[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CXTPTPZGATMNEP9Z6W9CWW":3,"skill-same:01M6CXTPTPZGATMNEP9Z6W9CWW":83},{"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":28,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":56,"repositoryHtmlUrl":57,"repositoryHomepageUrl":58,"ownerHtmlUrl":59,"ownerBlogUrl":60,"ownerDescription":61,"updatedAt":62,"install":63,"resources":76},"01M6CXTPTPZGATMNEP9Z6W9CWW","anthropic-expert",null,"Expert on Anthropic Claude API, models, prompt engineering, function calling, vision, and best practices. Triggers on anthropic, claude, api, prompt, function calling, vision, messages api, embeddings","eric861129\u002FSKILLS_All-in-one","eric861129","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F74950944?v=4","01M6CXHDYEYRPFGGV4EFXCSYCF","ChiYu-Huang","01M6CXHE2J5CN1EBTY0FKV3ZKW",52,"MIT","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FDevelopment & Code Tools\u002Fclaude-starter\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"anthropic expert","expert","function calling","calling","models","vision","read","prompt","grep","claude api","api","anthropic claude","engineering","messages","embeddings","best practices","prompt engineering","2026-11-10 10:12:30",false,"---\nname: anthropic-expert\ndescription: Expert on Anthropic Claude API, models, prompt engineering, function calling, vision, and best practices. Triggers on anthropic, claude, api, prompt, function calling, vision, messages api, embeddings\nallowed-tools: Read, Grep, Glob\nmodel: sonnet\n---\n\n# Anthropic API Expert\n\n## Purpose\n\nProvide expert guidance on Anthropic's Claude API, including prompt engineering, function calling, vision capabilities, and best practices based on official Anthropic documentation.\n\n## When to Use\n\nAuto-invoke when users mention:\n- **Anthropic** - company, API, platform\n- **Claude** - models (Opus, Sonnet, Haiku), capabilities\n- **API** - Messages API, streaming, embeddings\n- **Features** - function calling, vision, extended context, prompt caching\n- **Integration** - SDKs (Python, TypeScript), REST API\n\n## Knowledge Base\n\n**Full access to official Anthropic documentation (when available):**\n- **Location:** `docs\u002F`\n- **Files:** 199 markdown files\n- **Format:** `.md` files\n\n**Note:** Documentation must be pulled separately:\n```bash\npipx install docpull\ndocpull https:\u002F\u002Fdocs.anthropic.com -o .claude\u002Fskills\u002Fanthropic\u002Fdocs\n```\n\n## Process\n\nWhen a user asks about Anthropic\u002FClaude:\n\n### 1. Identify Topic\n```\nCommon topics:\n- Getting started \u002F API keys\n- Model selection (Opus, Sonnet, Haiku)\n- Messages API \u002F streaming\n- Prompt engineering techniques\n- Function\u002Ftool calling\n- Vision and image analysis\n- Extended context (200K tokens)\n- Prompt caching\n- Rate limits and pricing\n- Error handling\n```\n\n### 2. Search Documentation\n\nUse Grep to find relevant docs:\n```bash\n# Search for specific topics\nGrep \"function calling|tool\" docs\u002F --output-mode files_with_matches -i\nGrep \"vision|image\" docs\u002F --output-mode content -C 3\n```\n\nCheck the INDEX.md for navigation:\n```bash\nRead docs\u002FINDEX.md\n```\n\n### 3. Read Relevant Files\n\nRead the most relevant documentation files:\n```bash\nRead docs\u002Fpath\u002Fto\u002Frelevant-doc.md\n```\n\n### 4. Provide Answer\n\nStructure your response:\n- **Direct answer** - solve the user's problem first\n- **Code examples** - show API calls with proper formatting\n- **Best practices** - mention Claude-specific patterns\n- **Model selection** - recommend appropriate model (Opus\u002FSonnet\u002FHaiku)\n- **References** - cite specific docs for deeper reading\n- **Cost optimization** - mention prompt caching, model choice\n\n## Example Workflows\n\n### Example 1: Function Calling\n```\nUser: \"How do I implement function calling with Claude?\"\n\n1. Search: Grep \"function calling|tool\" docs\u002F\n2. Read: Function calling documentation\n3. Answer:\n   - Explain tool use format\n   - Show request\u002Fresponse example\n   - Discuss tool choice vs any\n   - Best practices for tool definitions\n```\n\n### Example 2: Vision Capabilities\n```\nUser: \"Can Claude analyze images?