[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MDHXB1TR7VBFRKD70YHRWY":3,"skill-same:01M6MDHXB1TR7VBFRKD70YHRWY":91},{"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":34,"publishedAt":55,"linkOnly":56,"markdownContent":57,"markdownBody":58,"frontMatter":59,"refName":62,"commitSha":63,"skillDirectory":64,"forksCount":65,"repositoryHtmlUrl":66,"repositoryHomepageUrl":67,"ownerHtmlUrl":68,"ownerBlogUrl":69,"ownerDescription":70,"updatedAt":71,"install":72,"resources":84},"01M6MDHXB1TR7VBFRKD70YHRWY","muapi-social-media-video",null,"Brand-aware social media video creator. Reads brand-identity.md, ICP.md, and messaging.md to write a post\u002Fstoryboard, craft an optimized Seedance 2.0 Director prompt, generate reference frames with the best available image model, and produce platform-ready video.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FSamurAIGPT\u002FGenerative-Media-Skills\u002Flibrary\u002Fsocial\u002Fsocial-media-video\u002FSKILL.md",[18,23,26,29],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000019","营销推广",{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":30,"categoryName":31,"taxonomyType":32,"taxonomyTypeDesc":33},"01JBSEEDCAT000000000000035","市场营销","PROFESSION","适用职业",[35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54],"muapi social media video","muapi","Video","Media","social media","social","ready","icp","platform","director","craft","storyboard","brand-identity","image","write","brand","model","messaging","generate","identity","2026-11-10 10:12:30",false,"---\nslug: muapi-social-media-video\nname: muapi-social-media-video\nversion: \"1.0.0\"\ndescription: Brand-aware social media video creator. Reads brand-identity.md, ICP.md, and messaging.md to write a post\u002Fstoryboard, craft an optimized Seedance 2.0 Director prompt, generate reference frames with the best available image model, and produce platform-ready video.\nacceptLicenseTerms: true\n---\n\n# Social Media Video Creator\n\n**End-to-end pipeline: Brand Files → Storyboard → Reference Images → Seedance 2.0 Video.**\n\nReads your brand identity, ICP, and messaging documents to produce on-brand social video — fully optimized for Seedance 2.0's instructional prompt grammar and your target platform.\n\n---\n\n## Agent Execution Protocol\n\n### Step 1 — Read Brand Files\n\nBefore writing anything, the agent MUST read all available brand files. Look for them in the working directory or any `brand\u002F` subdirectory:\n\n| File | What to extract |\n|:---|:---|\n| `brand-identity.md` | Visual style, color palette, tone, logo\u002Fproduct aesthetics, brand personality |\n| `ICP.md` | Target audience — who they are, their pain points, what motivates them |\n| `messaging.md` | Core value props, hooks, CTAs, campaign themes, taglines |\n\nIf a file is missing, proceed with what's available and note the gap.\n\n---\n\n### Step 2 — Write the Social Post + Storyboard\n\nUse brand context to produce:\n\n**Social Post Copy** (for caption\u002Fcopy):\n- Hook line (first 1–2 sentences — must stop the scroll)\n- Body (3–5 sentences: problem → solution → proof → CTA)\n- Hashtags (5–8 relevant tags)\n- CTA (one clear action)\n\n**Storyboard** (match duration to platform spec):\n```\n0–3s:  [Opening scene — hook\u002Fvisual surprise — camera move]\n3–7s:  [Core message — product\u002Fsubject in action — camera move]\n7–10s: [Resolution — brand moment — CTA text on screen]\n10–15s: [Logo\u002Ftagline hold — background music fade]\n```\n\nTone must match brand personality. If brand is playful → upbeat transitions, bright grade.\nIf brand is premium → slow reveals, dark luxury aesthetic, moody lighting.\n\n---\n\n### Step 3 — Craft the Seedance 2.0 Director Prompt\n\nTransform the storyboard into a **technical Director Brief** for Seedance 2.0.