[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71JEBDSCZN3E3C461AJYM0V":3,"skill-same:01M71JEBDSCZN3E3C461AJYM0V":72},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":50,"commitSha":51,"skillDirectory":5,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":54,"ownerHtmlUrl":55,"ownerBlogUrl":56,"ownerDescription":57,"updatedAt":58,"install":59,"resources":71},"01M71JEBDSCZN3E3C461AJYM0V","create-subagent",null,"Create custom subagents for specialized AI tasks. Use when you want to create a new type of subagent, set up task-specific agents, configure code reviewers, debuggers, or domain-specific assistants with custom prompts.","caezium\u002Fskills","caezium","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F113233555?v=4","01M71JB77ZPBAWEK009Y2W8BP7","Henry Zhang","01M71JB792NVXCWSYD27HQ0964",3,"MIT","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fcreate-subagent\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"create","create subagent","subagent","type","specialized","task","tasks","code","you","configure","when","use","new","true","custom","up","domain-specific","for","domain","SET","2026-11-10 10:12:30",false,"---\nname: create-subagent\ndescription: >-\n  Create custom subagents for specialized AI tasks. Use when you want to create\n  a new type of subagent, set up task-specific agents, configure code reviewers,\n  debuggers, or domain-specific assistants with custom prompts.\ndisable-model-invocation: true\n---\n# Creating Custom Subagents\n\nThis skill guides you through creating custom subagents for Cursor. Subagents are specialized AI assistants that run in isolated contexts with custom system prompts.\n\n## When to Use Subagents\n\nSubagents help you:\n- **Preserve context** by isolating exploration from your main conversation\n- **Specialize behavior** with focused system prompts for specific domains\n- **Reuse configurations** across projects with user-level subagents\n\n### Inferring from Context\n\nIf you have previous conversation context, infer the subagent's purpose and behavior from what was discussed. Create the subagent based on specialized tasks or workflows that emerged in the conversation.\n\n## Subagent Locations\n\n| Location | Scope | Priority |\n|----------|-------|----------|\n| `.cursor\u002Fagents\u002F` | Current project | Higher |\n| `~\u002F.cursor\u002Fagents\u002F` | All your projects | Lower |\n\nWhen multiple subagents share the same name, the higher-priority location wins.\n\n**Project subagents** (`.cursor\u002Fagents\u002F`): Ideal for codebase-specific agents. Check into version control to share with your team.\n\n**User subagents** (`~\u002F.cursor\u002Fagents\u002F`): Personal agents available across all your projects.\n\n## Subagent File Format\n\nCreate a `.md` file with YAML frontmatter and a markdown body (the system prompt):\n\n```markdown\n---\nname: code-reviewer\ndescription: Reviews code for quality and best practices\n---\n\nYou are a code reviewer. When invoked, analyze the code and provide\nspecific, actionable feedback on quality, security, and best practices.\n```\n\n### Required Fields\n\n| Field | Description |\n|-------|-------------|\n| `name` | Unique identifier (lowercase letters and hyphens only) |\n| `description` | When to delegate to this subagent (be specific!) |\n\n## Writing Effective Descriptions\n\nThe description is **critical** - the AI uses it to decide when to delegate.\n\n```yaml\n# ❌ Too vague\ndescription: Helps with code\n\n# ✅ Specific and actionable\ndescription: Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.\n```\n\nInclude \"use proactively\" to encourage automatic delegation.\n\n## Example Subagents\n\n### Code Reviewer\n\n```markdown\n---\nname: code-reviewer\ndescription: Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.\n---\n\nYou are a senior code reviewer ensuring high standards of code quality and security.\n\nWhen invoked:\n1. Run git diff to see recent changes\n2. Focus on modified files\n3. Begin review immediately\n\nReview checklist:\n- Code is clear and readable\n- Functions and variables are well-named\n- No duplicated code\n- Proper error handling\n- No exposed secrets or API keys\n- Input validation implemented\n- Good test coverage\n- Performance considerations addressed\n\nProvide feedback organized by priority:\n- Critical issues (must fix)\n- Warnings (should fix)\n- Suggestions (consider improving)\n\nInclude specific examples of how to fix issues.