[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F8AGPSZETNFJRBJMPJKDQR":3,"skill-same:01M7F8AGPSZETNFJRBJMPJKDQR":67},{"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":36,"commitSha":37,"skillDirectory":38,"forksCount":39,"repositoryHtmlUrl":40,"repositoryHomepageUrl":6,"ownerHtmlUrl":41,"ownerBlogUrl":6,"ownerDescription":42,"updatedAt":43,"install":44,"resources":56},"01M7F8AGPSZETNFJRBJMPJKDQR","create-app",null,"End-to-end app creation from a single description. Five tiers: blank project, guided, templated, fully generated, or feature addition to existing codebase. Routes through PRD, architecture, and Archon campaign with verification at every step.","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\u002F06-前端与设计\u002Fcreate-app\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: create-app\nlicense: MIT\ndescription: >-\n  End-to-end app creation from a single description. Five tiers: blank project,\n  guided, templated, fully generated, or feature addition to existing codebase.\n  Routes through PRD, architecture, and Archon campaign with verification at every step.\nuser-invocable: true\nauto-trigger: false\ntrigger_keywords:\n  - create app\n  - build app\n  - build me\n  - make an app\n  - new app\n  - generate app\n  - add auth\n  - add payments\n  - integrate\neffort: max\n---\n\n# \u002Fcreate-app — From Description to Verified Application\n\n## Orientation\n\n**Use when:** building a new app from scratch -- full scaffold, design system, and feature set from a single description.\n**Don't use when:** adding a feature to an existing app (use \u002Fmarshal or \u002Farchon); generating a single component (use \u002Fscaffold).\n\n## Tier Detection\n\nUse when the user wants to create an app, add a feature, or scaffold a project. Classify the input into one of five tiers:\n\n### Tier 1: Blank Project\n- Trigger: \"create a blank project\", \"new project\", \"scaffold\"\n- Action: Run \u002Fscaffold with stack detection. No PRD, no architecture.\n\n### Tier 2: Guided\n- Trigger: \"I want to build...\", \"help me create...\", description with questions\n- Action: \u002Fprd → user approves → \u002Farchitect → user approves → \u002Farchon\n- Human checkpoints: after PRD, after architecture, before each major phase.\n\n### Tier 3: Templated\n- Trigger: Describes a well-known app type (\"a todo app\", \"a blog\", \"a dashboard with auth\")\n- Action: Load template PRD if available → \u002Farchitect with template defaults → \u002Farchon\n- Template detection: check `.planning\u002F_templates\u002Fapp-types\u002F` for matching templates.\n  If no template matches, fall through to Tier 2.\n\n### Tier 4: Generated (Full Autonomy)\n- Trigger: \"build me [detailed description]\", \"create [app] and deploy it\"\n- Action: \u002Fprd (minimal questions) → \u002Farchitect (auto-approve if confidence high) → \u002Farchon with self-correction loop\n- Human checkpoints: after PRD only. Architecture and execution are autonomous.\n- Safety: all Archon self-correction mechanisms active. Direction alignment every\n  2 phases. Quality spot-checks every phase. Circuit breakers armed.\n\n### Tier 5: Feature Addition (Existing Codebase)\n- Trigger: existing project + feature description (\"add auth\", \"add a dashboard\", \"add dark mode\")\n- Detection: project has source files (src\u002F, app\u002F, lib\u002F, package.json with deps) AND description is a feature, not a standalone app\n- Action: \u002Fprd in feature mode → \u002Farchitect in existing codebase mode → \u002Farchon\n- Key differences from greenfield tiers:\n  - PRD reads existing codebase before asking questions\n  - Architecture describes changes to existing files, not a standalone system\n  - Phase 0 is always \"Baseline\" — record current typecheck\u002Ftest state\n  - Every phase end condition includes \"no new typecheck errors\" + \"existing tests pass\"\n  - Risk register always includes \"regression in existing functionality\"\n- Human checkpoints: after feature spec (PRD). Architecture can auto-approve if\n  the feature is well-scoped and all conditions are machine-verifiable.