[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F4F4TCH5A5F35ZARS1TMVG":3,"skill-same:01M7F4F4TCH5A5F35ZARS1TMVG":47},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7F4F4TCH5A5F35ZARS1TMVG","search-first",null,"Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Invokes the researcher agent.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsearch-first\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: search-first\ndescription: Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Invokes the researcher agent.\norigin: ECC\n---\n\n# \u002Fsearch-first — Research Before You Code\n\nSystematizes the \"search for existing solutions before implementing\" workflow.\n\n## Trigger\n\nUse this skill when:\n- Starting a new feature that likely has existing solutions\n- Adding a dependency or integration\n- The user asks \"add X functionality\" and you're about to write code\n- Before creating a new utility, helper, or abstraction\n\n## Workflow\n\n```\n┌─────────────────────────────────────────────┐\n│  1. NEED ANALYSIS                           │\n│     Define what functionality is needed      │\n│     Identify language\u002Fframework constraints  │\n├─────────────────────────────────────────────┤\n│  2. PARALLEL SEARCH (researcher agent)      │\n│     ┌──────────┐ ┌──────────┐ ┌──────────┐  │\n│     │  npm \u002F   │ │  MCP \u002F   │ │  GitHub \u002F │  │\n│     │  PyPI    │ │  Skills  │ │  Web      │  │\n│     └──────────┘ └──────────┘ └──────────┘  │\n├─────────────────────────────────────────────┤\n│  3. EVALUATE                                │\n│     Score candidates (functionality, maint, │\n│     community, docs, license, deps)         │\n├─────────────────────────────────────────────┤\n│  4. DECIDE                                  │\n│     ┌─────────┐  ┌──────────┐  ┌─────────┐  │\n│     │  Adopt  │  │  Extend  │  │  Build   │  │\n│     │ as-is   │  │  \u002FWrap   │  │  Custom  │  │\n│     └─────────┘  └──────────┘  └─────────┘  │\n├─────────────────────────────────────────────┤\n│  5. IMPLEMENT                               │\n│     Install package \u002F Configure MCP \u002F       │\n│     Write minimal custom code               │\n└─────────────────────────────────────────────┘\n```\n\n## Decision Matrix\n\n| Signal | Action |\n|--------|--------|\n| Exact match, well-maintained, MIT\u002FApache | **Adopt** — install and use directly |\n| Partial match, good foundation | **Extend** — install + write thin wrapper |\n| Multiple weak matches | **Compose** — combine 2-3 small packages |\n| Nothing suitable found | **Build** — write custom, but informed by research |\n\n## How to Use\n\n### Quick Mode (inline)\n\nBefore writing a utility or adding functionality, mentally run through:\n\n0. Does this already exist in the repo? → `rg` through relevant modules\u002Ftests first\n1. Is this a common problem? → Search npm\u002FPyPI\n2. Is there an MCP for this? → Check `~\u002F.claude\u002Fsettings.json` and search\n3. Is there a skill for this? → Check `~\u002F.claude\u002Fskills\u002F`\n4. Is there a GitHub implementation\u002Ftemplate? → Run GitHub code search for maintained OSS before writing net-new code\n\n### Full Mode (agent)\n\nFor non-trivial functionality, launch the researcher agent:\n\n```\nTask(subagent_type=\"general-purpose\", prompt=\"\n  Research existing tools for: [DESCRIPTION]\n  Language\u002Fframework: [LANG]\n  Constraints: [ANY]\n\n  Search: npm\u002FPyPI, MCP servers, Claude Code skills, GitHub\n  Return: Structured comparison with recommendation\n\")\n```\n\n## Search Shortcuts by Category\n\n### Development Tooling\n- Linting → `eslint`, `ruff`, `textlint`, `markdownlint`\n- Formatting → `prettier`, `black`, `gofmt`\n- Testing → `jest`, `pytest`, `go test`\n- Pre-commit → `husky`, `lint-staged`, `pre-commit`\n\n### AI\u002FLLM Integration\n- Claude SDK → Context7 for latest docs\n- Prompt management → Check MCP servers\n- Document processing → `unstructured`, `pdfplumber`, `mammoth`\n\n### Data & APIs\n- HTTP clients → `httpx` (Python), `ky`\u002F`got` (Node)\n- Validation → `zod` (TS), `pydantic` (Python)\n- Database → Check for MCP servers first\n\n### Content & Publishing\n- Markdown processing → `remark`, `unified`, `markdown-it`\n- Image optimization → `sharp`, `imagemin`\n\n## Integration Points\n\n### With planner agent\nThe planner should invoke researcher before Phase 1 (Architecture Review):\n- Researcher identifies available tools\n- Planner incorporates them into the implementation plan\n- Avoids \"reinventing the wheel\" in the plan\n\n### With architect agent\nThe architect should consult researcher for:\n- Technology stack decisions\n- Integration pattern discovery\n- Existing reference architectures\n\n### With iterative-retrieval skill\nCombine for progressive discovery:\n- Cycle 1: Broad search (npm, PyPI, MCP)\n- Cycle 2: Evaluate top candidates in detail\n- Cycle 3: Test compatibility with project constraints\n\n## Examples\n\n### Example 1: \"Add dead link checking\"\n```\nNeed: Check markdown files for broken links\nSearch: npm \"markdown dead link checker\"\nFound: textlint-rule-no-dead-link (score: 9\u002F10)\nAction: ADOPT — npm install textlint-rule-no-dead-link\nResult: Zero custom code, battle-tested solution\n```\n\n### Example 2: \"Add HTTP client wrapper\"\n```\nNeed: Resilient HTTP client with retries and timeout handling\nSearch: npm \"http client retry\", PyPI \"httpx retry\"\nFound: got (Node) with retry plugin, httpx (Python) with built-in retry\nAction: ADOPT — use got\u002Fhttpx directly with retry config\nResult: Zero custom code, production-proven libraries\n```\n\n### Example 3: \"Add config file linter\"\n```\nNeed: Validate project config files against a schema\nSearch: npm \"config linter schema\", \"json schema validator cli\"\nFound: ajv-cli (score: 8\u002F10)\nAction: ADOPT + EXTEND — install ajv-cli, write project-specific schema\nResult: 1 package + 1 schema file, no custom validation logic\n```\n\n## Anti-Patterns\n\n- **Jumping to code**: Writing a utility without checking if one exists\n- **Ignoring MCP**: Not checking if an MCP server already provides the capability\n- **Over-customizing**: Wrapping a library so heavily it loses its benefits\n- **Dependency bloat**: Installing a massive package for one small feature\n","# \u002Fsearch-first — Research Before You Code\n\nSystematizes the \"search for existing solutions before implementing\" workflow.\n\n## Trigger\n\nUse this skill when:\n- Starting a new feature that likely has existing solutions\n- Adding a dependency or integration\n- The user asks \"add X functionality\" and you're about to write code\n- Before creating a new utility, helper, or abstraction\n\n## Workflow\n\n```\n┌─────────────────────────────────────────────┐\n│  1. NEED ANALYSIS                           │\n│     Define what functionality is needed      │\n│     Identify language\u002Fframework constraints  │\n├─────────────────────────────────────────────┤\n│  2. PARALLEL SEARCH (researcher agent)      │\n│     ┌──────────┐ ┌──────────┐ ┌──────────┐  │\n│     │  npm \u002F   │ │  MCP \u002F   │ │  GitHub \u002F │  │\n│     │  PyPI    │ │  Skills  │ │  Web      │  │\n│     └──────────┘ └──────────┘ └──────────┘  │\n├─────────────────────────────────────────────┤\n│  3. EVALUATE                                │\n│     Score candidates (functionality, maint, │\n│     community, docs, license, deps)         │\n├─────────────────────────────────────────────┤\n│  4. DECIDE                                  │\n│     ┌─────────┐  ┌──────────┐  ┌─────────┐  │\n│     │  Adopt  │  │  Extend  │  │  Build   │  │\n│     │ as-is   │  │  \u002FWrap   │  │  Custom  │  │\n│     └─────────┘  └──────────┘  └─────────┘  │\n├─────────────────────────────────────────────┤\n│  5. IMPLEMENT                               │\n│     Install package \u002F Configure MCP \u002F       │\n│     Write minimal custom code               │\n└─────────────────────────────────────────────┘\n```\n\n## Decision Matrix\n\n| Signal | Action |\n|--------|--------|\n| Exact match, well-maintained, MIT\u002FApache | **Adopt** — install and use directly |\n| Partial match, good foundation | **Extend** — install + write thin wrapper |\n| Multiple weak matches | **Compose** — combine 2-3 small packages |\n| Nothing suitable found | **Build** — write custom, but informed by research |\n\n## How to Use\n\n### Quick Mode (inline)\n\nBefore writing