[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71HCW2ADPT3WG1HHCV1XPAF":3,"skill-same:01M71HCW2ADPT3WG1HHCV1XPAF":95},{"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":28,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":56,"commitSha":57,"skillDirectory":58,"forksCount":59,"repositoryHtmlUrl":60,"repositoryHomepageUrl":6,"ownerHtmlUrl":61,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":62,"install":63,"resources":76},"01M71HCW2ADPT3WG1HHCV1XPAF","qa-scroll",null,"QA test skill for verifying scroll-based media feeds — video autoplay, scroll navigation, mute\u002Funmute, and playback progression. Uses the CDP + agent-device dual-driver architecture. Works with any React Native app using expo-video or similar video player libraries. Invoke when user says \"test scroll feed\", \"test video playback\", \"QA the feed\", \"verify video autoplay\", \"run scroll tests\", \"test media player\", or any task requiring scroll-based media feed verification.","runecraftai\u002Farcanum","runecraftai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F279098826?v=4","01M71HBGS1RCAJ490RAYST7M00","01M71HBGT1CB94MNS6T6SGAZKW",1,"MIT","https:\u002F\u002Fgithub.com\u002Frunecraftai\u002Farcanum\u002Fblob\u002Fmain\u002Fpackages\u002Ffamiliar\u002Fskills\u002Fqa-automation\u002Fqa-scroll\u002FSKILL.md",[17,22,25],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":26,"categoryName":27,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"qa","scroll","qa scroll","react native","verification","libraries","browser","react","Test Skill","architecture","Bash","when","invoke","player","agent-browser","Media","feeds","cdp","app","Video","2026-11-10 10:12:30",false,"---\nname: qa-scroll\ndescription: >\n  QA test skill for verifying scroll-based media feeds — video autoplay, scroll navigation,\n  mute\u002Funmute, and playback progression. Uses the CDP + agent-device dual-driver architecture.\n  Works with any React Native app using expo-video or similar video player libraries.\n  Invoke when user says \"test scroll feed\", \"test video playback\", \"QA the feed\",\n  \"verify video autoplay\", \"run scroll tests\", \"test media player\", or any task\n  requiring scroll-based media feed verification.\nallowed-tools: Bash(agent-device:*) Bash(agent-browser:*) Bash(xcrun:*) Bash(node:*) Bash(curl:*) Bash(npx:*) Read\n---\n\n# qa-scroll\n\nQA test skill for verifying scroll-based media feeds — **video autoplay**, **scroll navigation**, **mute\u002Funmute toggle**, and **playback progression**. Uses the dual-driver architecture (CDP + agent-device) to test media feeds in native mobile apps.\n\n## What It Tests\n\n| Test | Method | Assertion |\n|------|--------|-----------|\n| First video autoplays | CDP player state query | `player.playing === true`, `currentTime > 0` |\n| Video progress advances | CDP currentTime check after delay | `currentTime` increased between checks |\n| Scroll to next video | CDP scroll hook or agent-device swipe | New video starts playing |\n| Mute toggle | CDP `player.muted = !player.muted` | Mute state flips |\n| Unmute toggle | CDP `player.muted = !player.muted` | Mute state flips back |\n| Scroll continuity | Multiple swipes | Each new video autoplays |\n| Final route check | CDP `cdp_get_route` | Still on the feed screen |\n\n## Setup Guard (Automatic)\n\nThe skill includes a **setup guard** that runs before every test. It checks and auto-fixes:\n\n| Check | What it does if missing |\n|-------|------------------------|\n| iOS Simulator booted | Boots it or auto-detects a booted one |\n| Dev server running | Starts it in background, waits up to 60s |\n| App in foreground | Launches via `xcrun simctl launch` |\n| CDP target available | Polls `\u002Fjson` endpoint for up to 30s |\n| CDP connection functional | Sends `eval 1+1`, retries 3x |\n| Navigation module ID valid | Auto-scans Metro modules with caching |\n| Error overlay | Suppresses LogBox errors via