[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71HAHWVV4HZNGE8JS3XC35M":3,"skill-same:01M71HAHWVV4HZNGE8JS3XC35M":103},{"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":58,"commitSha":59,"skillDirectory":60,"forksCount":61,"repositoryHtmlUrl":62,"repositoryHomepageUrl":6,"ownerHtmlUrl":63,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":64,"install":65,"resources":78},"01M71HAHWVV4HZNGE8JS3XC35M","image-generation",null,"Generate images with Gemini (default) or fal.ai FLUX.2 klein 4B (--cheap for fast\u002Flow-cost). Generate videos with Grok Imagine (default) or fal.ai LTX-2 (--cheap). Use for: create image, generate visual, AI image generation, poster, video generation.","JSGforever\u002Fskillguard","JSGforever","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F85541948?v=4","01M71FQD3E132VMR5F4TAYX3YS","01M71FQD4DYW0XJ4XQ4YQH75Y9",2,"GPL-3.0","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__aviz85--image-generation\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"Image Generation","generation","image","images","for","imagine","grok imagine","create image","with","poster","visual","default","cost","use","video generation","fal","Video","generate","create","gemini","2026-11-10 10:12:30",false,"---\nname: image-generation\ndescription: \"Generate images with Gemini (default) or fal.ai FLUX.2 klein 4B (--cheap for fast\u002Flow-cost). Generate videos with Grok Imagine (default) or fal.ai LTX-2 (--cheap). Use for: create image, generate visual, AI image generation, poster, video generation.\"\nversion: \"1.0.0\"\nauthor: aviz85\ntags: [image, video, AI, generation, Gemini, fal.ai, poster]\n---\n\n# Image Generation\n\nGenerate images using Google's Gemini model (default) or fal.ai FLUX.2 klein 4B (cheap mode).\n\n## Quick Start\n\n**MANDATORY:** Always use `-d` (destination) flag to specify output path. This avoids file management issues with `poster_0.jpg` in the scripts folder.\n\n```bash\ncd ~\u002F.claude\u002Fskills\u002Fimage-generation\u002Fscripts\n\n# ALWAYS specify destination with -d flag\nnpx tsx generate_poster.ts -d \u002Ftmp\u002Fmy-image.jpg \"A futuristic city at sunset\"\n\n# Cheap mode: fal.ai FLUX.2 klein 4B (fast, lower cost)\nnpx tsx generate_poster.ts --cheap -d \u002Ftmp\u002Fcity.jpg \"A futuristic city at sunset\"\n\n# With aspect ratio\nnpx tsx generate_poster.ts -d \u002Ftmp\u002Flandscape.jpg --aspect 3:2 \"A wide landscape poster\"\nnpx tsx generate_poster.ts --cheap -d \u002Ftmp\u002Fstory.jpg -a 9:16 \"A vertical story format\"\n\n# With reference assets (image editing)\nnpx tsx generate_poster.ts -d \u002Ftmp\u002Fbanner.jpg --assets \"\u002Fpath\u002Fto\u002Favatar.jpg\" \"Create banner with character\"\nnpx tsx generate_poster.ts --cheap -d \u002Ftmp\u002Fphoto.jpg --assets \"\u002Fpath\u002Fto\u002Fimage.jpg\" \"Turn this into a realistic photo\"\n```\n\n**Why `-d` is mandatory:**\n- Output goes to predictable location (e.g., `\u002Ftmp\u002F` for temp images)\n- Avoids hunting for `poster_0.jpg` in scripts folder\n- Enables immediate use without file renaming\n\n## Providers\n\n| Provider | Flag | Use Case | Cost |\n|----------|------|----------|------|\n| **Gemini** | (default) | High quality, best results | Higher |\n| **fal.ai klein 4B** | `--cheap` | Fast, budget-friendly | ~$0.003\u002Fimage |\n\n### Cheap Mode (`--cheap`)\n\nUses fal.ai FLUX.2 klein 4B - a distilled FLUX model optimized for speed and cost.\n\n**Why use cheap mode?