\n\n**Rules:**\n1. Never use vague descriptors (\"beautiful\", \"amazing\", \"8k\"). Use technical cinematography language.\n2. Always specify camera movement, lens type, and lighting physically.\n3. For 10s+ videos, use timecode segments: `0–3s: [...] 3–7s: [...] 7–10s: [...]`\n4. Integrate `@image1`, `@image2` reference tags if images are provided.\n5. Always include sound direction (even brief) — Seedance generates audio.\n6. Lead with composition, end with texture and micro-motion.\n\n**Director Brief Template:**\n```\n[SCENE] {environment, lighting, time of day}\n[SUBJECT] {product\u002Fcharacter\u002Fsubject with specific detail}\n[ACTION] {what happens — fluid, continuous, physically plausible}\n[CAMERA] {movement + lens + framing}\n[STYLE] {color grade, mood, film reference if helpful}\n[SOUND] {music tone, sound effects, ambient}\n0–Xs: {if multi-beat}\n```\n\n---\n\n### Step 4 — Generate Reference Images (If Needed)\n\n**When to generate reference images:**\n\n| Scenario | Mode | Images Needed |\n|:---|:---|:---|\n| Product showcase | `i2v` | 1 product shot as first frame |\n| Scene transition | `first-last` | 2 images — opening and closing frame |\n| Brand character | `i2v` | 1 character reference |\n| Pure concept | `t2v` | None — text only |\n| Mood\u002Fstyle anchor | `i2v` | 1 style reference image |\n\n**Image generation — best models by use case:**\n\n| Use Case | Recommended Model | Why |\n|:---|:---|:---|\n| Photorealistic product\u002Fscene | `google-imagen4-ultra` | Highest realism, great lighting |\n| Concept art \u002F stylized | `flux-kontext-pro-t2i` | Creative fidelity, style adherence |\n| Fastest turnaround | `google-imagen4-fast` | Speed with good quality |\n| Highly detailed\u002Feditorial | `hidream-i1-full` | Fine detail, editorial quality |\n| Character with identity | `ideogram-v3-t2i` | Strong text + character rendering |\n\n**Reference image prompt format:**\nWrite a clean, technical image prompt (not a Seedance prompt). Include:\n- Subject description + key product\u002Fbrand visual elements\n- Lighting (studio, golden hour, etc.)\n- Shot framing (medium shot, product close-up, etc.)\n- Mood\u002Fcolor palette matching brand identity\n- NO motion language (this is for a still frame)\n\nExecute image generation:\n```bash\nbash core\u002Fmedia\u002Fgenerate-image.sh \\\n  --model google-imagen4-ultra \\\n  --prompt \"your image prompt\" \\\n  --aspect-ratio 9:16 \\\n  --view\n```\n\n---\n\n### Step 5 — Generate the Video\n\nChoose mode, tier, and camera based on content type and available assets.\n\n**Mode selection:**\n\n| Situation | Mode | Command |\n|:---|:---|:---|\n| No reference images | `t2v` | default |\n| 1 image (first frame) | `i2v` | `--mode i2v --file ref.jpg` |\n| Start + end frames | `first-last` | `--mode first-last --tier global --file start.jpg --file end.jpg` |\n| Multi-ref blend | `i2v` | up to 9 images |\n\n**Invoke the script:**\n```bash\nbash library\u002Fsocial\u002Fsocial-media-video\u002Fscripts\u002Frun-social-video.sh \\\n  --prompt \"your director brief here\" \\\n  --platform instagram \\\n  --camera drone \\\n  [--mode t2v|i2v|first-last] \\\n  [--file ref_image.jpg] \\\n  [--gen-ref \"reference image prompt\"] \\\n  [--tier global] \\\n  [--quality high] \\\n  [--view]\n```\n\n---\n\n## Platform Specs\n\n| Platform | Format | Aspect | Duration | Notes |\n|:---|:---|:---|:---|:---|\n| Instagram Reels | Vertical | 9:16 | 10–15s | Hook in first 1s |\n| Instagram Feed | Square | 1:1 | 10s | Static-feel works well |\n| TikTok | Vertical | 9:16 | 10–15s | High energy, fast cuts |\n| YouTube Shorts | Vertical | 9:16 | 15s | Max quality |\n| LinkedIn | Landscape | 16:9 | 10–15s | Professional tone |\n| Twitter\u002FX | Landscape | 16:9 | 10s | Punchy, direct |\n| YouTube (long) | Landscape | 16:9 | 15s | Cinematic, slow builds |\n| Pinterest | Portrait | 4:3 | 10s | Lifestyle-forward |\n\n> **Tier note:** Use `--tier global` or `--tier vip` for `1:1` and `21:9` formats. Chinese tier supports only 16:9, 9:16, 4:3, 3:4.