n| Feedback | 120\u002Fmin | Per API key | 20 concurrent |\n\n## Instructions\n\n### Step 1: Per-Endpoint Rate Limiter\n\nClinical queries and DeepConsult have different limits. Track separately.\n\n```typescript\nclass OpenEvidenceRateLimiter {\n  private limits: Record\u003Cstring, { rpm: number; concurrent: number }> = {\n    'query': { rpm: 60, concurrent: 10 },\n    'deepconsult': { rpm: 10, concurrent: 2 },\n    'feedback': { rpm: 120, concurrent: 20 },\n  };\n  private active: Map\u003Cstring, number> = new Map();\n  private requests: Map\u003Cstring, number[]> = new Map();\n\n  async acquire(endpoint: string): Promise\u003Cvoid> {\n    const limit = this.limits[endpoint];\n    if (!limit) throw new Error(`Unknown endpoint: ${endpoint}`);\n\n    \u002F\u002F Check concurrent\n    const active = this.active.get(endpoint) || 0;\n    if (active >= limit.concurrent) {\n      await this.waitForSlot(endpoint);\n    }\n\n    \u002F\u002F Check RPM\n    const now = Date.now();\n    const times = (this.requests.get(endpoint) || []).filter(t => now - t \u003C 60000);  # 60000: 1 minute in ms\n    if (times.length >= limit.rpm) {\n      const waitMs = 60000 - (now - times[0]);  # 1 minute in ms\n      await new Promise(r => setTimeout(r, waitMs + 100));\n    }\n\n    this.active.set(endpoint, (this.active.get(endpoint) || 0) + 1);\n    times.push(Date.now());\n    this.requests.set(endpoint, times);\n  }\n\n  release(endpoint: string): void {\n    this.active.set(endpoint, Math.max(0, (this.active.get(endpoint) || 0) - 1));\n  }\n}\n```\n\n### Step 2: Clinical Query Priority Queue\n\nStat queries should preempt routine queries.\n\n```typescript\nclass ClinicalQueryQueue {\n  private statQueue: Array\u003C() => Promise\u003Cany>> = [];\n  private routineQueue: Array\u003C() => Promise\u003Cany>> = [];\n  private limiter = new OpenEvidenceRateLimiter();\n\n  async submit(query: any, urgency: 'stat' | 'routine'): Promise\u003Cany> {\n    return new Promise((resolve, reject) => {\n      const task = async () => {\n        await this.limiter.acquire('query');\n        try {\n          const result = await openevidence.query(query);\n          resolve(result);\n        } catch (e) { reject(e); }\n        finally { this.limiter.release('query'); }\n      };\n      if (urgency === 'stat') this.statQueue.push(task);\n      else this.routineQueue.push(task);\n      this.process();\n    });\n  }\n\n  private async process() {\n    const task = this.statQueue.shift() || this.routineQueue.shift();\n    if (task) await task();\n  }\n}\n```\n\n### Step 3: Backoff Strategy for 429 Responses\n\n```typescript\nasync function queryWithBackoff(query: any, maxRetries = 3): Promise\u003Cany> {\n  for (let attempt = 0; attempt \u003C= maxRetries; attempt++) {\n    try {\n      return await openevidence.query(query);\n    } catch (e: any) {\n      if (e.status === 429 && attempt \u003C maxRetries) {  # HTTP 429 Too Many Requests\n        const retryAfter = parseInt(e.headers?.['retry-after'] || '5');\n        await new Promise(r => setTimeout(r, retryAfter * 1000));  # 1000: 1 second in ms\n      } else { throw e; }\n    }\n  }\n}\n```\n\n## Error Handling\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| 429 on clinical query | Exceeded 60 RPM | Queue with priority, backoff |\n| DeepConsult rejected | Exceeded 10 RPM or 2 concurrent | Queue deep consults separately |\n| Stat query delayed | Behind routine queries | Implement priority queue |\n| Concurrent limit hit | Too many parallel queries | Track and limit active requests |\n\n## Examples\n\n\n**Basic usage**: Apply openevidence rate limits to a standard project setup with default configuration options.\n\n**Advanced scenario**: Customize openevidence rate limits for production environments with multiple constraints and team-specific requirements.\n\n## Resources\n- [OpenEvidence API](https:\u002F\u002Fwww.openevidence.com)\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","# OpenEvidence Rate Limits\n\n## Overview\nRate limit management for OpenEvidence clinical query API. Clinical decision support queries are latency-sensitive but also expensive (web-scale medical literature search per query), requiring careful throughput management.\n\n## Prerequisites\n- OpenEvidence API access\n- Understanding of clinical workflow request patterns\n- Redis for rate tracking (recommended)\n\n## OpenEvidence Rate Limits\n\n| Endpoint | Limit | Window | Burst |\n|----------|-------|--------|-------|\n| Clinical Query | 60\u002Fmin | Per API key | 10 concurrent |\n| DeepConsult | 10\u002Fmin | Per API key | 2 concurrent |\n| Feedback | 120\u002Fmin | Per API key | 20 concurrent |\n\n## Instructions\n\n### Step 1: Per-Endpoint Rate Limiter\n\nClinical queries and DeepConsult have different limits. Track separately.