\"\n\n1. Search: Grep \"vision|image\" docs\u002F -i\n2. Read: Vision API documentation\n3. Answer:\n   - Supported image formats\n   - Image encoding (base64, URLs)\n   - Show example API call\n   - Limitations and best practices\n```\n\n### Example 3: Prompt Engineering\n```\nUser: \"How do I write better prompts for Claude?\"\n\n1. Search: Grep \"prompt|engineering\" docs\u002F\n2. Read: Prompt engineering guide\n3. Answer:\n   - Clear instructions principle\n   - Examples and context\n   - XML tags for structure\n   - Chain of thought prompting\n```\n\n## Key Concepts to Reference\n\n**Models:**\n- Claude 3.5 Opus - most capable\n- Claude 3.5 Sonnet - balanced (recommended for most use cases)\n- Claude 3.5 Haiku - fast and economical\n\n**API Features:**\n- Messages API (primary interface)\n- Streaming responses\n- Function\u002Ftool calling\n- Vision (image analysis)\n- Extended context (200K tokens)\n- Prompt caching (reduce costs)\n\n**Best Practices:**\n- System prompts vs user messages\n- XML tags for structure\n- Few-shot examples\n- Clear, specific instructions\n- Appropriate model selection\n\n**SDKs:**\n- Python SDK (`anthropic`)\n- TypeScript SDK (`@anthropic-ai\u002Fsdk`)\n- REST API (curl\u002FHTTP)\n\n## Response Style\n\n- **Clear** - API developers want precise answers\n- **Code-first** - show working examples\n- **Model-aware** - recommend appropriate Claude model\n- **Cost-conscious** - mention caching, model choice\n- **Cite sources** - reference specific doc sections\n\n## Follow-up Suggestions\n\nAfter answering, suggest:\n- Related API features\n- Cost optimization strategies\n- Error handling patterns\n- Testing approaches\n- Safety and moderation considerations\n","# Anthropic API Expert\n\n## Purpose\n\nProvide expert guidance on Anthropic's Claude API, including prompt engineering, function calling, vision capabilities, and best practices based on official Anthropic documentation.\n\n## When to Use\n\nAuto-invoke when users mention:\n- **Anthropic** - company, API, platform\n- **Claude** - models (Opus, Sonnet, Haiku), capabilities\n- **API** - Messages API, streaming, embeddings\n- **Features** - function calling, vision, extended context, prompt caching\n- **Integration** - SDKs (Python, TypeScript), REST API\n\n## Knowledge Base\n\n**Full access to official Anthropic documentation (when available):**\n- **Location:** `docs\u002F`\n- **Files:** 199 markdown files\n- **Format:** `.md` files\n\n**Note:** Documentation must be pulled separately:\n```bash\npipx install docpull\ndocpull https:\u002F\u002Fdocs.anthropic.com -o .claude\u002Fskills\u002Fanthropic\u002Fdocs\n```\n\n## Process\n\nWhen a user asks about Anthropic\u002FClaude:\n\n### 1. Identify Topic\n```\nCommon topics:\n- Getting started \u002F API keys\n- Model selection (Opus, Sonnet, Haiku)\n- Messages API \u002F streaming\n- Prompt engineering techniques\n- Function\u002Ftool calling\n- Vision and image analysis\n- Extended context (200K tokens)\n- Prompt caching\n- Rate limits and pricing\n- Error handling\n```\n\n### 2. Search Documentation\n\nUse Grep to find relevant docs:\n```bash\n# Search for specific topics\nGrep \"function calling|tool\" docs\u002F --output-mode files_with_matches -i\nGrep \"vision|image\" docs\u002F --output-mode content -C 3\n```\n\nCheck the INDEX.md for navigation:\n```bash\nRead docs\u002FINDEX.md\n```\n\n### 3. Read Relevant Files\n\nRead the most relevant documentation files:\n```bash\nRead docs\u002Fpath\u002Fto\u002Frelevant-doc.md\n```\n\n### 4. Provide Answer\n\nStructure your response:\n- **Direct answer** - solve the user's problem first\n- **Code examples** - show API calls with proper formatting\n- **Best practices** - mention Claude-specific patterns\n- **Model selection** - recommend appropriate model (Opus\u002FSonnet\u002FHaiku)\n- **References** - cite specific docs for deeper reading\n- **Cost optimization** - mention prompt caching, model choice\n\n## Example Workflows\n\n### Example 1: Function Calling\n```\nUser: \"How do I implement function calling with Claude?