\n\n---\n\n## Camera Language Reference\n\n### Standard Camera Intents (--camera \u002F --intent flags)\n\n| Intent | Movement | Best For |\n|:---|:---|:---|\n| `reveal` | Slow crane up, wide establishing | Product launches, brand reveals |\n| `epic` | Dolly in + orbit, low hero angle | Brand manifesto, emotional story |\n| `product` | Static macro orbit, precision reveal | E-commerce, product demo |\n| `narrative` | Tracking shot, Steadicam | Testimonials, story-driven |\n| `tense` | Handheld jitter, dutch angle | High-energy, urgency |\n| `comedy` | Reactive handheld, punchy zooms | Lighthearted brand content |\n\n### Specialty Camera Intents (New)\n\n| Intent | Description | Best For |\n|:---|:---|:---|\n| `fpv` | First-person subjective POV — immersive GoPro-style, continuous forward motion, peripheral detail close-ups | Action brands, travel, sports, tech demos |\n| `drone` | Aerial cinematic flythrough — smooth gimbal-stabilized, sweeping laterals, descend from high altitude into scene | Real estate, luxury, outdoor brands, epic reveals |\n| `flythrough` | Ground-level architectural flythrough — continuous dolly through space, seamless portal transitions | Architecture, interior design, venue showcases |\n\n**FPV Prompt Enrichment:**\n```\nImmersive first-person POV shot. Camera glides forward through [scene] at eye level.\nSlight natural motion stabilization with GoPro-style wide angle.\nPeripheral detail rushing past — [details]. Smooth continuous forward motion.\nNo cuts throughout. [Subject] visible in foreground periphery.\n```\n\n**Drone Flythrough Prompt Enrichment:**\n```\nCinematic aerial drone shot. Camera descends from 200m altitude toward [subject\u002Fscene],\nsweeping lateral arc as it descends. Gimbal-stabilized smooth motion.\nGolden hour atmosphere, long shadows across [terrain\u002Fscene].\nFinal frame settles into medium establishing shot.\nAerial cinematography, DJI Inspire aesthetic.\n```\n\n---\n\n## Prompt Quality Checklist\n\nBefore finalizing the Seedance prompt, verify:\n\n- [ ] Scene environment is physically specific (not \"nice background\")\n- [ ] Camera movement named explicitly (dolly in, orbit, drone flythrough, FPV, etc.)\n- [ ] Lighting described technically (volumetric god rays, rim lighting, soft diffused, etc.)\n- [ ] Subject\u002Fproduct described with visual specifics from brand-identity.md\n- [ ] Sound direction included (even one line)\n- [ ] Timecodes used for 10s+ videos\n- [ ] `@image1` etc. referenced if images are provided\n- [ ] Brand CTA or tagline included in final seconds\n- [ ] No vague adjectives (\"amazing\", \"beautiful\", \"stunning\") — replaced with technical terms\n\n---\n\n## Example: Full Workflow\n\n**User**: \"Make an Instagram Reel for our cold brew coffee brand, drone shot, premium feel\"\n\n**Step 1 — Brand read**: Read `brand-identity.md` (minimalist packaging, dark roast, black + gold palette), `ICP.md` (urban professionals 25–40, values quality), `messaging.md` (\"Precision Brewed. Zero Compromise.\")\n\n**Step 2 — Storyboard**:\n```\n0–2s:  Drone descends over rooftop terrace at sunrise, fog below.\n2–5s:  Drone swoops down toward coffee cup on white marble, steam rising.\n5–9s:  Close-up orbit of bottle, specular gold highlights, ice cubes.\n9–11s: Product settles, black screen fades in: \"Zero Compromise.\" + logo\nSound: Minimal lounge beat, coffee pour sound effect at 5s.\n```\n\n**Step 3 — Seedance Director Prompt**:\n```\n0–2s: Cinematic aerial drone shot. Camera descends at 30° angle toward a rooftop terrace at sunrise.\nGolden hour atmosphere, San Francisco bay fog below horizon. Gimbal-stabilized smooth descent.