\n\n```typescript\nclass OpenEvidenceRateLimiter {\n  private limits: Record\u003Cstring, { rpm: number; concurrent: number }> = {\n    'query': { rpm: 60, concurrent: 10 },\n    'deepconsult': { rpm: 10, concurrent: 2 },\n    'feedback': { rpm: 120, concurrent: 20 },\n  };\n  private active: Map\u003Cstring, number> = new Map();\n  private requests: Map\u003Cstring, number[]> = new Map();\n\n  async acquire(endpoint: string): Promise\u003Cvoid> {\n    const limit = this.limits[endpoint];\n    if (!limit) throw new Error(`Unknown endpoint: ${endpoint}`);\n\n    \u002F\u002F Check concurrent\n    const active = this.active.get(endpoint) || 0;\n    if (active >= limit.concurrent) {\n      await this.waitForSlot(endpoint);\n    }\n\n    \u002F\u002F Check RPM\n    const now = Date.now();\n    const times = (this.requests.get(endpoint) || []).filter(t => now - t \u003C 60000);  # 60000: 1 minute in ms\n    if (times.length >= limit.rpm) {\n      const waitMs = 60000 - (now - times[0]);  # 1 minute in ms\n      await new Promise(r => setTimeout(r, waitMs + 100));\n    }\n\n    this.active.set(endpoint, (this.active.get(endpoint) || 0) + 1);\n    times.push(Date.now());\n    this.requests.set(endpoint, times);\n  }\n\n  release(endpoint: string): void {\n    this.active.set(endpoint, Math.max(0, (this.active.get(endpoint) || 0) - 1));\n  }\n}\n```\n\n### Step 2: Clinical Query Priority Queue\n\nStat queries should preempt routine queries.\n\n```typescript\nclass ClinicalQueryQueue {\n  private statQueue: Array\u003C() => Promise\u003Cany>> = [];\n  private routineQueue: Array\u003C() => Promise\u003Cany>> = [];\n  private limiter = new OpenEvidenceRateLimiter();\n\n  async submit(query: any, urgency: 'stat' | 'routine'): Promise\u003Cany> {\n    return new Promise((resolve, reject) => {\n      const task = async () => {\n        await this.limiter.acquire('query');\n        try {\n          const result = await openevidence.query(query);\n          resolve(result);\n        } catch (e) { reject(e); }\n        finally { this.limiter.release('query'); }\n      };\n      if (urgency === 'stat') this.statQueue.push(task);\n      else this.routineQueue.push(task);\n      this.process();\n    });\n  }\n\n  private async process() {\n    const task = this.statQueue.shift() || this.routineQueue.shift();\n    if (task) await task();\n  }\n}\n```\n\n### Step 3: Backoff Strategy for 429 Responses\n\n```typescript\nasync function queryWithBackoff(query: any, maxRetries = 3): Promise\u003Cany> {\n  for (let attempt = 0; attempt \u003C= maxRetries; attempt++) {\n    try {\n      return await openevidence.query(query);\n    } catch (e: any) {\n      if (e.status === 429 && attempt \u003C maxRetries) {  # HTTP 429 Too Many Requests\n        const retryAfter = parseInt(e.headers?.['retry-after'] || '5');\n        await new Promise(r => setTimeout(r, retryAfter * 1000));  # 1000: 1 second in ms\n      } else { throw e; }\n    }\n  }\n}\n```\n\n## Error Handling\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| 429 on clinical query | Exceeded 60 RPM | Queue with priority, backoff |\n| DeepConsult rejected | Exceeded 10 RPM or 2 concurrent | Queue deep consults separately |\n| Stat query delayed | Behind routine queries | Implement priority queue |\n| Concurrent limit hit | Too many parallel queries | Track and limit active requests |\n\n## Examples\n\n\n**Basic usage**: Apply openevidence rate limits to a standard project setup with default configuration options.\n\n**Advanced scenario**: Customize openevidence rate limits for production environments with multiple constraints and team-specific requirements.\n\n## Resources\n- [OpenEvidence API](https:\u002F\u002Fwww.openevidence.com)\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",{"name":5,"author":24,"license":15,"version":25,"description":26,"allowed-tools":27,"compatible-with":28},"Jeremy Longshore \u003Cjeremy@intentsolutions.io>","1.0.0","Implement OpenEvidence rate limiting, backoff, and request optimization.\nUse when handling rate limit errors, implementing retry logic,\nor optimizing API request throughput for clinical queries.\nTrigger with phrases like \"openevidence rate limit\", \"openevidence throttling\",\n\"openevidence 429\", \"openevidence retry\", \"openevidence backoff\".\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 openevidence-rate-limits",{"tool":41,"command":42},"bunx","bunx skills add SamuelChien\u002Fmega-skills-collection --skill openevidence-rate-limits",{"tool":44,"command":45},"pnpm","pnpm dlx skills add SamuelChien\u002Fmega-skills-collection --skill openevidence-rate-limits","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fopenevidence-rate-limits\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",[],[]]