CDP |\n\n## Configuration\n\nBefore running, set your app-specific values in `qa.config.sh` or `qa.config.local.sh`:\n\n```bash\n# Required\nexport APP_BUNDLE_ID=\"com.yourapp.dev\"\nexport PROJECT_DIR=\"\u002Fpath\u002Fto\u002Fyour\u002Fproject\"\n\n# Video player (for expo-video apps)\nexport VIDEO_PLAYER_CLASS=\"VideoPlayer\"     # Class to look for\nexport GLOBAL_PLAYERS_VAR=\"__qaVideoPlayers\" # Global tracking variable\n\n# Screen names (for CDP navigation)\nexport SCREEN_EXPLORE=\"ExploreScreen\"       # Your feed screen name\n\n# Optional: if your app has a feed scroll hook\nexport GLOBAL_FEED_VAR=\"__qaFeedState\"      # Feed state debug hook name\n```\n\n## Test Result States\n\n| Status | Meaning |\n|--------|---------|\n| **passed** | Assertion verified via CDP |\n| **failed** | Assertion verified but wrong |\n| **skipped** | CDP query inconclusive — cannot determine pass\u002Ffail |\n\n## Architecture\n\n```\nCDP (Hermes Runtime)              agent-device (Simulator)\n┌──────────────────────┐          ┌──────────────────────┐\n│ navigate to tab      │          │ swipe up (scroll)     │\n│ install debug hook   │          │ tap center (fallback) │\n│ query player state   │          │ screenshot capture    │\n│   .playing           │          │ appstate check        │\n│   .muted             │          │                       │\n│   .currentTime       │          │                       │\n│ toggle mute via CDP  │          │                       │\n│ dismiss error overlay│          │                       │\n└──────────────────────┘          └──────────────────────┘\n```\n\n### Why CDP, not agent-browser?\n\n`agent-browser` uses Playwright's CDP protocol which sends `Target.setDiscoverTargets` — a method Hermes doesn't support. Native apps don't have a DOM to interact with. Raw CDP via WebSocket to Hermes is the correct approach for JS runtime queries in React Native apps.\n\n### Why agent-device, not agent-browser?\n\n`agent-device` is purpose-built for iOS\u002FAndroid simulator control — screenshots, swipe gestures, accessibility snapshots. `agent-browser` is for web pages. Native apps render native views, not web views.\n\n## Usage\n\n### Run the example test\n```bash\nbash .pi\u002Fskills\u002Fqa-automation\u002Fqa-scroll\u002Frun.sh\n```\n\n### Run a specific flow\n```bash\nbash .pi\u002Fskills\u002Fqa-automation\u002Fqa-scroll\u002Fflows\u002Fexample-scroll-test.sh\n```\n\n### View results\n- Screenshots: `\u002Ftmp\u002Fqa-tests\u002Fscreenshots\u002F\u003Ctest-name>\u002F`\n- Report JSON: `\u002Ftmp\u002Fqa-tests\u002F\u003Ctest-name>-report.json`\n\n## Customizing for Your App\n\n### Step 1: Configure video player detection\n\nThe debug hook patches `VideoPlayer.prototype.play()` to track instances. If your app uses a different video player:\n\n```bash\n# In qa.config.sh:\nexport VIDEO_PLAYER_CLASS=\"MyVideoPlayer\"  # Your player class name\n```\n\nThe hook scans Metro modules looking for `module.default.VideoPlayer` or `module.VideoPlayer`. Adjust the scan in `scroll-helpers.sh` if your player is exported differently.\n\n### Step 2: Configure feed scrolling\n\nIf your app exposes a scroll-to-next function via a debug hook:\n\n```bash\n# In your app code (dev builds only):\nglobalThis.__qaFeedState = {\n    currentIndex: 0,\n    scrollToNext: () => { \u002F* scroll logic *\u002F },\n    scrollToIndex: (i) => { \u002F* scroll to index *\u002F },\n    getData: () => { \u002F* return feed data array *\u002F },\n    getItem: (i) => { \u002F* return item at index *\u002F }\n};\n```\n\nIf no hook is available, the skill falls back to `agent-device swipe` gestures.\n\n### Step 3: Create your test flow\n\nCopy `flows\u002Fexample-scroll-test.sh` and customize the steps for your app's feed structure.