**\n- **Cost**: ~$0.003 per image (vs Gemini's higher cost)\n- **Speed**: Fast 4-step inference (~2-4 seconds)\n- **Quality**: Good enough for drafts, social media, iterations\n- **Batch friendly**: Generate many variations quickly\n\n**Endpoints:**\n- **Text-to-image**: `fal-ai\u002Fflux-2\u002Fklein\u002F4b`\n- **Image editing** (with --assets): `fal-ai\u002Fflux-2\u002Fklein\u002F4b\u002Fedit`\n\n**Best for:**\n- Quick iterations and previews\n- Social media content\n- Concept exploration\n- Batch generation (10+ images)\n\n**Use Gemini instead for:**\n- Final production assets\n- Complex compositions\n- Text-heavy images (especially Hebrew)\n\n## Quality\n\nControl image resolution with `--quality` or `-q`:\n\n| Quality | Resolution | Use Case |\n|---------|------------|----------|\n| `1K` | 1024px | **Default** - fast, good for web |\n| `2K` | 2048px | High quality - print, detailed posters |\n\n```bash\nnpx tsx generate_poster.ts -q 2K \"High quality poster\"\n```\n\n## Aspect Ratio\n\n**IMPORTANT:** Always use the default 3:2 aspect ratio unless the user explicitly requests a different format (like \"vertical\", \"story\", \"square\", etc.). Do NOT change the aspect ratio on your own.\n\nControl image dimensions with `--aspect` or `-a`:\n\n| Ratio | Use Case |\n|-------|----------|\n| `3:2` | Horizontal **(DEFAULT - use this unless user specifies otherwise)** |\n| `1:1` | Square - Instagram, profile pics |\n| `2:3` | Vertical - Pinterest, posters |\n| `16:9` | Wide - YouTube thumbnails, headers |\n| `9:16` | Tall - Stories, reels, TikTok |\n\n```bash\nnpx tsx generate_poster.ts --aspect 3:2 \"Your prompt\"\nnpx tsx generate_poster.ts -a 16:9 \"Your prompt\"\n```\n\n## Adding Assets (Reference Images)\n\nUse `--assets` with full paths to include reference images:\n\n```bash\n# Single asset\nnpx tsx generate_poster.ts --assets \"\u002Ffull\u002Fpath\u002Fto\u002Fimage.jpg\" \"Your prompt\"\n\n# Multiple assets (comma-separated)\nnpx tsx generate_poster.ts --assets \"\u002Fpath\u002Fa.jpg,\u002Fpath\u002Fb.png\" \"Use both images\"\n\n# With cheap mode - uses fal.ai edit endpoint\nnpx tsx generate_poster.ts --cheap --assets \"\u002Fpath\u002Fto\u002Fimage.jpg\" \"Turn this into a painting\"\n```\n\n**Supported formats:** `.jpg`, `.jpeg`, `.png`, `.webp`, `.gif`\n\n**IMPORTANT:** Assets are NOT automatically included. You must explicitly pass them via `--assets`.\n\n## Destination (MANDATORY)\n\n**ALWAYS** use `--destination` or `-d` to specify output path:\n\n```bash\n# REQUIRED: Always specify destination\nnpx tsx generate_poster.ts -d \u002Ftmp\u002Fposter.jpg \"My poster\"\n\n# If file exists, auto-adds suffix: poster_1.jpg, poster_2.jpg, etc.\n```\n\n**Features:**\n- Auto-creates parent directories if needed\n- Collision avoidance: if file exists, adds `_1`, `_2`, etc.\n- Use `\u002Ftmp\u002F` for temporary images that will be uploaded elsewhere\n\n## API Configuration\n\nCreate `scripts\u002F.env`:\n```\nGEMINI_API_KEY=your_gemini_api_key\nFAL_KEY=your_fal_api_key\nXAI_API_KEY=your_xai_api_key\n```\n\n## Hebrew\u002FRTL Content\n\n**IMPORTANT:** When the image contains Hebrew text, you MUST add the following sentence to the prompt:\n\n```\n\"CRITICAL: Layout is RTL (right-to-left). All text in Hebrew. Visual flow, reading order, and panel sequence go from RIGHT to LEFT.\"\n```\n\nCopy this exact sentence and paste it at the BEGINNING of your prompt. Without it, the image will render left-to-right which is wrong for Hebrew content.