\"\n\n1. Search: Grep \"function calling|tool\" docs\u002F\n2. Read: Function calling documentation\n3. Answer:\n   - Explain tool use format\n   - Show request\u002Fresponse example\n   - Discuss tool choice vs any\n   - Best practices for tool definitions\n```\n\n### Example 2: Vision Capabilities\n```\nUser: \"Can Claude analyze images?\"\n\n1. Search: Grep \"vision|image\" docs\u002F -i\n2. Read: Vision API documentation\n3. Answer:\n   - Supported image formats\n   - Image encoding (base64, URLs)\n   - Show example API call\n   - Limitations and best practices\n```\n\n### Example 3: Prompt Engineering\n```\nUser: \"How do I write better prompts for Claude?\"\n\n1. Search: Grep \"prompt|engineering\" docs\u002F\n2. Read: Prompt engineering guide\n3. Answer:\n   - Clear instructions principle\n   - Examples and context\n   - XML tags for structure\n   - Chain of thought prompting\n```\n\n## Key Concepts to Reference\n\n**Models:**\n- Claude 3.5 Opus - most capable\n- Claude 3.5 Sonnet - balanced (recommended for most use cases)\n- Claude 3.5 Haiku - fast and economical\n\n**API Features:**\n- Messages API (primary interface)\n- Streaming responses\n- Function\u002Ftool calling\n- Vision (image analysis)\n- Extended context (200K tokens)\n- Prompt caching (reduce costs)\n\n**Best Practices:**\n- System prompts vs user messages\n- XML tags for structure\n- Few-shot examples\n- Clear, specific instructions\n- Appropriate model selection\n\n**SDKs:**\n- Python SDK (`anthropic`)\n- TypeScript SDK (`@anthropic-ai\u002Fsdk`)\n- REST API (curl\u002FHTTP)\n\n## Response Style\n\n- **Clear** - API developers want precise answers\n- **Code-first** - show working examples\n- **Model-aware** - recommend appropriate Claude model\n- **Cost-conscious** - mention caching, model choice\n- **Cite sources** - reference specific doc sections\n\n## Follow-up Suggestions\n\nAfter answering, suggest:\n- Related API features\n- Cost optimization strategies\n- Error handling patterns\n- Testing approaches\n- Safety and moderation considerations\n",{"name":5,"model":51,"description":7,"allowed-tools":52},"sonnet","Read, Grep, Glob","main","cbdd44aae21131521c09e42762e36178c790eacf","public\u002FSKILLS\u002FDevelopment & Code Tools\u002Fclaude-starter",13,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one","http:\u002F\u002Fhuangchiyu.com\u002FSKILLS_All-in-one\u002F","https:\u002F\u002Fgithub.com\u002Feric861129","https:\u002F\u002Fhuangchiyu.com\u002FChiYu-Blog\u002F","開發工程師，專注於 C#／.NET 系統現代化、AI-assisted engineering、開源工具與技術寫作。","2026-04-16 14:28:14",{"source":8,"skillName":5,"commands":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add eric861129\u002FSKILLS_All-in-one --skill anthropic-expert",{"tool":69,"command":70},"bunx","bunx skills add eric861129\u002FSKILLS_All-in-one --skill anthropic-expert",{"tool":72,"command":73},"pnpm","pnpm dlx skills add eric861129\u002FSKILLS_All-in-one --skill anthropic-expert","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FDevelopment & Code Tools\u002Fclaude-starter\u002FSKILL.md",true,[77],{"path":78,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":81,"sourceHtmlUrl":82},"skill.json","REFERENCE","参考文档",1274,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FDevelopment & Code Tools\u002Fclaude-starter\u002Fskill.json",[84,111,142,167,192,212],{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":91,"publishedAt":46},"01M6CZ1WR3KNVTKSWH4GNWT646","what-if-oracle","Run structured What-If scenario analysis with multi-branch possibility exploration. Use this skill when the user asks speculative questions like \"what if...\", \"what would happen if...\", \"what are the possibilities\", \"explore scenarios\", \"scenario analysis\", \"possibility space\", \"what could go wrong\", \"best case \u002F worst case\", \"risk analysis\", \"contingency planning\", \"strategic options\", or any question about uncertain futures. Also trigger when the user faces a fork-in-the-road decision, wants to stress-test an idea, or needs to think through consequences before committing.