\n\n## File Structure\n\n```\nqa-scroll\u002F\n├── SKILL.md                          # This file\n├── lib\u002F\n│   ├── setup-guard.sh                # Prerequisites checker + auto-fixer\n│   └── scroll-helpers.sh             # Video state, mute control, feed interaction\n├── flows\u002F\n│   └── example-scroll-test.sh        # Example test (customize for your app)\n└── run.sh                            # Runner with JSON report output\n```\n\n## Troubleshooting\n\n### \"Setup guard failed\"\nCheck the specific `[SETUP]` line that shows `FAILED`. Common causes:\n- Simulator not installed or wrong UDID\n- Dev server port in use by another process\n- App not installed (build and install first)\n\n### \"No CDP target found\"\nThe app needs to be connected to the dev server. After a fresh install, launch the app and wait for the connection.\n\n### \"VideoPlayer class not found\"\nThe module scan didn't find your video player class. Check:\n- Is the video player library installed? (`expo-video`, `react-native-video`, etc.)\n- Does the class name match `VIDEO_PLAYER_CLASS` in config?\n- Try widening the scan range: `export MODULE_SCAN_END=10000`\n\n### Tests show \"skipped\"\nCDP couldn't read player state. The debug hook may not have captured any players yet. Common causes:\n- No video content loaded (API returned empty feed)\n- Players created before hook was installed (hook captures on `play()` call)\n- Video library doesn't use the expected class structure\n\n### Error overlay appears\nThe setup guard suppresses LogBox, but errors during CDP eval may trigger new overlays. The test automatically checks for and dismisses overlays before screenshots.\n","# qa-scroll\n\nQA test skill for verifying scroll-based media feeds — **video autoplay**, **scroll navigation**, **mute\u002Funmute toggle**, and **playback progression**. Uses the dual-driver architecture (CDP + agent-device) to test media feeds in native mobile apps.\n\n## What It Tests\n\n| Test | Method | Assertion |\n|------|--------|-----------|\n| First video autoplays | CDP player state query | `player.playing === true`, `currentTime > 0` |\n| Video progress advances | CDP currentTime check after delay | `currentTime` increased between checks |\n| Scroll to next video | CDP scroll hook or agent-device swipe | New video starts playing |\n| Mute toggle | CDP `player.muted = !player.muted` | Mute state flips |\n| Unmute toggle | CDP `player.muted = !player.muted` | Mute state flips back |\n| Scroll continuity | Multiple swipes | Each new video autoplays |\n| Final route check | CDP `cdp_get_route` | Still on the feed screen |\n\n## Setup Guard (Automatic)\n\nThe skill includes a **setup guard** that runs before every test. It checks and auto-fixes:\n\n| Check | What it does if missing |\n|-------|------------------------|\n| iOS Simulator booted | Boots it or auto-detects a booted one |\n| Dev server running | Starts it in background, waits up to 60s |\n| App in foreground | Launches via `xcrun simctl launch` |\n| CDP target available | Polls `\u002Fjson` endpoint for up to 30s |\n| CDP connection functional | Sends `eval 1+1`, retries 3x |\n| Navigation module ID valid | Auto-scans Metro modules with caching |\n| Error overlay | Suppresses LogBox errors via CDP |\n\n## Configuration\n\nBefore running, set your app-specific values in `qa.config.sh` or `qa.config.local.sh`:\n\n```bash\n# Required\nexport APP_BUNDLE_ID=\"com.yourapp.dev\"\nexport PROJECT_DIR=\"\u002Fpath\u002Fto\u002Fyour\u002Fproject\"\n\n# Video player (for expo-video apps)\nexport VIDEO_PLAYER_CLASS=\"VideoPlayer\"     # Class to look for\nexport GLOBAL_PLAYERS_VAR=\"__qaVideoPlayers\" # Global tracking variable\n\n# Screen names (for CDP navigation)\nexport SCREEN_EXPLORE=\"ExploreScreen\"       # Your feed screen name\n\n# Optional: if your app has a feed scroll hook\nexport GLOBAL_FEED_VAR=\"__qaFeedState\"      # Feed state debug hook name\n```\n\n## Test Result States\n\n| Status | Meaning |\n|--------|---------|\n| **passed** | Assertion verified via CDP |\n| **failed** | Assertion verified but wrong |\n| **skipped** | CDP query