[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M754X6FWFN3TDZQEJ5S9Z9MT":3,"skill-same:01M754X6FWFN3TDZQEJ5S9Z9MT":87},{"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},"01M754X6FWFN3TDZQEJ5S9Z9MT","openrouter-context-optimization",null,"Optimize token usage and context window management. Use when reducing costs or fitting more information into model context. Trigger with phrases like 'openrouter context', 'token optimization', 'context window', 'reduce tokens'.","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\u002Fopenrouter-context-optimization\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: openrouter-context-optimization\ndescription: |\n  Optimize token usage and context window management. Use when reducing costs or fitting more information into model context. Trigger with phrases like 'openrouter context', 'token optimization', 'context window', 'reduce tokens'.\nallowed-tools: Read, Write, Edit, Grep\nversion: 1.0.0\nlicense: MIT\nauthor: Jeremy Longshore \u003Cjeremy@intentsolutions.io>\ncompatible-with: claude-code, codex, openclaw\n---\n# Openrouter Context Optimization\n\n## Overview\n\nThis skill covers techniques for managing token budgets, optimizing prompt length, and making the most of each model's context window.\n\n## Prerequisites\n\n- OpenRouter integration\n- Tokenizer library (tiktoken for OpenAI models, or approximate counting)\n\n## Instructions\n\n1. **Count tokens before sending**: Use `tiktoken` (Python) or `js-tiktoken` (JS) to estimate token counts before making API calls; abort if the prompt exceeds the model's context limit\n2. **Implement conversation pruning**: For multi-turn chats, drop or summarize older messages when total tokens approach the context limit, keeping system prompts and recent messages\n3. **Optimize system prompts**: Move static instructions to the system message and keep them concise; every token in the system prompt is repeated on every request\n4. **Use response length controls**: Set `max_tokens` to the minimum needed for your use case; shorter completions cost less and return faster\n5. **Select models by context need**: Route short-context tasks to cheaper models and reserve large-context models (128K+) for tasks that genuinely need them\n\n## Output\n\n- Token budget calculator that warns before exceeding context limits\n- Conversation pruning middleware that keeps chats within context bounds\n- Cost reduction from optimized prompt engineering (typically 20-40% savings)\n\n## Error Handling\n\n| Error | Cause | Fix |\n|-------|-------|-----|\n| 400 `context_length_exceeded` | Prompt + max_tokens exceeds model limit | Prune messages or switch to a model with a larger context window |\n| Truncated responses | `max_tokens` set too low | Increase `max_tokens` or split the task into smaller requests |\n| Token count mismatch | Wrong tokenizer for the model | Use the correct tokenizer per model family; fall back to rough estimation (1 token ~ 4 chars) |\n\nSee `${CLAUDE_SKILL_DIR}\u002Freferences\u002Ferrors.md` for full error reference.\n\n## Examples\n\nSee `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fexamples.md` for runnable code samples.\n\n## Resources\n\n- [OpenRouter Documentation](https:\u002F\u002Fopenrouter.ai\u002Fdocs)\n- [OpenRouter Models](https:\u002F\u002Fopenrouter.ai\u002Fmodels)\n- [OpenRouter API Reference](https:\u002F\u002Fopenrouter.ai\u002Fdocs\u002Fapi-reference)\n- [OpenRouter Status](https:\u002F\u002Fstatus.openrouter.ai)\n","# Openrouter Context Optimization\n\n## Overview\n\nThis skill covers techniques for managing token budgets, optimizing prompt length, and making the most of each model's context window.\n\n## Prerequisites\n\n- OpenRouter integration\n- Tokenizer library (tiktoken for OpenAI models, or approximate counting)\n\n## Instructions\n\n1. **Count tokens before sending**: Use `tiktoken` (Python) or `js-tiktoken` (JS) to estimate token counts before making API calls; abort if the prompt exceeds the model's context limit\n2. **Implement conversation pruning**: For multi-turn chats, drop or summarize older messages when total tokens approach the context limit, keeping system prompts and recent messages\n3. **Optimize system prompts**: Move static instructions to the system message and keep them concise; every token in the system prompt is repeated on every request\n4. **Use response length controls**: Set `max_tokens` to the minimum needed for your use case; shorter completions cost less and return faster\n5. **Select models by context need**: Route short-context tasks to cheaper models and reserve large-context models (128K+) for tasks that genuinely need them\n\n## Output\n\n- Token budget calculator that warns before exceeding context limits\n- Conversation pruning middleware that keeps chats within context bounds\n- Cost reduction from optimized prompt engineering (typically 20-40% savings)\n\n## Error Handling\n\n| Error | Cause | Fix |\n|-------|-------|-----|\n| 400 `context_length_exceeded` | Prompt + max_tokens exceeds model limit | Prune messages or switch to a model with a larger context window |\n| Truncated responses | `max_tokens` set too low | Increase `max_tokens` or split the task into smaller requests |\n| Token count mismatch | Wrong tokenizer for the model | Use the correct tokenizer per model family; fall back to rough estimation (1 token ~ 4 chars) |\n\nSee `${CLAUDE_SKILL_DIR}\u002Freferences\u002Ferrors.md` for full error reference.