[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MH772RFH5BEBB4ZP3JRPZP":3,"skill-same:01M6MH772RFH5BEBB4ZP3JRPZP":91},{"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":30,"publishedAt":51,"linkOnly":52,"markdownContent":53,"markdownBody":54,"frontMatter":55,"refName":71,"commitSha":72,"skillDirectory":73,"forksCount":13,"repositoryHtmlUrl":74,"repositoryHomepageUrl":6,"ownerHtmlUrl":75,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":76,"install":77,"resources":90},"01M6MH772RFH5BEBB4ZP3JRPZP","stage-launch",null,"Phase 2 of building a Claude Managed Agent — turn a validated build sheet into exact API payloads and a resumable BYOK curl launch script, then launch (environment → agent → session → kickoff) using the founder's OWN Anthropic key. Use when the user says \"launch it\", \"deploy the agent\", \"create the agent now\", or when the orchestrator routes phase=stage-launch. payload_generator.py emits the four ordered payloads; launch_script_writer.py writes launch.sh that reads $ANTHROPIC_API_KEY at runtime and never embeds it; payload_validator.py runs a pre-launch check including an API-key-leak scan. No tool in this skill makes network calls — the user runs launch.sh themselves. Distinct from interview (planning) and grade-iterate (the outcome loop).","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-gemini-skills-stage-launch-skill-70780026\u002FSKILL.md",[17,22,25],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":26,"categoryName":27,"taxonomyType":28,"taxonomyTypeDesc":29},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50],"launch","stage launch","stage","managed","cli","at","validator","now","kickoff","writer","opencode","never","byok","outcome","orchestrator","cma","loop","api","code","create","2026-11-10 10:12:30",false,"---\nname: stage-launch\ndescription: Phase 2 of building a Claude Managed Agent — turn a validated build sheet into exact API payloads and a resumable BYOK curl launch script, then launch (environment → agent → session → kickoff) using the founder's OWN Anthropic key. Use when the user says \"launch it\", \"deploy the agent\", \"create the agent now\", or when the orchestrator routes phase=stage-launch. payload_generator.py emits the four ordered payloads; launch_script_writer.py writes launch.sh that reads $ANTHROPIC_API_KEY at runtime and never embeds it; payload_validator.py runs a pre-launch check including an API-key-leak scan. No tool in this skill makes network calls — the user runs launch.sh themselves. Distinct from interview (planning) and grade-iterate (the outcome loop).\nversion: 2.11.2\nauthor: Alireza Rezvani\nlicense: MIT\ntags: [cma, launch, payloads, curl, byok, api-key-safety, environment, agent, session]\ncompatible_tools: [claude-code, codex-cli, cursor, antigravity, opencode, gemini-cli]\n---\n\n# Phase 2 — Stage → Launch\n\nTurn the build sheet into runnable artifacts, then let the founder launch with\ntheir own key. **No script here touches the network or the key** — the user runs\n`launch.sh`.\n\n## Workflow\n\n1. **Generate payloads.**\n   ```bash\n   python3 scripts\u002Fpayload_generator.py \\\n     --sheet .\u002Fmy-agent\u002Fbuild-sheet.json --out-dir .\u002Fmy-agent\n   # -> .\u002Fmy-agent\u002Fpayloads\u002F{01-environment,02-agent,03-session,04-kickoff}.json\n   ```\n   Agent toolset → `always_allow`; every MCP toolset → `always_ask` (baked into\n   the agent payload's `permission_policies`).\n2. **Write the launch script.**\n   ```bash\n   python3 scripts\u002Flaunch_script_writer.py --out-dir .\u002Fmy-agent\n   ```\n   `launch.sh` creates environment → agent → session → kickoff **in order**,\n   chaining IDs, and **resumes** on re-run (each step skips if its `*.id` file\n   exists). It reads `$ANTHROPIC_API_KEY` at runtime.\n3. **Validate before launch.**\n   ```bash\n   python3 scripts\u002Fpayload_validator.py --dir .\u002Fmy-agent\n   ```\n   FAIL blocks — especially a `key_leak` finding. Fix and re-run.\n4. **Minimal key step (never in chat).** Check the shell first:\n   ```bash\n   [ -n \"$ANTHROPIC_API_KEY\" ] && echo \"key present\" || echo \"export ANTHROPIC_API_KEY=... first\"\n   ```\n   Point the founder to platform.claude.com → API keys. **Never print the key to\n   chat, never write it to a file.