inconclusive — cannot determine pass\u002Ffail |\n\n## Architecture\n\n```\nCDP (Hermes Runtime)              agent-device (Simulator)\n┌──────────────────────┐          ┌──────────────────────┐\n│ navigate to tab      │          │ swipe up (scroll)     │\n│ install debug hook   │          │ tap center (fallback) │\n│ query player state   │          │ screenshot capture    │\n│   .playing           │          │ appstate check        │\n│   .muted             │          │                       │\n│   .currentTime       │          │                       │\n│ toggle mute via CDP  │          │                       │\n│ dismiss error overlay│          │                       │\n└──────────────────────┘          └──────────────────────┘\n```\n\n### Why CDP, not agent-browser?\n\n`agent-browser` uses Playwright's CDP protocol which sends `Target.setDiscoverTargets` — a method Hermes doesn't support. Native apps don't have a DOM to interact with. Raw CDP via WebSocket to Hermes is the correct approach for JS runtime queries in React Native apps.\n\n### Why agent-device, not agent-browser?\n\n`agent-device` is purpose-built for iOS\u002FAndroid simulator control — screenshots, swipe gestures, accessibility snapshots. `agent-browser` is for web pages. Native apps render native views, not web views.\n\n## Usage\n\n### Run the example test\n```bash\nbash .pi\u002Fskills\u002Fqa-automation\u002Fqa-scroll\u002Frun.sh\n```\n\n### Run a specific flow\n```bash\nbash .pi\u002Fskills\u002Fqa-automation\u002Fqa-scroll\u002Fflows\u002Fexample-scroll-test.sh\n```\n\n### View results\n- Screenshots: `\u002Ftmp\u002Fqa-tests\u002Fscreenshots\u002F\u003Ctest-name>\u002F`\n- Report JSON: `\u002Ftmp\u002Fqa-tests\u002F\u003Ctest-name>-report.json`\n\n## Customizing for Your App\n\n### Step 1: Configure video player detection\n\nThe debug hook patches `VideoPlayer.prototype.play()` to track instances. If your app uses a different video player:\n\n```bash\n# In qa.config.sh:\nexport VIDEO_PLAYER_CLASS=\"MyVideoPlayer\"  # Your player class name\n```\n\nThe hook scans Metro modules looking for `module.default.VideoPlayer` or `module.VideoPlayer`. Adjust the scan in `scroll-helpers.sh` if your player is exported differently.\n\n### Step 2: Configure feed scrolling\n\nIf your app exposes a scroll-to-next function via a debug hook:\n\n```bash\n# In your app code (dev builds only):\nglobalThis.__qaFeedState = {\n    currentIndex: 0,\n    scrollToNext: () => { \u002F* scroll logic *\u002F },\n    scrollToIndex: (i) => { \u002F* scroll to index *\u002F },\n    getData: () => { \u002F* return feed data array *\u002F },\n    getItem: (i) => { \u002F* return item at index *\u002F }\n};\n```\n\nIf no hook is available, the skill falls back to `agent-device swipe` gestures.\n\n### Step 3: Create your test flow\n\nCopy `flows\u002Fexample-scroll-test.sh` and customize the steps for your app's feed structure.\n\n## File Structure\n\n```\nqa-scroll\u002F\n├── SKILL.md                          # This file\n├── lib\u002F\n│   ├── setup-guard.sh                # Prerequisites checker + auto-fixer\n│   └── scroll-helpers.sh             # Video state, mute control, feed interaction\n├── flows\u002F\n│   └── example-scroll-test.sh        # Example test (customize for your app)\n└── run.sh                            # Runner with JSON report output\n```\n\n## Troubleshooting\n\n### \"Setup guard failed\"\nCheck the specific `[SETUP]` line that shows `FAILED`. Common causes:\n- Simulator not installed or wrong UDID\n- Dev server port in use by another process\n- App not installed (build and install first)\n\n### \"No CDP target found\"\nThe app needs to be connected to the dev server. After a fresh install, launch the app and wait for the connection.\n\n### \"VideoPlayer class not found\"\nThe module scan didn't find your video player class. Check:\n- Is the video player library installed? (`expo-video`, `react-native-video`, etc.)