\n```\n\n### Debugger\n\n```markdown\n---\nname: debugger\ndescription: Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.\n---\n\nYou are an expert debugger specializing in root cause analysis.\n\nWhen invoked:\n1. Capture error message and stack trace\n2. Identify reproduction steps\n3. Isolate the failure location\n4. Implement minimal fix\n5. Verify solution works\n\nDebugging process:\n- Analyze error messages and logs\n- Check recent code changes\n- Form and test hypotheses\n- Add strategic debug logging\n- Inspect variable states\n\nFor each issue, provide:\n- Root cause explanation\n- Evidence supporting the diagnosis\n- Specific code fix\n- Testing approach\n- Prevention recommendations\n\nFocus on fixing the underlying issue, not the symptoms.\n```\n\n### Data Scientist\n\n```markdown\n---\nname: data-scientist\ndescription: Data analysis expert for SQL queries, BigQuery operations, and data insights. Use proactively for data analysis tasks and queries.\n---\n\nYou are a data scientist specializing in SQL and BigQuery analysis.\n\nWhen invoked:\n1. Understand the data analysis requirement\n2. Write efficient SQL queries\n3. Use BigQuery command line tools (bq) when appropriate\n4. Analyze and summarize results\n5. Present findings clearly\n\nKey practices:\n- Write optimized SQL queries with proper filters\n- Use appropriate aggregations and joins\n- Include comments explaining complex logic\n- Format results for readability\n- Provide data-driven recommendations\n\nFor each analysis:\n- Explain the query approach\n- Document any assumptions\n- Highlight key findings\n- Suggest next steps based on data\n\nAlways ensure queries are efficient and cost-effective.\n```\n\n## Subagent Creation Workflow\n\n### Step 1: Decide the Scope\n\n- **Project-level** (`.cursor\u002Fagents\u002F`): For codebase-specific agents shared with team\n- **User-level** (`~\u002F.cursor\u002Fagents\u002F`): For personal agents across all projects\n\n### Step 2: Create the File\n\n```bash\n# For project-level\nmkdir -p .cursor\u002Fagents\ntouch .cursor\u002Fagents\u002Fmy-agent.md\n\n# For user-level\nmkdir -p ~\u002F.cursor\u002Fagents\ntouch ~\u002F.cursor\u002Fagents\u002Fmy-agent.md\n```\n\n### Step 3: Define Configuration\n\nWrite the frontmatter with the required fields (`name` and `description`).\n\n### Step 4: Write the System Prompt\n\nThe body becomes the system prompt. Be specific about:\n- What the agent should do when invoked\n- The workflow or process to follow\n- Output format and structure\n- Any constraints or guidelines\n\n### Step 5: Test the Agent\n\nAsk the AI to use your new agent:\n\n```\nUse the my-agent subagent to [task description]\n```\n\n## Best Practices\n\n1. **Design focused subagents**: Each should excel at one specific task\n2. **Write detailed descriptions**: Include trigger terms so the AI knows when to delegate\n3. **Check into version control**: Share project subagents with your team\n4. **Use proactive language**: Include \"use proactively\" in descriptions\n\n## Troubleshooting\n\n### Subagent Not Found\n- Ensure file is in `.cursor\u002Fagents\u002F` or `~\u002F.cursor\u002Fagents\u002F`\n- Check file has `.md` extension\n- Verify YAML frontmatter syntax is valid\n","# Creating Custom Subagents\n\nThis skill guides you through creating custom subagents for Cursor. Subagents are specialized AI assistants that run in isolated contexts with custom system prompts.\n\n## When to Use Subagents\n\nSubagents help you:\n- **Preserve context** by isolating exploration from your main conversation\n- **Specialize behavior** with focused system prompts for specific domains\n- **Reuse configurations** across projects with user-level subagents\n\n### Inferring from Context\n\nIf you have previous conversation context, infer the subagent's purpose and behavior from what was discussed. Create the subagent based on specialized tasks or workflows that emerged in the conversation.\n\n## Subagent Locations\n\n| Location | Scope | Priority |\n|----------|-------|----------|\n| `.cursor\u002Fagents\u002F` | Current project | Higher |\n| `~\u002F.cursor\u002Fagents\u002F` | All your projects | Lower |\n\nWhen multiple subagents share the same name, the higher-priority location wins.\n\n**Project subagents** (`.cursor\u002Fagents\u002F`): Ideal for codebase-specific agents. Check into version control to share with your team.\n\n**User subagents** (`~\u002F.cursor\u002Fagents\u002F`): Personal agents available across all your projects.