\n2–5s: Drone rapidly closes toward a glass of cold brew coffee on white marble.\nSteam curling upward. Macro lens approach. Caustic light patterns on wet glass surface.\n5–9s: Slow precision orbit around cold brew bottle. Black matte label with gold embossed text catching\nspecular highlights. Ice cubes with subsurface light scattering. Commercial macro aesthetic.\n9–11s: Static product hero shot. Letterbox crop, deep focus, black fade in from sides.\nSound: Minimal ambient beat, single piano note, coffee liquid sound effect at 5s mark.\nMaintain cinematic color grade — deep blacks, warm gold midtones throughout.\n```\n\n**Step 4 — Generate reference**: `google-imagen4-ultra` → cold brew bottle product shot (9:16)\n\n**Step 5 — Generate video**:\n```bash\nbash library\u002Fsocial\u002Fsocial-media-video\u002Fscripts\u002Frun-social-video.sh \\\n  --prompt \"0–2s: Cinematic aerial drone shot...\" \\\n  --platform instagram \\\n  --camera drone \\\n  --mode i2v \\\n  --file media_outputs\u002Fcoldbrew_ref.jpg \\\n  --duration 11 \\\n  --tier global \\\n  --view\n```\n\n---\n\n## Common Mistakes to Avoid\n\n1. **Reading brand files and ignoring them** — the storyboard must visually match the brand palette and tone.\n2. **Generic prompts** — \"a nice video of a product\" produces generic output. Every token must direct.\n3. **Wrong tier for aspect ratio** — 1:1 and 21:9 require `--tier global` or `--tier vip`.\n4. **Forgetting sound** — Seedance generates audio. Direct it, or you get random results.\n5. **FPV with static subject** — FPV requires continuous motion in the scene. Pair with movement-rich environments.\n6. **Drone without establishing shot** — drone works best when it resolves INTO something (a product, a scene, a subject).\n7. **Too many scene changes in 5s** — match complexity to duration. 5s = 1 beat. 15s = 3–4 beats.\n","# Social Media Video Creator\n\n**End-to-end pipeline: Brand Files → Storyboard → Reference Images → Seedance 2.0 Video.**\n\nReads your brand identity, ICP, and messaging documents to produce on-brand social video — fully optimized for Seedance 2.0's instructional prompt grammar and your target platform.\n\n---\n\n## Agent Execution Protocol\n\n### Step 1 — Read Brand Files\n\nBefore writing anything, the agent MUST read all available brand files. Look for them in the working directory or any `brand\u002F` subdirectory:\n\n| File | What to extract |\n|:---|:---|\n| `brand-identity.md` | Visual style, color palette, tone, logo\u002Fproduct aesthetics, brand personality |\n| `ICP.md` | Target audience — who they are, their pain points, what motivates them |\n| `messaging.md` | Core value props, hooks, CTAs, campaign themes, taglines |\n\nIf a file is missing, proceed with what's available and note the gap.\n\n---\n\n### Step 2 — Write the Social Post + Storyboard\n\nUse brand context to produce:\n\n**Social Post Copy** (for caption\u002Fcopy):\n- Hook line (first 1–2 sentences — must stop the scroll)\n- Body (3–5 sentences: problem → solution → proof → CTA)\n- Hashtags (5–8 relevant tags)\n- CTA (one clear action)\n\n**Storyboard** (match duration to platform spec):\n```\n0–3s:  [Opening scene — hook\u002Fvisual surprise — camera move]\n3–7s:  [Core message — product\u002Fsubject in action — camera move]\n7–10s: [Resolution — brand moment — CTA text on screen]\n10–15s: [Logo\u002Ftagline hold — background music fade]\n```\n\nTone must match brand personality. If brand is playful → upbeat transitions, bright grade.\nIf brand is premium → slow reveals, dark luxury aesthetic, moody lighting.\n\n---\n\n### Step 3 — Craft the Seedance 2.0 Director Prompt\n\nTransform the storyboard into a **technical Director Brief** for Seedance 2.0.\n\n**Rules:**\n1. Never use vague descriptors (\"beautiful\", \"amazing\", \"8k\"). Use technical cinematography language.