\n- Does the class name match `VIDEO_PLAYER_CLASS` in config?\n- Try widening the scan range: `export MODULE_SCAN_END=10000`\n\n### Tests show \"skipped\"\nCDP couldn't read player state. The debug hook may not have captured any players yet. Common causes:\n- No video content loaded (API returned empty feed)\n- Players created before hook was installed (hook captures on `play()` call)\n- Video library doesn't use the expected class structure\n\n### Error overlay appears\nThe setup guard suppresses LogBox, but errors during CDP eval may trigger new overlays. The test automatically checks for and dismisses overlays before screenshots.\n",{"name":5,"description":54,"allowed-tools":55},"QA test skill for verifying scroll-based media feeds — video autoplay, scroll navigation, mute\u002Funmute, and playback progression. Uses the CDP + agent-device dual-driver architecture. Works with any React Native app using expo-video or similar video player libraries. Invoke when user says \"test scroll feed\", \"test video playback\", \"QA the feed\", \"verify video autoplay\", \"run scroll tests\", \"test media player\", or any task requiring scroll-based media feed verification.\n","Bash(agent-device:*) Bash(agent-browser:*) Bash(xcrun:*) Bash(node:*) Bash(curl:*) Bash(npx:*) Read","main","33b040feb49e126600394272a8e321a3cd279e8b","packages\u002Ffamiliar\u002Fskills\u002Fqa-automation\u002Fqa-scroll",0,"https:\u002F\u002Fgithub.com\u002Frunecraftai\u002Farcanum","https:\u002F\u002Fgithub.com\u002Frunecraftai","2026-07-29 22:08:52",{"source":8,"skillName":5,"commands":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add runecraftai\u002Farcanum --skill qa-scroll",{"tool":69,"command":70},"bunx","bunx skills add runecraftai\u002Farcanum --skill qa-scroll",{"tool":72,"command":73},"pnpm","pnpm dlx skills add runecraftai\u002Farcanum --skill qa-scroll","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frunecraftai\u002Farcanum\u002Fblob\u002Fmain\u002Fpackages\u002Ffamiliar\u002Fskills\u002Fqa-automation\u002Fqa-scroll\u002FSKILL.md",true,[77,83,87,91],{"path":78,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":81,"sourceHtmlUrl":82},"flows\u002Fexample-scroll-test.sh","SCRIPT","脚本",12333,"https:\u002F\u002Fgithub.com\u002Frunecraftai\u002Farcanum\u002Fblob\u002Fmain\u002Fpackages\u002Ffamiliar\u002Fskills\u002Fqa-automation\u002Fqa-scroll\u002Fflows\u002Fexample-scroll-test.sh",{"path":84,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":85,"sourceHtmlUrl":86},"lib\u002Fscroll-helpers.sh",16828,"https:\u002F\u002Fgithub.com\u002Frunecraftai\u002Farcanum\u002Fblob\u002Fmain\u002Fpackages\u002Ffamiliar\u002Fskills\u002Fqa-automation\u002Fqa-scroll\u002Flib\u002Fscroll-helpers.sh",{"path":88,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":89,"sourceHtmlUrl":90},"lib\u002Fsetup-guard.sh",16751,"https:\u002F\u002Fgithub.com\u002Frunecraftai\u002Farcanum\u002Fblob\u002Fmain\u002Fpackages\u002Ffamiliar\u002Fskills\u002Fqa-automation\u002Fqa-scroll\u002Flib\u002Fsetup-guard.sh",{"path":92,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":93,"sourceHtmlUrl":94},"run.sh",1934,"https:\u002F\u002Fgithub.com\u002Frunecraftai\u002Farcanum\u002Fblob\u002Fmain\u002Fpackages\u002Ffamiliar\u002Fskills\u002Fqa-automation\u002Fqa-scroll\u002Frun.sh",[96,124,149,173,193,217],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":100,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":104,"publishedAt":49},"01M71HGTN9FRQ3WEZMVVX7C3VZ","using-agent-skills","Discovers and invokes the right @runecraft\u002Fspells skill for the current task. Use when starting a session, when a request is ambiguous about which workflow to apply, or when you need to pick among the 13-skill Arcanum catalog. EN triggers: \u002Fskill, which skill, pick a skill, what skill should I use, skill discovery, meta skill. PT triggers: qual skill, qual habilidade, descobrir skill, qual fluxo usar. Do NOT use for: actual