\n\n## Examples\n\nSee `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fexamples.md` for runnable code samples.\n\n## Resources\n\n- [OpenRouter Documentation](https:\u002F\u002Fopenrouter.ai\u002Fdocs)\n- [OpenRouter Models](https:\u002F\u002Fopenrouter.ai\u002Fmodels)\n- [OpenRouter API Reference](https:\u002F\u002Fopenrouter.ai\u002Fdocs\u002Fapi-reference)\n- [OpenRouter Status](https:\u002F\u002Fstatus.openrouter.ai)\n",{"name":5,"author":24,"license":15,"version":25,"description":26,"allowed-tools":27,"compatible-with":28},"Jeremy Longshore \u003Cjeremy@intentsolutions.io>","1.0.0","Optimize token usage and context window management. Use when reducing costs or fitting more information into model context. Trigger with phrases like 'openrouter context', 'token optimization', 'context window', 'reduce tokens'.\n","Read, Write, Edit, 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 openrouter-context-optimization",{"tool":41,"command":42},"bunx","bunx skills add SamuelChien\u002Fmega-skills-collection --skill openrouter-context-optimization",{"tool":44,"command":45},"pnpm","pnpm dlx skills add SamuelChien\u002Fmega-skills-collection --skill openrouter-context-optimization","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fopenrouter-context-optimization\u002FSKILL.md",true,[49,55,59,63,67,71,75,79,83],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fcontext-recycling.md","REFERENCE","参考文档",1958,"https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fopenrouter-context-optimization\u002Freferences\u002Fcontext-recycling.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fcontext-truncation.md",2876,"https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fopenrouter-context-optimization\u002Freferences\u002Fcontext-truncation.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fefficient-message-patterns.md",1931,"https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fopenrouter-context-optimization\u002Freferences\u002Fefficient-message-patterns.md",{"path":64,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Ferrors.md",323,"https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fopenrouter-context-optimization\u002Freferences\u002Ferrors.md",{"path":68,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fexamples.md",3746,"https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fopenrouter-context-optimization\u002Freferences\u002Fexamples.md",{"path":72,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Fmodel-specific-optimization.md",1067,"https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fopenrouter-context-optimization\u002Freferences\u002Fmodel-specific-optimization.md",{"path":76,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fprompt-optimization.md",2022,"https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fopenrouter-context-optimization\u002Freferences\u002Fprompt-optimization.md",{"path":80,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fresponse-length-control.md",987,"https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fopenrouter-context-optimization\u002Freferences\u002Fresponse-length-control.md",{"path":84,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Ftoken-estimation.md",1546,"https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fopenrouter-context-optimization\u002Freferences\u002Ftoken-estimation.md",[88,95,102,109,116,124],{"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},"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":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"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":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"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":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"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":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":120,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"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":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"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",[],[]]