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fwhat-if-oracle\u002FSKILL.md",[90],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[92,93,94,95,96,97,98,99,100,101,102,103,104,35,105,106,107,108,109,110],"oracle","what if oracle","go","run","planning","ux","futures","risk","analysis","explore","decision","branch","question","write","idea","exploration","options","stress-test","strategies",{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":127,"publishedAt":46},"01M6CZ1QHGJE91A95MSN5EK5Q9","venue-templates","Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fvenue-templates\u002FSKILL.md",[117,120,123,124],{"categoryNo":118,"categoryName":119,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":121,"categoryName":122,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":125,"categoryName":126,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000036","内容创作者",[128,129,130,131,132,133,134,135,136,137,35,105,138,139,140,141],"templates","venue templates","research","guidelines","NeurIPS","ICML","LaTeX","science","Bash","access","edit","proposals","Academic","requirements",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":150,"publishedAt":46},"01M6CZ1KBQD2E5RTFB3BGVX7CD","the-fool","Use when challenging ideas, plans, decisions, or proposals using structured critical reasoning. Invoke to play devil's advocate, run a pre-mortem, red team, or audit evidence and assumptions.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fthe-fool\u002FSKILL.md",[148,149],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[151,152,94,153,154,95,155,156,157,158,159,160,161,162,139,163,164,30,165,166],"the fool","review","workflow","architecture","code","audit","forge","devil","team","designer","reviewer","challenge","stress test","evidence","poke","ideas",{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":176,"publishedAt":46},"01M6CZ1ES826S7P1X3333E40TA","scientific-writing","Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA\u002FAMA\u002FVancouver), figures\u002Ftables, reporting guidelines (CONSORT\u002FSTROBE\u002FPRISMA), for research papers and journal submissions.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fscientific-writing\u002FSKILL.md",[173,174,175],{"categoryNo":118,"categoryName":119,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":125,"categoryName":126,"taxonomyType":26,"taxonomyTypeDesc":27},[177,178,131,179,180,181,182,183,136,184,35,105,138,185,186,187,188,189,190,191],"writing","scientific writing","core","reporting","deep research","Citations","Outlines","tool","use","never","structure","deep","full","stage","prisma",{"skillNo":193,"name":194,"nameZh":6,"description":195,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":196,"categories":197,"keywords":199,"publishedAt":46},"01M6CZ1B2JGJTB9FRD0TW4RXXE","scientific-brainstorming","Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fscientific-brainstorming\u002FSKILL.md",[198],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[200,201,130,202,96,203,204,205,185,206,207,208,107,209,210,190,211],"brainstorming","scientific brainstorming","sessions","data","hypothesis","open","ideation","creative","do","connections","research ideation","generation",{"skillNo":213,"name":214,"nameZh":6,"description":215,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":216,"categories":217,"keywords":224,"publishedAt":46},"01M6CZ16JG8N7A2ZX04BGE8J2Y","research-lookup","Look up current research information using the Parallel Chat API (primary) or Perplexity sonar-pro-search (academic paper searches). Automatically routes queries to the best backend. Use for finding papers, gathering research data, and verifying scientific information.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fresearch-lookup\u002FSKILL.md",[218,221,222,223],{"categoryNo":219,"categoryName":220,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":121,"categoryName":122,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[130,225,226,227,203,228,39,136,229,230,35,105,138,185,231,232,233,234,235,140],"lookup","research lookup","search","perplexity","parallel","openrouter","backend","up","look","queries","chat"]