\n\n## Subagent File Format\n\nCreate a `.md` file with YAML frontmatter and a markdown body (the system prompt):\n\n```markdown\n---\nname: code-reviewer\ndescription: Reviews code for quality and best practices\n---\n\nYou are a code reviewer. When invoked, analyze the code and provide\nspecific, actionable feedback on quality, security, and best practices.\n```\n\n### Required Fields\n\n| Field | Description |\n|-------|-------------|\n| `name` | Unique identifier (lowercase letters and hyphens only) |\n| `description` | When to delegate to this subagent (be specific!) |\n\n## Writing Effective Descriptions\n\nThe description is **critical** - the AI uses it to decide when to delegate.\n\n```yaml\n# ❌ Too vague\ndescription: Helps with code\n\n# ✅ Specific and actionable\ndescription: Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.\n```\n\nInclude \"use proactively\" to encourage automatic delegation.\n\n## Example Subagents\n\n### Code Reviewer\n\n```markdown\n---\nname: code-reviewer\ndescription: Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.\n---\n\nYou are a senior code reviewer ensuring high standards of code quality and security.\n\nWhen invoked:\n1. Run git diff to see recent changes\n2. Focus on modified files\n3. Begin review immediately\n\nReview checklist:\n- Code is clear and readable\n- Functions and variables are well-named\n- No duplicated code\n- Proper error handling\n- No exposed secrets or API keys\n- Input validation implemented\n- Good test coverage\n- Performance considerations addressed\n\nProvide feedback organized by priority:\n- Critical issues (must fix)\n- Warnings (should fix)\n- Suggestions (consider improving)\n\nInclude specific examples of how to fix issues.\n```\n\n### Debugger\n\n```markdown\n---\nname: debugger\ndescription: Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.\n---\n\nYou are an expert debugger specializing in root cause analysis.\n\nWhen invoked:\n1. Capture error message and stack trace\n2. Identify reproduction steps\n3. Isolate the failure location\n4. Implement minimal fix\n5. Verify solution works\n\nDebugging process:\n- Analyze error messages and logs\n- Check recent code changes\n- Form and test hypotheses\n- Add strategic debug logging\n- Inspect variable states\n\nFor each issue, provide:\n- Root cause explanation\n- Evidence supporting the diagnosis\n- Specific code fix\n- Testing approach\n- Prevention recommendations\n\nFocus on fixing the underlying issue, not the symptoms.\n```\n\n### Data Scientist\n\n```markdown\n---\nname: data-scientist\ndescription: Data analysis expert for SQL queries, BigQuery operations, and data insights. Use proactively for data analysis tasks and queries.\n---\n\nYou are a data scientist specializing in SQL and BigQuery analysis.\n\nWhen invoked:\n1. Understand the data analysis requirement\n2. Write efficient SQL queries\n3. Use BigQuery command line tools (bq) when appropriate\n4. Analyze and summarize results\n5. Present findings clearly\n\nKey practices:\n- Write optimized SQL queries with proper filters\n- Use appropriate aggregations and joins\n- Include comments explaining complex logic\n- Format results for readability\n- Provide data-driven recommendations\n\nFor each analysis:\n- Explain the query approach\n- Document any assumptions\n- Highlight key findings\n- Suggest next steps based on data\n\nAlways ensure queries are efficient and cost-effective.\n```\n\n## Subagent Creation Workflow\n\n### Step 1: Decide the Scope\n\n- **Project-level** (`.cursor\u002Fagents\u002F`): For codebase-specific agents shared with team\n- **User-level** (`~\u002F.cursor\u002Fagents\u002F`): For personal agents across all projects\n\n### Step 2: Create the File\n\n```bash\n# For project-level\nmkdir -p .cursor\u002Fagents\ntouch .cursor\u002Fagents\u002Fmy-agent.md\n\n# For user-level\nmkdir -p ~\u002F.cursor\u002Fagents\ntouch ~\u002F.cursor\u002Fagents\u002Fmy-agent.md\n```\n\n### Step 3: Define Configuration\n\nWrite the frontmatter with the required fields (`name` and `description`).