[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MD8JWNAQMMEWZPQR4TRFNX":3,"skill-same:01M6MD8JWNAQMMEWZPQR4TRFNX":75},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":25,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":13,"repositoryHtmlUrl":58,"repositoryHomepageUrl":6,"ownerHtmlUrl":59,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":60,"install":61,"resources":74},"01M6MD8JWNAQMMEWZPQR4TRFNX","ship-gate",null,"Pre-production audit that scans a codebase for security, database, deployment, code quality, AI\u002FLLM, dependency, frontend, and observability issues. Intercepts deploy commands and blocks until critical items pass. Stack-agnostic. Use for \"run ship gate\", \"am I ready to ship\", \"pre-launch audit\", \"can I deploy\", \"push to production\", \"go live checklist\", \"preflight check\". Not for CI\u002FCD setup or infra provisioning.","JiayiV\u002Fquestion_mixing","JiayiV","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54466889?v=4","01M6JFJYYMRZ3QRGP9339JNQ2K","01M6JFJZ35KB0QVT50NAHPJA7G",0,"MIT","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fpublic-02-claude-skills-main-engineering-skills-ship-gate-skill-c5aa1dee\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"gate","ship","ship gate","stack","CI\u002FCD","critical","live","commands","production audit","ready","dependency","frontend","ci","audit","database","issues","code","run","security","go","2026-11-10 10:12:30",false,"---\nname: ship-gate\ndescription: >\n  Pre-production audit that scans a codebase for security, database,\n  deployment, code quality, AI\u002FLLM, dependency, frontend, and observability\n  issues. Intercepts deploy commands and blocks until critical items pass.\n  Stack-agnostic. Use for \"run ship gate\", \"am I ready to ship\",\n  \"pre-launch audit\", \"can I deploy\", \"push to production\", \"go live\n  checklist\", \"preflight check\". Not for CI\u002FCD setup or infra provisioning.\nlicense: MIT\nmetadata:\n  author: Rajaraman Arumugam\n  version: 1.0.0\n---\n\n# Ship Gate\n\nPre-production audit that scans a codebase and reports pass\u002Ffail\u002Fmanual\nacross 8 categories before anything ships.\n\n## Intercept Behavior\n\nWhen the user says \"push to production\", \"deploy\", \"ship it\", \"go live\",\nor similar deploy-intent phrases, do NOT proceed with deployment. Instead:\n\n1. Ask: \"Have you run the ship gate? Want me to scan now?\"\n2. If yes, run the full audit below.\n3. If the user says they already ran it, ask when. If more than 24 hours\n   ago or if code changed since, recommend re-running.\n\n## How It Works\n\n### Step 1: Detect Stack\n\nRun these checks in order to identify the project stack:\n\n```\nFramework detection:\n  package.json exists        -> Node.js project\n    \"next\" in dependencies   -> Next.js\n    \"react\" in dependencies  -> React (if not Next.js)\n    \"vue\" in dependencies    -> Vue\n    \"svelte\" in dependencies -> Svelte\n    \"astro\" in dependencies  -> Astro\n    \"express\" in dependencies -> Express\n    \"fastify\" in dependencies -> Fastify\n    \"hono\" in dependencies   -> Hono\n  requirements.txt or pyproject.toml -> Python project\n    \"django\" present         -> Django\n    \"flask\" present          -> Flask\n    \"fastapi\" present        -> FastAPI\n  go.mod exists              -> Go project\n  Cargo.toml exists          -> Rust project\n\nDatabase detection:\n  \"@supabase\u002Fsupabase-js\" in package.json -> Supabase\n  supabase\u002F directory exists              -> Supabase\n  \"prisma\" in dependencies                -> Prisma (check schema for DB type)\n  \"mongoose\" in dependencies              -> MongoDB\n  \"pg\" or \"postgres\" in dependencies      -> PostgreSQL\n  firebase.json or .firebaserc exists     -> Firebase\n\nDeploy target detection:\n  vercel.json or .vercel\u002F exists          -> Vercel\n  netlify.toml exists                     -> Netlify\n  Dockerfile exists                       -> Docker\u002FVPS\n  fly.toml exists                         -> Fly.io\n  railway.json exists                     -> Railway\n  .platform\u002Fapplications.yaml            -> Platform.sh\n\nAuth detection:\n  \"@clerk\" in dependencies                -> Clerk\n  \"next-auth\" in dependencies             -> NextAuth\n  \"@supabase\u002Fauth-helpers\" in deps        -> Supabase Auth\n  \"firebase\u002Fauth\" in imports              -> Firebase Auth\n\nAI\u002FLLM detection:\n  \"openai\" in dependencies                -> OpenAI\n  \"@anthropic-ai\u002Fsdk\" in dependencies     -> Claude API\n  \"@google\u002Fgenerative-ai\" in deps         -> Gemini\n```\n\nReport detected stack before proceeding. This determines which checks\nare relevant. Checks tagged with a specific stack in `references\u002Fchecks.md`\nare skipped if that stack is not detected.\n\n### Step 2: Run Automated Checks\n\nRun categories in this order: SEC, DB, CODE, DEP, AI, DEPLOY, FE, OBS.\nSecurity and database first because they produce the most critical findings.\n\nFor each category, run every auto-scannable check from\n`references\u002Fchecks.md` using the patterns in `references\u002Fpatterns.md`.\n\nReport progress after each category completes:\n```\n[1\u002F8] Security: 3 FAIL, 12 PASS, 3 SKIP\n[2\u002F8] Database: 1 FAIL, 5 PASS, 6 SKIP\n...\n```\n\nReport results as:\n- PASS: check passed\n- FAIL: issue found (with file path and line number)\n- SKIP: not applicable to this stack\n\n### Step 3: Manual Confirmation\n\nFor checks that cannot be automated (backup restore tested, rollback plan\nexists, staging test passed), present them as a checklist and ask the user\nto confirm each one.\n\n### Step 4: Verdict\n\nClassify results into three severities:\n- CRITICAL: must fix before shipping (secrets exposed, no auth on routes,\n  no HTTPS, SQL injection vectors, no RLS on Supabase tables)\n- HIGH: should fix before shipping (no error boundaries, no rate limiting,\n  console.logs in production, no pagination)\n- ADVISORY: recommended but not blocking (no OG tags, no custom 404,\n  no analytics, no SBOM)\n\nFinal output:\n\n```\nSHIP GATE REPORT\n================\nStack: Next.js + Supabase + Vercel\nScan time: 12s\n\nCRITICAL (3 items, must fix)\n  FAIL  [SEC-01] API key found in src\u002Flib\u002Fapi.ts:14\n  FAIL  [DB-07] RLS not enabled on \"profiles\" table\n  FAIL  [SEC-05] No CSRF protection on \u002Fapi\u002Fcheckout\n\nHIGH (5 items, should fix)\n  FAIL  [CODE-01] 12 console.log statements in production code\n  FAIL  [CODE-03] Empty catch block in src\u002Futils\u002Fauth.ts:45\n  FAIL  [DEP-04] 3 critical npm audit vulnerabilities\n  FAIL  [DEPLOY-05] No rollback plan documented\n  MANUAL [DEPLOY-06] Staging test not confirmed\n\nADVISORY (4 items, recommended)\n  FAIL  [FE-01] Missing OG meta tags\n  FAIL  [FE-03] No custom 404 page\n  PASS  [OBS-01] Error monitoring configured\n  SKIP  [AI-01] No AI\u002FLLM usage detected\n\nVERDICT: DO NOT SHIP (3 critical issues)\nFix critical items and re-run.\n```\n\nIf zero critical items remain, verdict is: CLEAR TO SHIP.\nIf only high items remain, verdict is: SHIP WITH CAUTION (acknowledge risks).\n\n## Categories\n\nEight categories, each with a code prefix. Full check details in\n`references\u002Fchecks.md`.