\n\n### Tier Classification\n\n| Input Pattern | Tier |\n|---|---|\n| \"blank project\", \"scaffold\", \"new empty\" | 1 |\n| \"help me build\", \"I want to create\", \"guide me\" | 2 |\n| \"todo app\", \"blog\", \"dashboard\", well-known app type | 3 |\n| \"build me [detailed]\", \"create [app]\", confident description | 4 |\n| \"add [feature]\", \"implement [feature]\", existing project + feature description | 5 |\n| Ambiguous | Default to Tier 2 (safest) |\n\n## Protocol\n\n### Step 1: CLASSIFY\n\nRead the user's input. Determine the tier. Announce what you'll do in plain language — not tier numbers. If the classification is wrong, accept user overrides (\"just scaffold it\" → Tier 1, \"just build it\" → Tier 4).\n\n### Step 2: EXECUTE TIER\n\n**Tier 1:** Invoke \u002Fscaffold. Done.\n\n**Tier 2:** \u002Fprd → user approves → \u002Farchitect → user approves → Archon campaign → brief user after each major phase.\n\n**Tier 3:** Check `.planning\u002F_templates\u002Fapp-types\u002F` for template → present PRD, ask for changes → \u002Farchitect with template defaults → Archon campaign.\n\n**Tier 4:**\n1. \u002Fprd express mode (0-1 questions)\n2. User approves PRD (only mandatory checkpoint)\n3. \u002Farchitect (auto-approve if all end conditions are machine-verifiable)\n4. Archon campaign with ALL safety systems active:\n   - Direction alignment every 2 phases, quality spot-check every phase\n   - Circuit breakers: 3 failures = new approach, 5+ type errors = park\n5. Execute autonomously until complete or parked\n6. Run full verification of all PRD end conditions, present results\n\n**Tier 5 (Feature Addition):**\n1. Read existing codebase — file tree, package.json, key entry points, existing patterns\n2. \u002Fprd in feature mode (max 2 questions)\n3. User approves feature spec (one mandatory checkpoint)\n4. \u002Farchitect in existing codebase mode — Phase 0 always \"Baseline\" (run typecheck + tests, record counts). Auto-approve if machine-verifiable.\n5. Archon campaign — every phase end condition includes \"no new typecheck errors vs baseline\" and \"existing tests pass\"\n6. On completion: verify all feature end conditions + baseline regression check, present results\n\n### Step 3: VERIFY (All Tiers except 1)\n\nCheck each PRD end condition (run commands, check files, invoke \u002Flive-preview for visual checks). Report PASS \u002F PARTIAL \u002F FAIL with specifics.\n\n### Step 4: DELIVER\n\nPresent: what was built, what was verified, what needs attention, how to run it, and suggested next step (e.g., \u002Fpostmortem or deploy command).\n\n## Quality Gates\n\n- PRD exists and is approved before any code is written\n- Architecture exists before Archon starts\n- Every campaign phase has machine-verifiable end conditions\n- Final verification checks all PRD end conditions\n- User receives a clear report of what was built and what needs attention\n\n## Fringe Cases\n\n**Vague requirements**: Default to Tier 2 and ask clarifying questions before producing the PRD.\n\n**Project already initialized**: Existing source files (src\u002F, app\u002F, package.json with deps) → automatically classify as Tier 5. Do not scaffold over an existing project.\n\n**If .planning\u002F does not exist**: \u002Fprd and \u002Farchitect will create it. If not possible, present inline and ask the user to run `\u002Fdo setup` first.\n\n**Tier misclassification**: Switch immediately on user correction without re-reading the input.\n\n## Exit Protocol\n\nAfter the campaign completes and verification runs, output:\n\n```\n---HANDOFF---\n- App: {name}\n- Built: {feature ledger summary}\n- Verified: {N}\u002F{total} end conditions passed\n- Status: {complete | partial | failed}\n- To run: {start command}\n- Next: {suggested next step, e.g., \u002Fpostmortem or deploy command}\n- Reversibility: amber -- multi-tier creation, revert the creation commits\n---\n```\n","# \u002Fcreate-app — From Description to Verified Application\n\n## Orientation\n\n**Use when:** building a new app from scratch -- full scaffold, design system, and feature set from a single description.\n**Don't use when:** adding a feature to an existing app (use \u002Fmarshal or \u002Farchon); generating a single component (use \u002Fscaffold).