[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79MVK4PFX9EMQABPVZ48XDK":3,"skill-same:01M79MVK4PFX9EMQABPVZ48XDK":46},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M79MVK4PFX9EMQABPVZ48XDK","dev",null,"This skill should be used when the user needs the OmniSkill Developers crew — stress-testing a plan before building, planning and TDD workflows, live version-exact library docs, building MCP servers, scaffolding new skills, browser-testing a web app, searching, scraping or crawling websites, reading PDFs and books as Markdown, reverse-engineering how an app or site works, or persisting memory across sessions. Triggers on \"\u002Fomniskill:dev\", \"grill me\", \"stress-test this plan\", \"set up TDD\", \"look up the docs for\", \"build an MCP server\", \"create a skill\", \"test my app in a browser\", \"scrape this site\", \"crawl\", \"search the web for\", \"how does this app do X\", \"reverse engineer\", \"convert this PDF\", \"render this JS page\", \"moli\", \"read this book\".","IPedrax\u002FOmniSkill","IPedrax","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F64429409?v=4","01M79MSCRSKESGTTRZMGK54KW0","01M79MSCSDY16CNNHW0VRGZFHF",9,"MIT","https:\u002F\u002Fgithub.com\u002FIPedrax\u002FOmniSkill\u002Fblob\u002Fmain\u002Fskills\u002Fdev\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: dev\ndescription: This skill should be used when the user needs the OmniSkill Developers crew — stress-testing a plan before building, planning and TDD workflows, live version-exact library docs, building MCP servers, scaffolding new skills, browser-testing a web app, searching, scraping or crawling websites, reading PDFs and books as Markdown, reverse-engineering how an app or site works, or persisting memory across sessions. Triggers on \"\u002Fomniskill:dev\", \"grill me\", \"stress-test this plan\", \"set up TDD\", \"look up the docs for\", \"build an MCP server\", \"create a skill\", \"test my app in a browser\", \"scrape this site\", \"crawl\", \"search the web for\", \"how does this app do X\", \"reverse engineer\", \"convert this PDF\", \"render this JS page\", \"moli\", \"read this book\".\nwhen_to_use: Use for engineering workflow and tooling tasks. For ordinary code edits in an existing repo, work directly instead.\nallowed-tools: Read Glob\n---\n\n# 01 — Developers\n\n> Ship code faster, from scaffold to QA. **Your build team.**\n\n## Pick the specialist\n\n| Skill | Use when |\n|---|---|\n| `grill-me` | Pressure-testing a plan or design **before** building it |\n| `superpowers` | Structured planning and test-driven development on a real feature |\n| `context7` | Needing the *current* API of a library — never answer library questions from memory |\n| `mcp-builder` | Wiring Claude to an external tool or API as an MCP server |\n| `skill-creator` | Turning a repeated workflow into a reusable skill |\n| `webapp-testing` | Verifying a web app actually works in a browser |\n| `scrapling` | Reading the web: search, fetch past bot walls, map or crawl a site, pull structured data |\n| `pdf-to-md` | Making a PDF or a whole book readable by AI: Markdown chapters with page anchors, audited word by word against the PDF so nothing is dropped silently |\n| `moli` | Reading JavaScript pages without Chromium: `moli fetch`, scrapling's `--engine moli`; built from source, with measured limits |\n| `rea` | How a shipped app or site works without its source: Electron bundles, .NET, APKs, binaries, with evidence |\n| `claude-mem` | Carrying durable knowledge across sessions |\n\n## Load it\n\nRead `${CLAUDE_SKILL_DIR}\u002F..\u002F\u003Cskill>\u002FSKILL.md` and follow it. Its paths that start with the CLAUDE_SKILL_DIR placeholder mean its own folder, `${CLAUDE_SKILL_DIR}\u002F..\u002F\u003Cskill>\u002F`: only the invoked skill gets the placeholder filled in, and Bash never sets it, so write that full path into any command it gives you.\n\n## Routing notes\n\n`context7` is near-free and high-value: any question about a library's API, config, or version behaviour should route here before answering. Guessing at library APIs from memory is the single most common source of wrong code.\n\nEngine order for reading the web: plain request, then `moli` for JavaScript, then Chromium for bot walls or app testing. Moli does not replace the Playwright MCP.\n\n`scrapling` is for other people's sites; `webapp-testing` is for the user's own app. `context7` still comes first for library docs.\n\n`superpowers` and `webapp-testing` compose — plan and build with the first, prove it works with the second.\n\n`grill-me` runs *before* both. When someone arrives with an approach already in mind and the stakes are real, interrogate it first — an hour of questions is cheaper than a week down the wrong branch.\n","# 01 — Developers\n\n> Ship code faster, from scaffold to QA. **Your build team.