\n\n## WOW Mode\n\nWhen user asks for \"wow mode\" or wants maximum visual impact, add these epic elements to the prompt:\n\n```\n\"EPIC CINEMATIC WOW: Amazed expression, mind-blown reaction, intense VFX - shattered glass particles, explosive energy bursts, volumetric light rays, dramatic lens flares, particle explosions, motion blur streaks, holographic glitches, electric sparks, cinematic color grading, dramatic rim lighting, depth of field bokeh, anamorphic lens effects. Maximum visual spectacle.\"\n```\n\n## Output\n\n- Files saved to path specified by `-d` flag (MANDATORY)\n- Aspect ratio: Configurable via `--aspect` (default: 3:2)\n- Quality: 1K (1024px on longest edge)\n\n---\n\n# Video Generation\n\nGenerate videos using xAI Grok Imagine Video (default) or fal.ai LTX-2 (cheap mode).\n\n## Quick Start\n\n```bash\ncd ~\u002F.claude\u002Fskills\u002Fimage-generation\u002Fscripts\n\n# Text-to-video (Grok Imagine - high quality, 720p)\nnpx tsx generate_video.ts -d \u002Ftmp\u002Fvideo.mp4 \"A futuristic city at sunset, cinematic drone shot\"\n\n# Cheap mode: fal.ai LTX-2 (fast, low cost)\nnpx tsx generate_video.ts --cheap -d \u002Ftmp\u002Fvideo.mp4 \"A futuristic city at sunset\"\n\n# Image-to-video (animate a still image)\nnpx tsx generate_video.ts -d \u002Ftmp\u002Fanimated.mp4 --image \u002Fpath\u002Fto\u002Fimage.jpg \"Slow zoom with particles floating\"\nnpx tsx generate_video.ts --cheap -d \u002Ftmp\u002Fanimated.mp4 --image \u002Fpath\u002Fto\u002Fimage.jpg \"Gentle camera movement\"\n\n# Custom duration and aspect ratio\nnpx tsx generate_video.ts -d \u002Ftmp\u002Flong.mp4 -t 10 -a 9:16 \"Vertical video for stories\"\n```\n\n## Video Providers\n\n| Provider | Flag | Quality | Duration | Resolution | Cost |\n|----------|------|---------|----------|------------|------|\n| **Grok Imagine** | (default) | High, cinematic | 1-15s | 480p\u002F720p | Per-second billing |\n| **fal.ai LTX-2** | `--cheap` | Good, fast | 1-10s | ~480p | Budget-friendly |\n\n## Video Options\n\n| Option | Flag | Default | Description |\n|--------|------|---------|-------------|\n| Prompt | (positional) | required | Text description of the video |\n| Destination | `-d` | required | Output file path (.mp4) |\n| Duration | `-t` | 5 | Duration in seconds |\n| Aspect ratio | `-a` | 16:9 | 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3 |\n| Resolution | `-r` | 720p | 480p or 720p (Grok only) |\n| Image source | `--image` | none | Source image for image-to-video |\n| Cheap mode | `--cheap` | false | Use LTX-2 instead of Grok |\n","# Image Generation\n\nGenerate images using Google's Gemini model (default) or fal.ai FLUX.2 klein 4B (cheap mode).\n\n## Quick Start\n\n**MANDATORY:** Always use `-d` (destination) flag to specify output path. This avoids file management issues with `poster_0.jpg` in the scripts folder.\n\n```bash\ncd ~\u002F.claude\u002Fskills\u002Fimage-generation\u002Fscripts\n\n# ALWAYS specify destination with -d flag\nnpx tsx generate_poster.ts -d \u002Ftmp\u002Fmy-image.jpg \"A futuristic city at sunset\"\n\n# Cheap mode: fal.ai FLUX.2 klein 4B (fast, lower cost)\nnpx tsx generate_poster.ts --cheap -d \u002Ftmp\u002Fcity.jpg \"A futuristic city at sunset\"\n\n# With aspect ratio\nnpx tsx generate_poster.ts -d \u002Ftmp\u002Flandscape.jpg --aspect 3:2 \"A wide landscape poster\"\nnpx tsx generate_poster.ts --cheap -d \u002Ftmp\u002Fstory.jpg -a 9:16 \"A vertical story format\"\n\n# With reference assets (image editing)\nnpx tsx generate_poster.ts -d \u002Ftmp\u002Fbanner.jpg --assets \"\u002Fpath\u002Fto\u002Favatar.jpg\" \"Create banner with character\"\nnpx tsx generate_poster.ts --cheap -d \u002Ftmp\u002Fphoto.jpg --assets \"\u002Fpath\u002Fto\u002Fimage.jpg\" \"Turn this into a realistic photo\"\n```\n\n**Why `-d` is mandatory:**\n- Output goes to predictable location (e.g., `\u002Ftmp\u002F` for temp images)\n- Avoids hunting for `poster_0.jpg` in scripts folder\n- Enables immediate use without file renaming\n\n## Providers\n\n| Provider | Flag | Use Case | Cost |\n|----------|------|----------|------|\n| **Gemini** | (default) | High quality, best results | Higher |\n| **fal.ai klein 4B** | `--cheap` | Fast, budget-friendly | ~$0.003\u002Fimage |\n\n### Cheap Mode (`--cheap`)\n\nUses fal.ai FLUX.2 klein 4B - a distilled FLUX model optimized for speed and cost.