\n\n## Tier Detection\n\nUse when the user wants to create an app, add a feature, or scaffold a project. Classify the input into one of five tiers:\n\n### Tier 1: Blank Project\n- Trigger: \"create a blank project\", \"new project\", \"scaffold\"\n- Action: Run \u002Fscaffold with stack detection. No PRD, no architecture.\n\n### Tier 2: Guided\n- Trigger: \"I want to build...\", \"help me create...\", description with questions\n- Action: \u002Fprd → user approves → \u002Farchitect → user approves → \u002Farchon\n- Human checkpoints: after PRD, after architecture, before each major phase.\n\n### Tier 3: Templated\n- Trigger: Describes a well-known app type (\"a todo app\", \"a blog\", \"a dashboard with auth\")\n- Action: Load template PRD if available → \u002Farchitect with template defaults → \u002Farchon\n- Template detection: check `.planning\u002F_templates\u002Fapp-types\u002F` for matching templates.\n  If no template matches, fall through to Tier 2.\n\n### Tier 4: Generated (Full Autonomy)\n- Trigger: \"build me [detailed description]\", \"create [app] and deploy it\"\n- Action: \u002Fprd (minimal questions) → \u002Farchitect (auto-approve if confidence high) → \u002Farchon with self-correction loop\n- Human checkpoints: after PRD only. Architecture and execution are autonomous.\n- Safety: all Archon self-correction mechanisms active. Direction alignment every\n  2 phases. Quality spot-checks every phase. Circuit breakers armed.\n\n### Tier 5: Feature Addition (Existing Codebase)\n- Trigger: existing project + feature description (\"add auth\", \"add a dashboard\", \"add dark mode\")\n- Detection: project has source files (src\u002F, app\u002F, lib\u002F, package.json with deps) AND description is a feature, not a standalone app\n- Action: \u002Fprd in feature mode → \u002Farchitect in existing codebase mode → \u002Farchon\n- Key differences from greenfield tiers:\n  - PRD reads existing codebase before asking questions\n  - Architecture describes changes to existing files, not a standalone system\n  - Phase 0 is always \"Baseline\" — record current typecheck\u002Ftest state\n  - Every phase end condition includes \"no new typecheck errors\" + \"existing tests pass\"\n  - Risk register always includes \"regression in existing functionality\"\n- Human checkpoints: after feature spec (PRD). Architecture can auto-approve if\n  the feature is well-scoped and all conditions are machine-verifiable.\n\n### Tier Classification\n\n| Input Pattern | Tier |\n|---|---|\n| \"blank project\", \"scaffold\", \"new empty\" | 1 |\n| \"help me build\", \"I want to create\", \"guide me\" | 2 |\n| \"todo app\", \"blog\", \"dashboard\", well-known app type | 3 |\n| \"build me [detailed]\", \"create [app]\", confident description | 4 |\n| \"add [feature]\", \"implement [feature]\", existing project + feature description | 5 |\n| Ambiguous | Default to Tier 2 (safest) |\n\n## Protocol\n\n### Step 1: CLASSIFY\n\nRead the user's input. Determine the tier. Announce what you'll do in plain language — not tier numbers. If the classification is wrong, accept user overrides (\"just scaffold it\" → Tier 1, \"just build it\" → Tier 4).\n\n### Step 2: EXECUTE TIER\n\n**Tier 1:** Invoke \u002Fscaffold. Done.\n\n**Tier 2:** \u002Fprd → user approves → \u002Farchitect → user approves → Archon campaign → brief user after each major phase.\n\n**Tier 3:** Check `.planning\u002F_templates\u002Fapp-types\u002F` for template → present PRD, ask for changes → \u002Farchitect with template defaults → Archon campaign.\n\n**Tier 4:**\n1. \u002Fprd express mode (0-1 questions)\n2. User approves PRD (only mandatory checkpoint)\n3. \u002Farchitect (auto-approve if all end conditions are machine-verifiable)\n4. Archon campaign with ALL safety systems active:\n   - Direction alignment every 2 phases, quality spot-check every phase\n   - Circuit breakers: 3 failures = new approach, 5+ type errors = park\n5. Execute autonomously until complete or parked\n6. Run full verification of all PRD end conditions, present results\n\n**Tier 5 (Feature Addition):**\n1. Read existing codebase — file tree, package.json, key entry points, existing patterns\n2. \u002Fprd in feature mode (max 2 questions)\n3. User approves feature spec (one mandatory checkpoint)\n4. \u002Farchitect in existing codebase mode — Phase 0 always \"Baseline\" (run typecheck + tests, record counts). Auto-approve if machine-verifiable.