**\n5. **Launch + watch the first poll.**\n   ```bash\n   export ANTHROPIC_API_KEY=...      # in their shell, not in chat\n   .\u002Fmy-agent\u002Flaunch.sh\n   ```\n   Mark checkpoints with Console deep links. Then `goal_state.py set --phase\n   grade-iterate` and advance.\n\n## Hard rules (API-key safety)\n\n- **The key never enters chat, a file, a payload, or a log.** `launch.sh` reads it\n  from the environment; `payload_validator.py` scans for `sk-ant-…` leaks and FAILs.\n- **Sequential launch.** environment → agent → session → kickoff. Watch the first\n  poll foreground before declaring success.\n- **Resumable.** Re-running `launch.sh` continues from the last created ID.\n\n## Forcing-question library (recommend + cite)\n\n1. \"Is the key in your shell env already?\" *Recommend:* check `$ANTHROPIC_API_KEY`\n   before anything. *Cite:* this SKILL, key-safety rules.\n2. \"Cloud or self-hosted environment?\" *Recommend:* cloud for v0. *Cite:*\n   cma-primitives.md (environment).\n3. \"Any MCP server in the payload?\" *Recommend:* keep it `always_ask`. *Cite:*\n   cma-primitives.md (permissions).\n4. \"Did the first poll return idle\u002Frunning cleanly?\" *Recommend:* watch it\n   foreground before moving on. *Cite:* cma-primitives.md (session lifecycle).\n\n## Tools\n\n- `scripts\u002Fpayload_generator.py` — build sheet → 4 ordered API payloads.\n- `scripts\u002Flaunch_script_writer.py` — resumable BYOK curl launcher (no key handling).\n- `scripts\u002Fpayload_validator.py` — pre-launch check + API-key-leak scan.\n","# Phase 2 — Stage → Launch\n\nTurn the build sheet into runnable artifacts, then let the founder launch with\ntheir own key. **No script here touches the network or the key** — the user runs\n`launch.sh`.\n\n## Workflow\n\n1. **Generate payloads.**\n   ```bash\n   python3 scripts\u002Fpayload_generator.py \\\n     --sheet .\u002Fmy-agent\u002Fbuild-sheet.json --out-dir .\u002Fmy-agent\n   # -> .\u002Fmy-agent\u002Fpayloads\u002F{01-environment,02-agent,03-session,04-kickoff}.json\n   ```\n   Agent toolset → `always_allow`; every MCP toolset → `always_ask` (baked into\n   the agent payload's `permission_policies`).\n2. **Write the launch script.**\n   ```bash\n   python3 scripts\u002Flaunch_script_writer.py --out-dir .\u002Fmy-agent\n   ```\n   `launch.sh` creates environment → agent → session → kickoff **in order**,\n   chaining IDs, and **resumes** on re-run (each step skips if its `*.id` file\n   exists). It reads `$ANTHROPIC_API_KEY` at runtime.\n3. **Validate before launch.**\n   ```bash\n   python3 scripts\u002Fpayload_validator.py --dir .\u002Fmy-agent\n   ```\n   FAIL blocks — especially a `key_leak` finding. Fix and re-run.\n4. **Minimal key step (never in chat).** Check the shell first:\n   ```bash\n   [ -n \"$ANTHROPIC_API_KEY\" ] && echo \"key present\" || echo \"export ANTHROPIC_API_KEY=... first\"\n   ```\n   Point the founder to platform.claude.com → API keys. **Never print the key to\n   chat, never write it to a file.**\n5. **Launch + watch the first poll.**\n   ```bash\n   export ANTHROPIC_API_KEY=...      # in their shell, not in chat\n   .\u002Fmy-agent\u002Flaunch.sh\n   ```\n   Mark checkpoints with Console deep links. Then `goal_state.py set --phase\n   grade-iterate` and advance.\n\n## Hard rules (API-key safety)\n\n- **The key never enters chat, a file, a payload, or a log.** `launch.sh` reads it\n  from the environment; `payload_validator.py` scans for `sk-ant-…` leaks and FAILs.\n- **Sequential launch.** environment → agent → session → kickoff. Watch the first\n  poll foreground before declaring success.\n- **Resumable.** Re-running `launch.sh` continues from the last created ID.\n\n## Forcing-question library (recommend + cite)\n\n1. \"Is the key in your shell env already?\" *Recommend:* check `$ANTHROPIC_API_KEY`\n   before anything. *Cite:* this SKILL, key-safety rules.\n2. \"Cloud or self-hosted environment?\" *Recommend:* cloud for v0. *Cite:*\n   cma-primitives.md (environment).\n3. \"Any MCP server in the payload?\" *Recommend:* keep it `always_ask`. *Cite:*\n   cma-primitives.md (permissions).\n4. \"Did the first poll return idle\u002Frunning cleanly?\" *Recommend:* watch it\n   foreground before moving on. *Cite:* cma-primitives.md (session lifecycle).