a utility or adding functionality, mentally run through:\n\n0. Does this already exist in the repo? → `rg` through relevant modules\u002Ftests first\n1. Is this a common problem? → Search npm\u002FPyPI\n2. Is there an MCP for this? → Check `~\u002F.claude\u002Fsettings.json` and search\n3. Is there a skill for this? → Check `~\u002F.claude\u002Fskills\u002F`\n4. Is there a GitHub implementation\u002Ftemplate? → Run GitHub code search for maintained OSS before writing net-new code\n\n### Full Mode (agent)\n\nFor non-trivial functionality, launch the researcher agent:\n\n```\nTask(subagent_type=\"general-purpose\", prompt=\"\n  Research existing tools for: [DESCRIPTION]\n  Language\u002Fframework: [LANG]\n  Constraints: [ANY]\n\n  Search: npm\u002FPyPI, MCP servers, Claude Code skills, GitHub\n  Return: Structured comparison with recommendation\n\")\n```\n\n## Search Shortcuts by Category\n\n### Development Tooling\n- Linting → `eslint`, `ruff`, `textlint`, `markdownlint`\n- Formatting → `prettier`, `black`, `gofmt`\n- Testing → `jest`, `pytest`, `go test`\n- Pre-commit → `husky`, `lint-staged`, `pre-commit`\n\n### AI\u002FLLM Integration\n- Claude SDK → Context7 for latest docs\n- Prompt management → Check MCP servers\n- Document processing → `unstructured`, `pdfplumber`, `mammoth`\n\n### Data & APIs\n- HTTP clients → `httpx` (Python), `ky`\u002F`got` (Node)\n- Validation → `zod` (TS), `pydantic` (Python)\n- Database → Check for MCP servers first\n\n### Content & Publishing\n- Markdown processing → `remark`, `unified`, `markdown-it`\n- Image optimization → `sharp`, `imagemin`\n\n## Integration Points\n\n### With planner agent\nThe planner should invoke researcher before Phase 1 (Architecture Review):\n- Researcher identifies available tools\n- Planner incorporates them into the implementation plan\n- Avoids \"reinventing the wheel\" in the plan\n\n### With architect agent\nThe architect should consult researcher for:\n- Technology stack decisions\n- Integration pattern discovery\n- Existing reference architectures\n\n### With iterative-retrieval skill\nCombine for progressive discovery:\n- Cycle 1: Broad search (npm, PyPI, MCP)\n- Cycle 2: Evaluate top candidates in detail\n- Cycle 3: Test compatibility with project constraints\n\n## Examples\n\n### Example 1: \"Add dead link checking\"\n```\nNeed: Check markdown files for broken links\nSearch: npm \"markdown dead link checker\"\nFound: textlint-rule-no-dead-link (score: 9\u002F10)\nAction: ADOPT — npm install textlint-rule-no-dead-link\nResult: Zero custom code, battle-tested solution\n```\n\n### Example 2: \"Add HTTP client wrapper\"\n```\nNeed: Resilient HTTP client with retries and timeout handling\nSearch: npm \"http client retry\", PyPI \"httpx retry\"\nFound: got (Node) with retry plugin, httpx (Python) with built-in retry\nAction: ADOPT — use got\u002Fhttpx directly with retry config\nResult: Zero custom code, production-proven libraries\n```\n\n### Example 3: \"Add config file linter\"\n```\nNeed: Validate project config files against a schema\nSearch: npm \"config linter schema\", \"json schema validator cli\"\nFound: ajv-cli (score: 8\u002F10)\nAction: ADOPT + EXTEND — install ajv-cli, write project-specific schema\nResult: 1 package + 1 schema file, no custom validation logic\n```\n\n## Anti-Patterns\n\n- **Jumping to code**: Writing a utility without checking if one exists\n- **Ignoring MCP**: Not checking if an MCP server already provides the capability\n- **Over-customizing**: Wrapping a library so heavily it loses its benefits\n- **Dependency bloat**: Installing a massive package for one small feature\n",{"name":5,"origin":24,"description":7},"ECC","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Fsearch-first",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill search-first",{"tool":39,"command":40},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill search-first",{"tool":42,"command":43},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill search-first","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsearch-first\u002FSKILL.md",true,[],[48,55,60,67,74,81],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":56,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]