\n\n| Prefix | Category | Auto | Manual | Tool |\n|--------|----------|------|--------|------|\n| SEC | Security | 15 | 3 | 0 |\n| DB | Database | 7 | 5 | 0 |\n| DEPLOY | Deployment | 3 | 8 | 0 |\n| CODE | Code Quality | 11 | 0 | 1 |\n| AI | AI\u002FLLM Security | 5 | 3 | 0 |\n| DEP | Dependencies | 5 | 0 | 1 |\n| FE | Frontend Quality | 7 | 3 | 0 |\n| OBS | Observability | 2 | 5 | 0 |\n\n## Scope\n\nThis skill audits. It does not fix. When it finds issues, it reports\nthem with file locations and remediation guidance. The user or another\nskill (systematic-debugging, backend-patterns, shadcn-stack) handles\nthe fix.\n\nThis skill does not:\n- Set up CI\u002FCD pipelines\n- Provision infrastructure\n- Configure monitoring tools\n- Run after deployment (it is pre-deploy only)\n\n## Integration Points\n\n- **karpathy-coder**: run ship-gate after karpathy-check passes — simplicity first, then production readiness\n- **adversarial-reviewer**: deep security review for items ship-gate flags as critical\n- **security-pen-testing**: penetration testing methodology for SEC-category findings\n- **code-reviewer**: general code quality review complements ship-gate's automated checks\n","# Ship Gate\n\nPre-production audit that scans a codebase and reports pass\u002Ffail\u002Fmanual\nacross 8 categories before anything ships.\n\n## Intercept Behavior\n\nWhen the user says \"push to production\", \"deploy\", \"ship it\", \"go live\",\nor similar deploy-intent phrases, do NOT proceed with deployment. Instead:\n\n1. Ask: \"Have you run the ship gate? Want me to scan now?\"\n2. If yes, run the full audit below.\n3. If the user says they already ran it, ask when. If more than 24 hours\n   ago or if code changed since, recommend re-running.\n\n## How It Works\n\n### Step 1: Detect Stack\n\nRun these checks in order to identify the project stack:\n\n```\nFramework detection:\n  package.json exists        -> Node.js project\n    \"next\" in dependencies   -> Next.js\n    \"react\" in dependencies  -> React (if not Next.js)\n    \"vue\" in dependencies    -> Vue\n    \"svelte\" in dependencies -> Svelte\n    \"astro\" in dependencies  -> Astro\n    \"express\" in dependencies -> Express\n    \"fastify\" in dependencies -> Fastify\n    \"hono\" in dependencies   -> Hono\n  requirements.txt or pyproject.toml -> Python project\n    \"django\" present         -> Django\n    \"flask\" present          -> Flask\n    \"fastapi\" present        -> FastAPI\n  go.mod exists              -> Go project\n  Cargo.toml exists          -> Rust project\n\nDatabase detection:\n  \"@supabase\u002Fsupabase-js\" in package.json -> Supabase\n  supabase\u002F directory exists              -> Supabase\n  \"prisma\" in dependencies                -> Prisma (check schema for DB type)\n  \"mongoose\" in dependencies              -> MongoDB\n  \"pg\" or \"postgres\" in dependencies      -> PostgreSQL\n  firebase.json or .firebaserc exists     -> Firebase\n\nDeploy target detection:\n  vercel.json or .vercel\u002F exists          -> Vercel\n  netlify.toml exists                     -> Netlify\n  Dockerfile exists                       -> Docker\u002FVPS\n  fly.toml exists                         -> Fly.io\n  railway.json exists                     -> Railway\n  .platform\u002Fapplications.yaml            -> Platform.sh\n\nAuth detection:\n  \"@clerk\" in dependencies                -> Clerk\n  \"next-auth\" in dependencies             -> NextAuth\n  \"@supabase\u002Fauth-helpers\" in deps        -> Supabase Auth\n  \"firebase\u002Fauth\" in imports              -> Firebase Auth\n\nAI\u002FLLM detection:\n  \"openai\" in dependencies                -> OpenAI\n  \"@anthropic-ai\u002Fsdk\" in dependencies     -> Claude API\n  \"@google\u002Fgenerative-ai\" in deps         -> Gemini\n```\n\nReport detected stack before proceeding. This determines which checks\nare relevant. Checks tagged with a specific stack in `references\u002Fchecks.md`\nare skipped if that stack is not detected.