\n\n**Why use cheap mode?**\n- **Cost**: ~$0.003 per image (vs Gemini's higher cost)\n- **Speed**: Fast 4-step inference (~2-4 seconds)\n- **Quality**: Good enough for drafts, social media, iterations\n- **Batch friendly**: Generate many variations quickly\n\n**Endpoints:**\n- **Text-to-image**: `fal-ai\u002Fflux-2\u002Fklein\u002F4b`\n- **Image editing** (with --assets): `fal-ai\u002Fflux-2\u002Fklein\u002F4b\u002Fedit`\n\n**Best for:**\n- Quick iterations and previews\n- Social media content\n- Concept exploration\n- Batch generation (10+ images)\n\n**Use Gemini instead for:**\n- Final production assets\n- Complex compositions\n- Text-heavy images (especially Hebrew)\n\n## Quality\n\nControl image resolution with `--quality` or `-q`:\n\n| Quality | Resolution | Use Case |\n|---------|------------|----------|\n| `1K` | 1024px | **Default** - fast, good for web |\n| `2K` | 2048px | High quality - print, detailed posters |\n\n```bash\nnpx tsx generate_poster.ts -q 2K \"High quality poster\"\n```\n\n## Aspect Ratio\n\n**IMPORTANT:** Always use the default 3:2 aspect ratio unless the user explicitly requests a different format (like \"vertical\", \"story\", \"square\", etc.). Do NOT change the aspect ratio on your own.\n\nControl image dimensions with `--aspect` or `-a`:\n\n| Ratio | Use Case |\n|-------|----------|\n| `3:2` | Horizontal **(DEFAULT - use this unless user specifies otherwise)** |\n| `1:1` | Square - Instagram, profile pics |\n| `2:3` | Vertical - Pinterest, posters |\n| `16:9` | Wide - YouTube thumbnails, headers |\n| `9:16` | Tall - Stories, reels, TikTok |\n\n```bash\nnpx tsx generate_poster.ts --aspect 3:2 \"Your prompt\"\nnpx tsx generate_poster.ts -a 16:9 \"Your prompt\"\n```\n\n## Adding Assets (Reference Images)\n\nUse `--assets` with full paths to include reference images:\n\n```bash\n# Single asset\nnpx tsx generate_poster.ts --assets \"\u002Ffull\u002Fpath\u002Fto\u002Fimage.jpg\" \"Your prompt\"\n\n# Multiple assets (comma-separated)\nnpx tsx generate_poster.ts --assets \"\u002Fpath\u002Fa.jpg,\u002Fpath\u002Fb.png\" \"Use both images\"\n\n# With cheap mode - uses fal.ai edit endpoint\nnpx tsx generate_poster.ts --cheap --assets \"\u002Fpath\u002Fto\u002Fimage.jpg\" \"Turn this into a painting\"\n```\n\n**Supported formats:** `.jpg`, `.jpeg`, `.png`, `.webp`, `.gif`\n\n**IMPORTANT:** Assets are NOT automatically included. You must explicitly pass them via `--assets`.\n\n## Destination (MANDATORY)\n\n**ALWAYS** use `--destination` or `-d` to specify output path:\n\n```bash\n# REQUIRED: Always specify destination\nnpx tsx generate_poster.ts -d \u002Ftmp\u002Fposter.jpg \"My poster\"\n\n# If file exists, auto-adds suffix: poster_1.jpg, poster_2.jpg, etc.\n```\n\n**Features:**\n- Auto-creates parent directories if needed\n- Collision avoidance: if file exists, adds `_1`, `_2`, etc.