implementation work (route to the specific skill instead), unrelated standalone tasks outside the Arcanum catalog, or runtime-specific configuration (e.g., opencode.json \u002F Claude Code plugin paths).","CC-BY-4.0","https:\u002F\u002Fgithub.com\u002Frunecraftai\u002Farcanum\u002Fblob\u002Fmain\u002Fpackages\u002Fspells\u002Fskills\u002Fusing-agent-skills\u002FSKILL.md",[103],{"categoryNo":26,"categoryName":27,"taxonomyType":20,"taxonomyTypeDesc":21},[105,106,107,108,109,110,40,111,112,113,114,115,116,117,118,119,120,121,122,123],"using agent skills","standalone","which","pt","pick","Meta","workflow","you","code","tasks","skill discovery","route","work","unrelated","opencode","request","paths","a skill","ambiguous",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":100,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":49},"01M71HGPD6N9JH2G8EVBXJR77X","typescript-patterns","TypeScript best practices and patterns for type-safe, maintainable code. Covers discriminated unions, generics, const assertions, type narrowing, and common anti-patterns. Extends (does not override) project tsconfig. EN triggers: \u002Ftypescript, TypeScript patterns, TS best practices, type safety, discriminated unions, generics, type narrowing. PT triggers: \u002Ftypescript, padrões TypeScript, boas práticas TS, segurança de tipos, unions discriminadas, genéricos. Do NOT use for: JavaScript-only projects, runtime performance, or replacing project tsconfig rules.","https:\u002F\u002Fgithub.com\u002Frunecraftai\u002Farcanum\u002Fblob\u002Fmain\u002Fpackages\u002Fspells\u002Fskills\u002Ftypescript-patterns\u002FSKILL.md",[],[131,132,133,134,135,136,108,137,138,139,140,141,142,143,144,145,146,147,113,148],"typescript","patterns","typescript patterns","do","projects","for","runtime","project","performance","en","maintainable code","triggers","only","use","assertions","Rules","best practices","common",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":100,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":159,"publishedAt":49},"01M71HGJAKX4TFN0PECYPJ9S38","test-driven-development","Drives development with tests — fail first, then make them pass, then refactor. Use when implementing any logic, fixing any bug, or changing any behavior. EN triggers: \u002Ftest, write tests first, TDD, prove it, 80\u002F15\u002F5 pyramid, Beyonce Rule. PT triggers: \u002Fteste, testes primeiro, provar com teste, pirâmide 80\u002F15\u002F5. Do NOT use for: production incident triage (use \u002Fdebug), or cosmetic-only changes with no behavioral surface.","https:\u002F\u002Fgithub.com\u002Frunecraftai\u002Farcanum\u002Fblob\u002Fmain\u002Fpackages\u002Fspells\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[155,158],{"categoryNo":156,"categoryName":157,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[160,161,162,163,108,164,165,166,143,40,167,168,169,170,171,134,136,140,142,172],"test driven development","development","test","driven","incident","implementing","write tests","write","bug","refactor","behavioral","make","tests",{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":100,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":179,"publishedAt":49},"01M71HGC1H4JQFJWH613XTJC59","spec-driven","Feature planning and implementation with 4 adaptive phases — Specify, Design, Tasks, Execute. Auto-sizes depth by complexity. Creates atomic tasks with verification criteria, atomic git commits, and requirement traceability. Features an independent Verifier (author != verifier, evidence-or-zero), persistent decision log (STATE.md), and test-coverage-matrix-driven tests, plus a self-improving lessons layer that turns verification failures into reusable project-local guidance. Stack-agnostic. Use when planning features (requirements, design, task breakdown), implementing with verification and atomic commits, or validating\u002Fverifying an implementation against a spec. Triggers (PT\u002FEN): \"specify feature\", \"vamos