\n\n### Step 2: Run Automated Checks\n\nRun categories in this order: SEC, DB, CODE, DEP, AI, DEPLOY, FE, OBS.\nSecurity and database first because they produce the most critical findings.\n\nFor each category, run every auto-scannable check from\n`references\u002Fchecks.md` using the patterns in `references\u002Fpatterns.md`.\n\nReport progress after each category completes:\n```\n[1\u002F8] Security: 3 FAIL, 12 PASS, 3 SKIP\n[2\u002F8] Database: 1 FAIL, 5 PASS, 6 SKIP\n...\n```\n\nReport results as:\n- PASS: check passed\n- FAIL: issue found (with file path and line number)\n- SKIP: not applicable to this stack\n\n### Step 3: Manual Confirmation\n\nFor checks that cannot be automated (backup restore tested, rollback plan\nexists, staging test passed), present them as a checklist and ask the user\nto confirm each one.\n\n### Step 4: Verdict\n\nClassify results into three severities:\n- CRITICAL: must fix before shipping (secrets exposed, no auth on routes,\n  no HTTPS, SQL injection vectors, no RLS on Supabase tables)\n- HIGH: should fix before shipping (no error boundaries, no rate limiting,\n  console.logs in production, no pagination)\n- ADVISORY: recommended but not blocking (no OG tags, no custom 404,\n  no analytics, no SBOM)\n\nFinal output:\n\n```\nSHIP GATE REPORT\n================\nStack: Next.js + Supabase + Vercel\nScan time: 12s\n\nCRITICAL (3 items, must fix)\n  FAIL  [SEC-01] API key found in src\u002Flib\u002Fapi.ts:14\n  FAIL  [DB-07] RLS not enabled on \"profiles\" table\n  FAIL  [SEC-05] No CSRF protection on \u002Fapi\u002Fcheckout\n\nHIGH (5 items, should fix)\n  FAIL  [CODE-01] 12 console.log statements in production code\n  FAIL  [CODE-03] Empty catch block in src\u002Futils\u002Fauth.ts:45\n  FAIL  [DEP-04] 3 critical npm audit vulnerabilities\n  FAIL  [DEPLOY-05] No rollback plan documented\n  MANUAL [DEPLOY-06] Staging test not confirmed\n\nADVISORY (4 items, recommended)\n  FAIL  [FE-01] Missing OG meta tags\n  FAIL  [FE-03] No custom 404 page\n  PASS  [OBS-01] Error monitoring configured\n  SKIP  [AI-01] No AI\u002FLLM usage detected\n\nVERDICT: DO NOT SHIP (3 critical issues)\nFix critical items and re-run.\n```\n\nIf zero critical items remain, verdict is: CLEAR TO SHIP.\nIf only high items remain, verdict is: SHIP WITH CAUTION (acknowledge risks).\n\n## Categories\n\nEight categories, each with a code prefix. Full check details in\n`references\u002Fchecks.md`.\n\n| Prefix | Category | Auto | Manual | Tool |\n|--------|----------|------|--------|------|\n| SEC | Security | 15 | 3 | 0 |\n| DB | Database | 7 | 5 | 0 |\n| DEPLOY | Deployment | 3 | 8 | 0 |\n| CODE | Code Quality | 11 | 0 | 1 |\n| AI | AI\u002FLLM Security | 5 | 3 | 0 |\n| DEP | Dependencies | 5 | 0 | 1 |\n| FE | Frontend Quality | 7 | 3 | 0 |\n| OBS | Observability | 2 | 5 | 0 |\n\n## Scope\n\nThis skill audits. It does not fix. When it finds issues, it reports\nthem with file locations and remediation guidance. The user or another\nskill (systematic-debugging, backend-patterns, shadcn-stack) handles\nthe fix.\n\nThis skill does not:\n- Set up CI\u002FCD pipelines\n- Provision infrastructure\n- Configure monitoring tools\n- Run after deployment (it is pre-deploy only)\n\n## Integration Points\n\n- **karpathy-coder**: run ship-gate after karpathy-check passes — simplicity first, then production readiness\n- **adversarial-reviewer**: deep security review for items ship-gate flags as critical\n- **security-pen-testing**: penetration testing methodology for SEC-category findings\n- **code-reviewer**: general code quality review complements ship-gate's automated checks\n",{"name":5,"license":14,"metadata":51,"description":54},{"author":52,"version":53},"Rajaraman Arumugam","1.0.0","Pre-production audit that scans a codebase for security, database, deployment, code quality, AI\u002FLLM, dependency, frontend, and observability issues. Intercepts deploy commands and blocks until critical items pass. Stack-agnostic. Use for \"run ship gate\", \"am I ready to ship\", \"pre-launch audit\", \"can I deploy\", \"push to production\", \"go live checklist\", \"preflight check\". Not for CI\u002FCD setup or infra provisioning.