\n\n### Step 4: Write the System Prompt\n\nThe body becomes the system prompt. Be specific about:\n- What the agent should do when invoked\n- The workflow or process to follow\n- Output format and structure\n- Any constraints or guidelines\n\n### Step 5: Test the Agent\n\nAsk the AI to use your new agent:\n\n```\nUse the my-agent subagent to [task description]\n```\n\n## Best Practices\n\n1. **Design focused subagents**: Each should excel at one specific task\n2. **Write detailed descriptions**: Include trigger terms so the AI knows when to delegate\n3. **Check into version control**: Share project subagents with your team\n4. **Use proactive language**: Include \"use proactively\" in descriptions\n\n## Troubleshooting\n\n### Subagent Not Found\n- Ensure file is in `.cursor\u002Fagents\u002F` or `~\u002F.cursor\u002Fagents\u002F`\n- Check file has `.md` extension\n- Verify YAML frontmatter syntax is valid\n",{"name":5,"description":7,"disable-model-invocation":49},true,"main","6ef866230c1ba3459fd08fc65141dfd37fffd41a",0,"https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills","https:\u002F\u002Fskills.henryzh.dev","https:\u002F\u002Fgithub.com\u002Fcaezium","henryzh.dev","quant, data science, full-stack, robotics.\r\nbuilding cool stuff","2026-08-24 19:21:44",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":49},[61,64,67],{"tool":62,"command":63},"npx","npx skills add caezium\u002Fskills --skill create-subagent",{"tool":65,"command":66},"bunx","bunx skills add caezium\u002Fskills --skill create-subagent",{"tool":68,"command":69},"pnpm","pnpm dlx skills add caezium\u002Fskills --skill create-subagent","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fcreate-subagent\u002FSKILL.md",[],[73,92,120,136,156,178],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":87,"publishedAt":44},"01M71JT4RYCAS18RF6003YYR1D","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwriting-for-agents\u002FSKILL.md",[79,82],{"categoryNo":80,"categoryName":81,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":83,"categoryName":84,"taxonomyType":85,"taxonomyTypeDesc":86},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[88,41,89,90,35,91,34],"writing for agents","writing","editing","documents",{"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":101,"publishedAt":44},"01M71JT0GES4AZ5ADH8EADNN1Z","wrangler","Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwrangler\u002FSKILL.md",[98],{"categoryNo":99,"categoryName":100,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",[94,102,103,104,105,106,107,108,109,110,111,112,113,41,114,115,116,117,118,119],"cloudflare","d1","knowledge","workflows","cli","secrets","commands","syntax","cloudflare workers","r2","queues","running","containers","correct","load","workers","best practices","store",{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":44},"01M71JSWX4R203M32K9A18AAW8","workers-best-practices","Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fworkers-best-practices\u002FSKILL.md",[],[127,117,118,128,129,130,41,102,131,104,36,94,89,116,34,31,132,133,134,135],"workers best practices","observability","reviews","promises","worker","common","streaming","state","anti-patterns",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":44},"01M71JST6P88MXGT2MWDTPJGEG","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwizard\u002FSKILL.md",[],[138,113,143,41,39,144,145,146,35,147,34,148,149,150,151,152,153,154,155,107],"setting","ci","provisioning infrastructure","only","invoke","Bash","one","interactive","can","credentials","dashboard","generate","human",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":160,"sourceHtmlUrl":161,"categories":162,"keywords":163,"publishedAt":44},"01M71JSQ95S7BQ61DAPN95X2W4","why","Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available evidence sources, searches each relevant category, and returns a cited read on decisions and tradeoffs. Use how for runtime behavior.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwhy\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwhy\u002FSKILL.md",[],[158,164,165,166,167,41,168,169,35,170,171,172,173,174,175,176,177],"sources","thresholds","evidence","relevant","runtime","design","decisions","work","how","behavior","read","data","rationale","returns",{"skillNo":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":182,"categories":183,"keywords":185,"publishedAt":44},"01M71JSMHFVSH8HK8GXN6YAX6J","week-prep","Generate a briefing with calendar, tasks, and attention flags. Use for \"week prep\", \"briefing\", or \"what's on this week\".","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fweek-prep\u002FSKILL.md",[184],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[186,187,188,189,190,41,191,192,193,194,35,148,30,195,196,154,197,174,198,199],"week prep","prep","deep","attention","get","search","messages","briefing","MCP","with","slack","calendar","flags","grep"]