**\n\n## Pick the specialist\n\n| Skill | Use when |\n|---|---|\n| `grill-me` | Pressure-testing a plan or design **before** building it |\n| `superpowers` | Structured planning and test-driven development on a real feature |\n| `context7` | Needing the *current* API of a library — never answer library questions from memory |\n| `mcp-builder` | Wiring Claude to an external tool or API as an MCP server |\n| `skill-creator` | Turning a repeated workflow into a reusable skill |\n| `webapp-testing` | Verifying a web app actually works in a browser |\n| `scrapling` | Reading the web: search, fetch past bot walls, map or crawl a site, pull structured data |\n| `pdf-to-md` | Making a PDF or a whole book readable by AI: Markdown chapters with page anchors, audited word by word against the PDF so nothing is dropped silently |\n| `moli` | Reading JavaScript pages without Chromium: `moli fetch`, scrapling's `--engine moli`; built from source, with measured limits |\n| `rea` | How a shipped app or site works without its source: Electron bundles, .NET, APKs, binaries, with evidence |\n| `claude-mem` | Carrying durable knowledge across sessions |\n\n## Load it\n\nRead `${CLAUDE_SKILL_DIR}\u002F..\u002F\u003Cskill>\u002FSKILL.md` and follow it. Its paths that start with the CLAUDE_SKILL_DIR placeholder mean its own folder, `${CLAUDE_SKILL_DIR}\u002F..\u002F\u003Cskill>\u002F`: only the invoked skill gets the placeholder filled in, and Bash never sets it, so write that full path into any command it gives you.\n\n## Routing notes\n\n`context7` is near-free and high-value: any question about a library's API, config, or version behaviour should route here before answering. Guessing at library APIs from memory is the single most common source of wrong code.\n\nEngine order for reading the web: plain request, then `moli` for JavaScript, then Chromium for bot walls or app testing. Moli does not replace the Playwright MCP.\n\n`scrapling` is for other people's sites; `webapp-testing` is for the user's own app. `context7` still comes first for library docs.\n\n`superpowers` and `webapp-testing` compose — plan and build with the first, prove it works with the second.\n\n`grill-me` runs *before* both. When someone arrives with an approach already in mind and the stakes are real, interrogate it first — an hour of questions is cheaper than a week down the wrong branch.\n",{"name":5,"description":7,"when_to_use":23,"allowed-tools":24},"Use for engineering workflow and tooling tasks. For ordinary code edits in an existing repo, work directly instead.","Read Glob","main","cc238b48e3c4fe0061cad0b0475142fbff5b183d","skills\u002Fdev",0,"https:\u002F\u002Fgithub.com\u002FIPedrax\u002FOmniSkill","https:\u002F\u002Fgithub.com\u002FIPedrax","2026-10-14 10:26:53",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add IPedrax\u002FOmniSkill --skill dev",{"tool":38,"command":39},"bunx","bunx skills add IPedrax\u002FOmniSkill --skill dev",{"tool":41,"command":42},"pnpm","pnpm dlx skills add IPedrax\u002FOmniSkill --skill dev","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FIPedrax\u002FOmniSkill\u002Fblob\u002Fmain\u002Fskills\u002Fdev\u002FSKILL.md",true,[],[47,54,61,68,75,81],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":18},"01M79N058MCJZPHNFYZCPJG3ZZ","xlsx","Excel with live formulas. OmniSkill Operations crew — adapter for the xlsx skill, which installs separately.","https:\u002F\u002Fgithub.com\u002FIPedrax\u002FOmniSkill\u002Fblob\u002Fmain\u002Fskills\u002Fxlsx\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":18},"01M79N01GR5C5EK22CKGG38VYH","webapp-testing","Browser-test a web app. OmniSkill Developers crew — drives a real browser to verify user flows, catches console and network errors, and writes tests that do not flake.","https:\u002F\u002Fgithub.com\u002FIPedrax\u002FOmniSkill\u002Fblob\u002Fmain\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":18},"01M79MZZSJHFKJRE46BNEHCYZ3","web-artifacts","shadcn HTML artifacts. OmniSkill Design crew — bundled copy of the Web Artifacts skill.","https:\u002F\u002Fgithub.com\u002FIPedrax\u002FOmniSkill\u002Fblob\u002Fmain\u002Fskills\u002Fweb-artifacts\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":18},"01M79MZXFMCV0QSQ2WN316JKGZ","video","Script and produce video. OmniSkill Social crew — structures short-form and long-form video around retention, with shot lists, captions, and platform-specific delivery.","https:\u002F\u002Fgithub.com\u002FIPedrax\u002FOmniSkill\u002Fblob\u002Fmain\u002Fskills\u002Fvideo\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M79MZV8SR0N02YX539Z5PS5E","vgpu","https:\u002F\u002Fgithub.com\u002FIPedrax\u002FOmniSkill\u002Fblob\u002Fmain\u002Fskills\u002Fvgpu\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M79MZS7JG9X0T4T5TGA4MMJS","uisfx","https:\u002F\u002Fgithub.com\u002FIPedrax\u002FOmniSkill\u002Fblob\u002Fmain\u002Fskills\u002Fuisfx\u002FSKILL.md",[],[]]