\n","main","068c2486ccc0f8d200a3db4d21ec137064eda3b4","skills\u002Fpublic-02-claude-skills-main-engineering-skills-ship-gate-skill-c5aa1dee","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing","https:\u002F\u002Fgithub.com\u002FJiayiV","2026-08-25 16:30:52",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add JiayiV\u002Fquestion_mixing --skill ship-gate",{"tool":67,"command":68},"bunx","bunx skills add JiayiV\u002Fquestion_mixing --skill ship-gate",{"tool":70,"command":71},"pnpm","pnpm dlx skills add JiayiV\u002Fquestion_mixing --skill ship-gate","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fpublic-02-claude-skills-main-engineering-skills-ship-gate-skill-c5aa1dee\u002FSKILL.md",true,[],[76,100,127,158,184,219],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":46},"01M6NN9PJS9NHWPDG4QP93BP8F","webmcpify","Make a web app agent-ready — propose a WebMCP tool manifest, integrate, verify in a real browser, heal; unrelated code stays untouched. Use for \"webmcpify\", \"add WebMCP\", or \"expose app actions to AI agents\".","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fwebmcpify\u002FSKILL.md",[],[78,83,84,85,86,42,87,88,89,90,91,92,93,94,35,95,96,97,98,99],"github","ai agents","web","notes","browser","https","actions","manifest","inventory","verify","tool","use","unrelated","app","scope","for","webmcp",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":104,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":46},"01M6NN6KZE5RBN6NGHN2WXV1RE","vardoger-analyze","Use when the user asks to personalize the GitHub Copilot CLI assistant, adapt Copilot to their style, use vardoger, or analyze their Copilot CLI conversation history. Reads the local session directory at `~\u002F.copilot\u002Fsession-state\u002F`, extracts recurring preferences and conventions, and writes a fenced personalization block into `~\u002F.copilot\u002Fcopilot-instructions.md`. Runs entirely on the user's machine via the local `vardoger` CLI (`pipx install vardoger`); no network calls and no uploads. Triggers: 'personalize my copilot', 'analyze my copilot history', 'tailor copilot to me', 'run vardoger', 'update my copilot instructions from history', 'make copilot learn my style'.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fvardoger-analyze\u002FSKILL.md",[],[108,109,110,111,112,113,43,114,115,116,117,118,119,120,121,122,123,124,125,126],"vardoger analyze","analyze","directory","cli","github copilot","copilot","update","learn","network","my style","install","conversation","me","local","github copilot cli","pipx","my","at","copilot instructions",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":139,"publishedAt":46},"01M6NN3CZGQP3XAJ04BM1NNYGT","transloadit-media-processing","Process media files (video, audio, images, documents) using Transloadit. Use when asked to encode video to HLS\u002FMP4, generate thumbnails, resize or watermark images, extract audio, concatenate clips, add subtitles, OCR documents, or run any media processing pipeline. Covers 86+ processing robots for file transformation at scale.