\n5. Archon campaign — every phase end condition includes \"no new typecheck errors vs baseline\" and \"existing tests pass\"\n6. On completion: verify all feature end conditions + baseline regression check, present results\n\n### Step 3: VERIFY (All Tiers except 1)\n\nCheck each PRD end condition (run commands, check files, invoke \u002Flive-preview for visual checks). Report PASS \u002F PARTIAL \u002F FAIL with specifics.\n\n### Step 4: DELIVER\n\nPresent: what was built, what was verified, what needs attention, how to run it, and suggested next step (e.g., \u002Fpostmortem or deploy command).\n\n## Quality Gates\n\n- PRD exists and is approved before any code is written\n- Architecture exists before Archon starts\n- Every campaign phase has machine-verifiable end conditions\n- Final verification checks all PRD end conditions\n- User receives a clear report of what was built and what needs attention\n\n## Fringe Cases\n\n**Vague requirements**: Default to Tier 2 and ask clarifying questions before producing the PRD.\n\n**Project already initialized**: Existing source files (src\u002F, app\u002F, package.json with deps) → automatically classify as Tier 5. Do not scaffold over an existing project.\n\n**If .planning\u002F does not exist**: \u002Fprd and \u002Farchitect will create it. If not possible, present inline and ask the user to run `\u002Fdo setup` first.\n\n**Tier misclassification**: Switch immediately on user correction without re-reading the input.\n\n## Exit Protocol\n\nAfter the campaign completes and verification runs, output:\n\n```\n---HANDOFF---\n- App: {name}\n- Built: {feature ledger summary}\n- Verified: {N}\u002F{total} end conditions passed\n- Status: {complete | partial | failed}\n- To run: {start command}\n- Next: {suggested next step, e.g., \u002Fpostmortem or deploy command}\n- Reversibility: amber -- multi-tier creation, revert the creation commits\n---\n```\n",{"name":5,"effort":24,"license":15,"description":7,"auto-trigger":20,"user-invocable":25,"trigger_keywords":26},"max",true,[27,28,29,30,31,32,33,34,35],"create app","build app","build me","make an app","new app","generate app","add auth","add payments","integrate","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","06-前端与设计\u002Fcreate-app",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":45,"prompt":55,"zipAvailable":25},[46,49,52],{"tool":47,"command":48},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill create-app",{"tool":50,"command":51},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill create-app",{"tool":53,"command":54},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill create-app","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fcreate-app\u002FSKILL.md",[57,63],{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"__benchmarks__\u002Fexisting-codebase.md","REFERENCE","参考文档",912,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fcreate-app\u002F__benchmarks__\u002Fexisting-codebase.md",{"path":64,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":65,"sourceHtmlUrl":66},"__benchmarks__\u002Fgreenfield-vague.md",864,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fcreate-app\u002F__benchmarks__\u002Fgreenfield-vague.md",[68,75,80,87,94,101],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":70,"nameZh":6,"description":71,"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":79,"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":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"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":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"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":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"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":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"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",[],[]]