especificar\", \"discutir feature\", \"discutir este caso\", \"design\", \"design da feature\", \"tarefas\", \"quebrar em tarefas\", \"implementar\", \"build\", \"validar\", \"verify work\", \"UAT\", \"validar implementação\", \"record decision\", \"pause work\", \"pausar trabalho\", \"resume work\", \"retomar trabalho\". Do NOT use for architecture decomposition analysis (use architecture skills) or technical design docs (treat as Complex scope: discuss gray areas + architecture-focused design).","https:\u002F\u002Fgithub.com\u002Frunecraftai\u002Farcanum\u002Fblob\u002Fmain\u002Fpackages\u002Fspells\u002Fskills\u002Fspec-driven\u002FSKILL.md",[],[180,181,163,182,183,184,185,108,138,186,165,187,188,189,190,191,40,192,114,38],"spec driven","spec","coverage","complexity","task breakdown","scope","decision","local","design","self-improving","auto","atomic commits","analysis",{"skillNo":194,"name":195,"nameZh":6,"description":196,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":100,"licenseFileUrl":6,"sourceHtmlUrl":197,"categories":198,"keywords":203,"publishedAt":49},"01M71HG5CSP04F29HRAG7XVYKG","skill-forge","Designs, authors, validates, and optimizes new Agent Skills from scratch. Use when creating a new skill, packaging a workflow as a skill, improving a skill's triggering accuracy, or evaluating whether a skill improves output quality. Covers the full lifecycle: DISCOVER, DESIGN, AUTHOR, VALIDATE, OPTIMIZE, DELIVER. Produces skills that follow the open SKILL.md format (YAML frontmatter + Markdown body, progressive disclosure, validation loops). EN triggers: \u002Fforge, create a skill, write a skill, build a skill, new skill, author a skill, package this as a skill, validate a skill, improve skill triggering, optimize skill description, evaluate skill quality. PT triggers: \u002Fforge, criar uma skill, escrever uma skill, construir uma skill, nova skill, empacotar como skill, validar skill, melhorar disparo, otimizar descrição de skill. Do NOT use for: discovering which existing skill to apply (use a dispatch\u002Fmeta skill), planning feature implementation, or designing software architecture.","https:\u002F\u002Fgithub.com\u002Frunecraftai\u002Farcanum\u002Fblob\u002Fmain\u002Fpackages\u002Fspells\u002Fskills\u002Fskill-forge\u002FSKILL.md",[199,202],{"categoryNo":200,"categoryName":201,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":26,"categoryName":27,"taxonomyType":20,"taxonomyTypeDesc":21},[204,205,206,107,207,208,108,209,110,210,211,188,38,212,213,167,214,122,215,216],"forge","skill forge","deliver","new agent","feature implementation","packaging","improve","open","create","de","software","new skill","full",{"skillNo":218,"name":219,"nameZh":6,"description":220,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":100,"licenseFileUrl":6,"sourceHtmlUrl":221,"categories":222,"keywords":223,"publishedAt":49},"01M71HG1RAQY3GXX0Q5TMW0XD6","shipping-and-launch","Prepares production launches with a pre-launch checklist, staged rollout, monitoring, and a rollback strategy — plus feature flag lifecycle (off → internal → beta → GA). Use when deploying a feature to production for the first time, releasing a significant change, or planning a rollout. EN triggers: \u002Fship, pre-launch checklist, staged rollout, feature flag, rollback plan, monitoring. PT triggers: \u002Fshippar, checklist pré-lançamento, rollout gradual, feature flag, plano de rollback. Do NOT use for: pre-production development work, or one-off internal tools with no user exposure.","https:\u002F\u002Fgithub.com\u002Frunecraftai\u002Farcanum\u002Fblob\u002Fmain\u002Fpackages\u002Fspells\u002Fskills\u002Fshipping-and-launch\u002FSKILL.md",[],[224,225,226,108,227,228,40,229,230,231,232,117,233,234,235,236,213,237,238,239],"shipping and launch","shipping","launch","time","beta","rollout","rollback plan","monitoring","rollback strategy","plan","change","exposure","plano","ship","Tools","pre-launch"]