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Ftransloadit-media-processing\u002FSKILL.md",[133,136],{"categoryNo":134,"categoryName":135,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":137,"categoryName":138,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[140,141,142,143,144,145,146,147,148,149,150,151,152,94,153,154,155,156,98,157],"transloadit media processing","Media","media processing","processing","MCP","mcp server","documents","subtitles","pipeline","ocr","Video","Audio","mp4","images","files","transformation","free","hls",{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":165,"publishedAt":46},"01M6NN28E92F9GH4WFYQ2H1Y15","terraform-azurerm-set-diff-analyzer","Analyze Terraform plan JSON output for AzureRM Provider to distinguish between false-positive diffs (order-only changes in Set-type attributes) and actual resource changes. Use when reviewing terraform plan output for Azure resources like Application Gateway, Load Balancer, Firewall, Front Door, NSG, and other resources with Set-type attributes that cause spurious diffs due to internal ordering changes.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fterraform-azurerm-set-diff-analyzer\u002FSKILL.md",[164],{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[166,167,168,169,170,171,172,173,174,94,175,176,177,178,179,180,181,182,183,98],"terraform","SET","terraform azurerm set diff analyzer","diff","analyzer","diffs","azure","gateway","firewall","only","resource changes","provider","resources","load balancer","attributes","front","load","balancer",{"skillNo":185,"name":186,"nameZh":6,"description":187,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":188,"categories":189,"keywords":201,"publishedAt":46},"01M6NN1QMH2TDYWTH3XY3N5XPV","technical-job-search","Use this skill when a software engineer asks for help with job search tasks: parsing or analyzing a job description, tailoring a CV\u002Fresume, writing a cover letter, evaluating a job offer, or drafting a post-interview follow-up email. Do not activate for general career advice unrelated to an active job search action.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Ftechnical-job-search\u002FSKILL.md",[190,193,198],{"categoryNo":191,"categoryName":192,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":194,"categoryName":195,"taxonomyType":196,"taxonomyTypeDesc":197},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",{"categoryNo":199,"categoryName":200,"taxonomyType":196,"taxonomyTypeDesc":197},"01JBSEEDCAT000000000000038","人力资源",[202,203,204,205,206,207,208,209,109,210,94,211,212,213,214,215,216,217,98,218],"search","Job Search","technical job search","technical","writing","tasks","email","parsing","interview","up","engineer","general","activate","do","task","cv","letter",{"skillNo":220,"name":221,"nameZh":6,"description":222,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":223,"categories":224,"keywords":225,"publishedAt":46},"01M6NMZFA67XYS1GS09WT42235","steno-mode","Shorthand-first response compression that cuts ~40% of response tokens while preserving technical precision and exact literals. Use when the user says \"steno mode\", \"shorthand mode\", \"compressed responses\", \"token reduction\", \"brief structured output\", or invokes \u002Fsteno. Supports four compression levels: lite, brief, court, machine. Do not trigger for requests needing polished prose such as onboarding\u002Ftutorial content, stakeholder or customer-facing copy, or teaching-focused explanations.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fsteno-mode\u002FSKILL.md",[],[226,227,228,229,230,205,231,94,215,232,233,234,235,236,237,238,239,240,98,241],"steno mode","mode","customer","brief","first","tutorial","teaching","tokens","as","trigger","structured output","machine","output","court","requests","response compression"]