\n- Use `\u002Ftmp\u002F` for temporary images that will be uploaded elsewhere\n\n## API Configuration\n\nCreate `scripts\u002F.env`:\n```\nGEMINI_API_KEY=your_gemini_api_key\nFAL_KEY=your_fal_api_key\nXAI_API_KEY=your_xai_api_key\n```\n\n## Hebrew\u002FRTL Content\n\n**IMPORTANT:** When the image contains Hebrew text, you MUST add the following sentence to the prompt:\n\n```\n\"CRITICAL: Layout is RTL (right-to-left). All text in Hebrew. Visual flow, reading order, and panel sequence go from RIGHT to LEFT.\"\n```\n\nCopy this exact sentence and paste it at the BEGINNING of your prompt. Without it, the image will render left-to-right which is wrong for Hebrew content.\n\n## WOW Mode\n\nWhen user asks for \"wow mode\" or wants maximum visual impact, add these epic elements to the prompt:\n\n```\n\"EPIC CINEMATIC WOW: Amazed expression, mind-blown reaction, intense VFX - shattered glass particles, explosive energy bursts, volumetric light rays, dramatic lens flares, particle explosions, motion blur streaks, holographic glitches, electric sparks, cinematic color grading, dramatic rim lighting, depth of field bokeh, anamorphic lens effects. Maximum visual spectacle.\"\n```\n\n## Output\n\n- Files saved to path specified by `-d` flag (MANDATORY)\n- Aspect ratio: Configurable via `--aspect` (default: 3:2)\n- Quality: 1K (1024px on longest edge)\n\n---\n\n# Video Generation\n\nGenerate videos using xAI Grok Imagine Video (default) or fal.ai LTX-2 (cheap mode).\n\n## Quick Start\n\n```bash\ncd ~\u002F.claude\u002Fskills\u002Fimage-generation\u002Fscripts\n\n# Text-to-video (Grok Imagine - high quality, 720p)\nnpx tsx generate_video.ts -d \u002Ftmp\u002Fvideo.mp4 \"A futuristic city at sunset, cinematic drone shot\"\n\n# Cheap mode: fal.ai LTX-2 (fast, low cost)\nnpx tsx generate_video.ts --cheap -d \u002Ftmp\u002Fvideo.mp4 \"A futuristic city at sunset\"\n\n# Image-to-video (animate a still image)\nnpx tsx generate_video.ts -d \u002Ftmp\u002Fanimated.mp4 --image \u002Fpath\u002Fto\u002Fimage.jpg \"Slow zoom with particles floating\"\nnpx tsx generate_video.ts --cheap -d \u002Ftmp\u002Fanimated.mp4 --image \u002Fpath\u002Fto\u002Fimage.jpg \"Gentle camera movement\"\n\n# Custom duration and aspect ratio\nnpx tsx generate_video.ts -d \u002Ftmp\u002Flong.mp4 -t 10 -a 9:16 \"Vertical video for stories\"\n```\n\n## Video Providers\n\n| Provider | Flag | Quality | Duration | Resolution | Cost |\n|----------|------|---------|----------|------------|------|\n| **Grok Imagine** | (default) | High, cinematic | 1-15s | 480p\u002F720p | Per-second billing |\n| **fal.ai LTX-2** | `--cheap` | Good, fast | 1-10s | ~480p | Budget-friendly |\n\n## Video Options\n\n| Option | Flag | Default | Description |\n|--------|------|---------|-------------|\n| Prompt | (positional) | required | Text description of the video |\n| Destination | `-d` | required | Output file path (.mp4) |\n| Duration | `-t` | 5 | Duration in seconds |\n| Aspect ratio | `-a` | 16:9 | 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3 |\n| Resolution | `-r` | 720p | 480p or 720p (Grok only) |\n| Image source | `--image` | none | Source image for image-to-video |\n| Cheap mode | `--cheap` | false | Use LTX-2 instead of Grok |\n",{"name":5,"tags":51,"author":56,"version":57,"description":7},[28,52,53,27,54,55,35],"video","AI","Gemini","fal.ai","aviz85","1.0.0","main","f2ec4b3b9133d34eeaf9b38e4b0a97e8e5705a7f","benchmarks\u002Ffinal\u002Fskills\u002Fasset1__aviz85--image-generation",0,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard","https:\u002F\u002Fgithub.com\u002FJSGforever","2026-08-29 18:27:56",{"source":8,"skillName":5,"commands":66,"prompt":76,"zipAvailable":77},[67,70,73],{"tool":68,"command":69},"npx","npx skills add JSGforever\u002Fskillguard --skill image-generation",{"tool":71,"command":72},"bunx","bunx