\n\n## Tools\n\n- `scripts\u002Fpayload_generator.py` — build sheet → 4 ordered API payloads.\n- `scripts\u002Flaunch_script_writer.py` — resumable BYOK curl launcher (no key handling).\n- `scripts\u002Fpayload_validator.py` — pre-launch check + API-key-leak scan.\n",{"name":5,"tags":56,"author":63,"license":14,"version":64,"description":7,"compatible_tools":65},[46,31,57,58,43,59,60,61,62],"payloads","curl","api-key-safety","environment","agent","session","Alireza Rezvani","2.11.2",[66,67,68,69,41,70],"claude-code","codex-cli","cursor","antigravity","gemini-cli","main","068c2486ccc0f8d200a3db4d21ec137064eda3b4","skills\u002Fpublic-02-claude-skills-main-gemini-skills-stage-launch-skill-70780026","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing","https:\u002F\u002Fgithub.com\u002FJiayiV","2026-08-25 16:30:52",{"source":8,"skillName":5,"commands":78,"prompt":88,"zipAvailable":89},[79,82,85],{"tool":80,"command":81},"npx","npx skills add JiayiV\u002Fquestion_mixing --skill stage-launch",{"tool":83,"command":84},"bunx","bunx skills add JiayiV\u002Fquestion_mixing --skill stage-launch",{"tool":86,"command":87},"pnpm","pnpm dlx skills add JiayiV\u002Fquestion_mixing --skill stage-launch","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fpublic-02-claude-skills-main-gemini-skills-stage-launch-skill-70780026\u002FSKILL.md",true,[],[92,117,143,172,200,233],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":51},"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",[],[94,99,100,101,102,49,103,104,105,106,107,108,109,110,111,112,113,114,115,116],"github","ai agents","web","notes","browser","https","actions","manifest","inventory","verify","tool","use","ready","unrelated","app","scope","for","webmcp",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":121,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":51},"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",[],[125,126,127,35,128,129,130,131,132,133,134,135,136,137,138,139,140,141,36,142],"vardoger analyze","analyze","directory","github copilot","copilot","run","update","learn","network","my style","install","conversation","me","local","github copilot cli","pipx","my","copilot instructions",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":153,"publishedAt":51},"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",[149,152],{"categoryNo":150,"categoryName":151,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[154,155,156,157,158,159,160,161,162,163,164,165,166,110,167,168,169,170,115,171],"transloadit media processing","Media","media processing","processing","MCP","mcp server","documents","subtitles","pipeline","ocr","Video","Audio","mp4","images","files","transformation","free","hls",{"skillNo":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":181,"publishedAt":51},"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",[178],{"categoryNo":179,"categoryName":180,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[182,183,184,185,186,187,188,189,190,110,191,192,193,194,195,196,197,198,199,115],"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":201,"name":202,"nameZh":6,"description":203,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":215,"publishedAt":51},"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",[206,209,212],{"categoryNo":207,"categoryName":208,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":210,"categoryName":211,"taxonomyType":28,"taxonomyTypeDesc":29},"01JBSEEDCAT000000000000036","内容创作者",{"categoryNo":213,"categoryName":214,"taxonomyType":28,"taxonomyTypeDesc":29},"01JBSEEDCAT000000000000038","人力资源",[216,217,218,219,220,221,222,223,126,224,110,225,226,227,228,229,230,231,115,232],"search","Job Search","technical job search","technical","writing","tasks","email","parsing","interview","up","engineer","general","activate","do","task","cv","letter",{"skillNo":234,"name":235,"nameZh":6,"description":236,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":237,"categories":238,"keywords":239,"publishedAt":51},"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",[],[240,241,242,243,244,219,245,110,229,246,247,248,249,250,251,252,253,254,115,255],"steno mode","mode","customer","brief","first","tutorial","teaching","tokens","as","trigger","structured output","machine","output","court","requests","response compression"]