\n2. Always specify camera movement, lens type, and lighting physically.\n3. For 10s+ videos, use timecode segments: `0–3s: [...] 3–7s: [...] 7–10s: [...]`\n4. Integrate `@image1`, `@image2` reference tags if images are provided.\n5. Always include sound direction (even brief) — Seedance generates audio.\n6. Lead with composition, end with texture and micro-motion.\n\n**Director Brief Template:**\n```\n[SCENE] {environment, lighting, time of day}\n[SUBJECT] {product\u002Fcharacter\u002Fsubject with specific detail}\n[ACTION] {what happens — fluid, continuous, physically plausible}\n[CAMERA] {movement + lens + framing}\n[STYLE] {color grade, mood, film reference if helpful}\n[SOUND] {music tone, sound effects, ambient}\n0–Xs: {if multi-beat}\n```\n\n---\n\n### Step 4 — Generate Reference Images (If Needed)\n\n**When to generate reference images:**\n\n| Scenario | Mode | Images Needed |\n|:---|:---|:---|\n| Product showcase | `i2v` | 1 product shot as first frame |\n| Scene transition | `first-last` | 2 images — opening and closing frame |\n| Brand character | `i2v` | 1 character reference |\n| Pure concept | `t2v` | None — text only |\n| Mood\u002Fstyle anchor | `i2v` | 1 style reference image |\n\n**Image generation — best models by use case:**\n\n| Use Case | Recommended Model | Why |\n|:---|:---|:---|\n| Photorealistic product\u002Fscene | `google-imagen4-ultra` | Highest realism, great lighting |\n| Concept art \u002F stylized | `flux-kontext-pro-t2i` | Creative fidelity, style adherence |\n| Fastest turnaround | `google-imagen4-fast` | Speed with good quality |\n| Highly detailed\u002Feditorial | `hidream-i1-full` | Fine detail, editorial quality |\n| Character with identity | `ideogram-v3-t2i` | Strong text + character rendering |\n\n**Reference image prompt format:**\nWrite a clean, technical image prompt (not a Seedance prompt). Include:\n- Subject description + key product\u002Fbrand visual elements\n- Lighting (studio, golden hour, etc.)\n- Shot framing (medium shot, product close-up, etc.)\n- Mood\u002Fcolor palette matching brand identity\n- NO motion language (this is for a still frame)\n\nExecute image generation:\n```bash\nbash core\u002Fmedia\u002Fgenerate-image.sh \\\n  --model google-imagen4-ultra \\\n  --prompt \"your image prompt\" \\\n  --aspect-ratio 9:16 \\\n  --view\n```\n\n---\n\n### Step 5 — Generate the Video\n\nChoose mode, tier, and camera based on content type and available assets.\n\n**Mode selection:**\n\n| Situation | Mode | Command |\n|:---|:---|:---|\n| No reference images | `t2v` | default |\n| 1 image (first frame) | `i2v` | `--mode i2v --file ref.jpg` |\n| Start + end frames | `first-last` | `--mode first-last --tier global --file start.jpg --file end.jpg` |\n| Multi-ref blend | `i2v` | up to 9 images |\n\n**Invoke the script:**\n```bash\nbash library\u002Fsocial\u002Fsocial-media-video\u002Fscripts\u002Frun-social-video.sh \\\n  --prompt \"your director brief here\" \\\n  --platform instagram \\\n  --camera drone \\\n  [--mode t2v|i2v|first-last] \\\n  [--file ref_image.jpg] \\\n  [--gen-ref \"reference image prompt\"] \\\n  [--tier global] \\\n  [--quality high] \\\n  [--view]\n```\n\n---\n\n## Platform Specs\n\n| Platform | Format | Aspect | Duration | Notes |\n|:---|:---|:---|:---|:---|\n| Instagram Reels | Vertical | 9:16 | 10–15s | Hook in first 1s |\n| Instagram Feed | Square | 1:1 | 10s | Static-feel works well |\n| TikTok | Vertical | 9:16 | 10–15s | High energy, fast cuts |\n| YouTube Shorts | Vertical | 9:16 | 15s | Max quality |\n| LinkedIn | Landscape | 16:9 | 10–15s | Professional tone |\n| Twitter\u002FX | Landscape | 16:9 | 10s | Punchy, direct |\n| YouTube (long) | Landscape | 16:9 | 15s | Cinematic, slow builds |\n| Pinterest | Portrait | 4:3 | 10s | Lifestyle-forward |\n\n> **Tier note:** Use `--tier global` or `--tier vip` for `1:1` and `21:9` formats. Chinese tier supports only 16:9, 9:16, 4:3, 3:4.