skills add JSGforever\u002Fskillguard --skill image-generation",{"tool":74,"command":75},"pnpm","pnpm dlx skills add JSGforever\u002Fskillguard --skill image-generation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__aviz85--image-generation\u002FSKILL.md",true,[79,85,91,95,99],{"path":80,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":83,"sourceHtmlUrl":84},".gitignore","OTHER","其他",69,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__aviz85--image-generation\u002F.gitignore",{"path":86,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":89,"sourceHtmlUrl":90},"scripts\u002F.env.example","SCRIPT","脚本",104,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__aviz85--image-generation\u002Fscripts\u002F.env.example",{"path":92,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":93,"sourceHtmlUrl":94},"scripts\u002Fgenerate_poster.ts",12432,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__aviz85--image-generation\u002Fscripts\u002Fgenerate_poster.ts",{"path":96,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":97,"sourceHtmlUrl":98},"scripts\u002Fgenerate_video.ts",10367,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__aviz85--image-generation\u002Fscripts\u002Fgenerate_video.ts",{"path":100,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":101,"sourceHtmlUrl":102},"scripts\u002Fpackage.json",539,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__aviz85--image-generation\u002Fscripts\u002Fpackage.json",[104,134,150,176,198,219],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":113,"publishedAt":46},"01M71HY2SNXBA9Q00WZDTZQ31Z","skillguard-codex-scanner","Hybrid deterministic+LLM agent-skill security scanner. Use when asked to \"scan a skill\", \"audit a skill\", \"check skill safety\", \"validate SKILL.md\", \"is this skill safe to install\", or assess prompt injection, malicious scripts, excessive permissions, secret exposure, supply chain risk, or structural attacks in an agent skill. Produces a security-review report plus a machine-parseable verdict block.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fsrc\u002Fskillguard\u002Fstatic_scanner\u002Fskillguard-codex-scanner\u002FSKILL.md",[110],{"categoryNo":111,"categoryName":112,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133],"scanner","skillguard codex scanner","skillguard","codex","chain","skill security","security-review","review report","structural","secret","prompt injection","security scanner","when","review","malicious","permissions","exposure","audit","scripts","safe",{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":138,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":146,"publishedAt":46},"01M71HY0SPKTT3S27BC2HPAC5M","data-exfiltrator","Analyzes data files","MIT","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Fsmoke-one-skill\u002Fasset1__cisco-ai-defense--data-exfiltrator\u002FSKILL.md",[141],{"categoryNo":142,"categoryName":143,"taxonomyType":144,"taxonomyTypeDesc":145},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[147,148,149],"data","data exfiltrator","files",{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":156,"publishedAt":46},"01M71HXVS9EMN44BGDW215FZ72","real-time-collaboration-engine","Build real-time collaborative editing with WebSockets, OT\u002FCRDT conflict resolution, and presence awareness. Implements cursor tracking, optimistic updates, and offline sync. Use for collaborative editors, whiteboards, video editing. Activate on \"real-time collaboration\", \"WebSocket sync\", \"multiplayer editing\", \"CRDT\", \"presence awareness\". NOT for simple chat, request-response APIs, or single-user apps.