\n\n---\n\n## Camera Language Reference\n\n### Standard Camera Intents (--camera \u002F --intent flags)\n\n| Intent | Movement | Best For |\n|:---|:---|:---|\n| `reveal` | Slow crane up, wide establishing | Product launches, brand reveals |\n| `epic` | Dolly in + orbit, low hero angle | Brand manifesto, emotional story |\n| `product` | Static macro orbit, precision reveal | E-commerce, product demo |\n| `narrative` | Tracking shot, Steadicam | Testimonials, story-driven |\n| `tense` | Handheld jitter, dutch angle | High-energy, urgency |\n| `comedy` | Reactive handheld, punchy zooms | Lighthearted brand content |\n\n### Specialty Camera Intents (New)\n\n| Intent | Description | Best For |\n|:---|:---|:---|\n| `fpv` | First-person subjective POV — immersive GoPro-style, continuous forward motion, peripheral detail close-ups | Action brands, travel, sports, tech demos |\n| `drone` | Aerial cinematic flythrough — smooth gimbal-stabilized, sweeping laterals, descend from high altitude into scene | Real estate, luxury, outdoor brands, epic reveals |\n| `flythrough` | Ground-level architectural flythrough — continuous dolly through space, seamless portal transitions | Architecture, interior design, venue showcases |\n\n**FPV Prompt Enrichment:**\n```\nImmersive first-person POV shot. Camera glides forward through [scene] at eye level.\nSlight natural motion stabilization with GoPro-style wide angle.\nPeripheral detail rushing past — [details]. Smooth continuous forward motion.\nNo cuts throughout. [Subject] visible in foreground periphery.\n```\n\n**Drone Flythrough Prompt Enrichment:**\n```\nCinematic aerial drone shot. Camera descends from 200m altitude toward [subject\u002Fscene],\nsweeping lateral arc as it descends. Gimbal-stabilized smooth motion.\nGolden hour atmosphere, long shadows across [terrain\u002Fscene].\nFinal frame settles into medium establishing shot.\nAerial cinematography, DJI Inspire aesthetic.\n```\n\n---\n\n## Prompt Quality Checklist\n\nBefore finalizing the Seedance prompt, verify:\n\n- [ ] Scene environment is physically specific (not \"nice background\")\n- [ ] Camera movement named explicitly (dolly in, orbit, drone flythrough, FPV, etc.)\n- [ ] Lighting described technically (volumetric god rays, rim lighting, soft diffused, etc.)\n- [ ] Subject\u002Fproduct described with visual specifics from brand-identity.md\n- [ ] Sound direction included (even one line)\n- [ ] Timecodes used for 10s+ videos\n- [ ] `@image1` etc. referenced if images are provided\n- [ ] Brand CTA or tagline included in final seconds\n- [ ] No vague adjectives (\"amazing\", \"beautiful\", \"stunning\") — replaced with technical terms\n\n---\n\n## Example: Full Workflow\n\n**User**: \"Make an Instagram Reel for our cold brew coffee brand, drone shot, premium feel\"\n\n**Step 1 — Brand read**: Read `brand-identity.md` (minimalist packaging, dark roast, black + gold palette), `ICP.md` (urban professionals 25–40, values quality), `messaging.md` (\"Precision Brewed. Zero Compromise.\")\n\n**Step 2 — Storyboard**:\n```\n0–2s:  Drone descends over rooftop terrace at sunrise, fog below.\n2–5s:  Drone swoops down toward coffee cup on white marble, steam rising.\n5–9s:  Close-up orbit of bottle, specular gold highlights, ice cubes.\n9–11s: Product settles, black screen fades in: \"Zero Compromise.\" + logo\nSound: Minimal lounge beat, coffee pour sound effect at 5s.\n```\n\n**Step 3 — Seedance Director Prompt**:\n```\n0–2s: Cinematic aerial drone shot. Camera descends at 30° angle toward a rooftop terrace at sunrise.\nGolden hour atmosphere, San Francisco bay fog below horizon. Gimbal-stabilized smooth descent.\n2–5s: Drone rapidly closes toward a glass of cold brew coffee on white marble.\nSteam curling upward. Macro lens approach. Caustic light patterns on wet glass surface.\n5–9s: Slow precision orbit around cold brew bottle. Black matte label with gold embossed text catching\nspecular highlights. Ice cubes with subsurface light scattering. Commercial macro aesthetic.\n9–11s: Static product hero shot. Letterbox crop, deep focus, black fade in from sides.\nSound: Minimal ambient beat, single piano note, coffee liquid sound effect at 5s mark.\nMaintain cinematic color grade — deep blacks, warm gold midtones throughout.\n```\n\n**Step 4 — Generate reference**: `google-imagen4-ultra` → cold brew bottle product shot (9:16)\n\n**Step 5 — Generate video**:\n```bash\nbash library\u002Fsocial\u002Fsocial-media-video\u002Fscripts\u002Frun-social-video.sh \\\n  --prompt \"0–2s: Cinematic aerial drone shot...\" \\\n  --platform instagram \\\n  --camera drone \\\n  --mode i2v \\\n  --file media_outputs\u002Fcoldbrew_ref.jpg \\\n  --duration 11 \\\n  --tier global \\\n  --view\n```\n\n---\n\n## Common Mistakes to Avoid\n\n1. **Reading brand files and ignoring them** — the storyboard must visually match the brand palette and tone.\n2. **Generic prompts** — \"a nice video of a product\" produces generic output. Every token must direct.\n3. **Wrong tier for aspect ratio** — 1:1 and 21:9 require `--tier global` or `--tier vip`.\n4. **Forgetting sound** — Seedance generates audio. Direct it, or you get random results.\n5. **FPV with static subject** — FPV requires continuous motion in the scene. Pair with movement-rich environments.\n6. **Drone without establishing shot** — drone works best when it resolves INTO something (a product, a scene, a subject).\n7. **Too many scene changes in 5s** — match complexity to duration. 5s = 1 beat. 15s = 3–4 beats.\n",{"name":5,"slug":5,"version":60,"description":7,"acceptLicenseTerms":61},"1.0.0",true,"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002FSamurAIGPT\u002FGenerative-Media-Skills\u002Flibrary\u002Fsocial\u002Fsocial-media-video",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":73,"prompt":83,"zipAvailable":61},[74,77,80],{"tool":75,"command":76},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill muapi-social-media-video",{"tool":78,"command":79},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill muapi-social-media-video",{"tool":81,"command":82},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill muapi-social-media-video","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FSamurAIGPT\u002FGenerative-Media-Skills\u002Flibrary\u002Fsocial\u002Fsocial-media-video\u002FSKILL.md",[85],{"path":86,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":89,"sourceHtmlUrl":90},"scripts\u002Frun-social-video.sh","SCRIPT","脚本",11241,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FSamurAIGPT\u002FGenerative-Media-Skills\u002Flibrary\u002Fsocial\u002Fsocial-media-video\u002Fscripts\u002Frun-social-video.sh",[92,102,110,118,126,134],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":96,"licenseFileUrl":97,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":101},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":96,"licenseFileUrl":106,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":101},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":96,"licenseFileUrl":114,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":101},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":96,"licenseFileUrl":122,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":101},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":96,"licenseFileUrl":130,"sourceHtmlUrl":131,"categories":132,"keywords":133,"publishedAt":101},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":96,"licenseFileUrl":138,"sourceHtmlUrl":139,"categories":140,"keywords":141,"publishedAt":101},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]