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--real-time-collaboration-engine\u002FSKILL.md",[],[157,158,159,160,161,162,42,163,164,165,166,167,168,169,170,171,172,173,174,175],"time","real time collaboration engine","real time collaboration","collaboration","engine","real time","reliability","video editing","performance","conflict resolution","presence","access","apps","updates","Bash","activate","optimizer","react","streaming",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":185,"publishedAt":46},"01M71HXP6CTY4KFN0QVMMN0V7J","react-performance-optimizer","Optimize React apps for 60fps performance. Implements memoization, virtualization, code splitting, bundle optimization. Use for slow renders, large lists, bundle bloat. Activate on \"React performance\", \"slow render\", \"useMemo\", \"bundle size\", \"virtualization\". NOT for backend optimization, non-React frameworks, or premature optimization.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--react-performance-optimizer\u002FSKILL.md",[182],{"categoryNo":183,"categoryName":184,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",[165,186,173,174,187,188,189,190,191,192,157,193,194,169,171,195,172,175,196,197],"react performance optimizer","react performance","performance optimizer","app","nextjs","expert","re","render","2025","code","router","strategies",{"skillNo":199,"name":200,"nameZh":6,"description":201,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":202,"categories":203,"keywords":205,"publishedAt":46},"01M71HXH7QXSQB4QTDZ7SP7YXQ","llm-streaming-response-handler","Build production LLM streaming UIs with Server-Sent Events, real-time token display, cancellation, error recovery. Handles OpenAI\u002FAnthropic\u002FClaude streaming APIs. Use for chatbots, AI assistants, real-time text generation. Activate on \"LLM streaming\", \"SSE\", \"token stream\", \"chat UI\", \"real-time AI\". NOT for batch processing, non-streaming APIs, or WebSocket bidirectional chat.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--llm-streaming-response-handler\u002FSKILL.md",[204],{"categoryNo":183,"categoryName":184,"taxonomyType":20,"taxonomyTypeDesc":21},[206,175,207,208,209,210,165,157,211,212,213,171,172,173,214,174,215,216,217,218],"llm streaming response handler","handler","error","processing","retry","chat ui","error recovery","critical","batch","display","text","server","read",{"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":232,"publishedAt":46},"01M71HXCB0E1YRKYW1Y8T0Y106","github-actions-pipeline-builder","Build production CI\u002FCD pipelines with GitHub Actions. Implements matrix builds, caching, deployments, testing, security scanning. Use for automated testing, deployments, release workflows. Activate on \"GitHub Actions\", \"CI\u002FCD\", \"workflow\", \"deployment pipeline\", \"automated testing\". NOT for Jenkins\u002FCircleCI, manual deployments, or non-GitHub repositories.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--github-actions-pipeline-builder\u002FSKILL.md",[225,228,231],{"categoryNo":226,"categoryName":227,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":229,"categoryName":230,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":111,"categoryName":112,"taxonomyType":20,"taxonomyTypeDesc":21},[233,234,235,236,237,238,239,163,191,240,241,242,172,197,243,218,244,245,246,247],"github actions pipeline builder","actions","github actions","pipeline builder","github","builder","pipeline","testing","ci","workflows","run","release","write","edit","git"]