CommunityProgramación y desarrollogithub.com

modbender/skill-library-mcp

An MCP server that provides on-demand skill loading for AI coding assistants.

¿Qué es skill-library-mcp?

skill-library-mcp is a Claude Code agent skill that an MCP server that provides on-demand skill loading for AI coding assistants.

Compatible con~Claude Code~Codex CLI~Cursor
npx skills add modbender/skill-library-mcp

Installed? Explore more Programación y desarrollo skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →

Preguntar en tu IA favorita

Abre un nuevo chat con esta habilidad de agente ya precargada.

Documentación

Cine Cog - Grand Cinema, Accessible to Everyone

If you can imagine it, CellCog can film it.

The grandest cinematics were locked behind million-dollar production budgets — epic compositions, consistent characters across scenes, cinematic lighting, sweeping narratives. For the first time, AI makes all of this accessible from a single prompt.

CellCog's mission with Cine-cog: make the grandest visual storytelling available to everyone. Character-consistent widescreen cinematics, generated from imagination, not budgets.


Prerequisites

This skill requires the cellcog skill for SDK setup and API calls.

clawhub install cellcog

Read the cellcog skill first for SDK setup. This skill shows you what's possible.

Quick pattern (v1.0+):

# Fire-and-forget - returns immediately
result = client.create_chat(
    prompt="[your cinematic vision]",
    notify_session_key="agent:main:main",
    task_label="cinematic-video",
    chat_mode="agent team"  # Agent team for cinematic depth
)
# You'll be notified when your film is ready

What Makes Cine-cog Different

Full Production Pipeline

From a single prompt, CellCog handles the entire cinematic pipeline:

  1. Script & storyboard — Deep reasoning breaks your vision into scenes, shots, and narrative beats
  2. Character design — Creates characters that stay consistent across every frame
  3. Scene generation — Widescreen (16:9) frames with cinematic composition, lighting, and depth
  4. Animation — Brings static frames to life with motion, camera movement, and lipsync
  5. Sound design — Original score, voiceover, and sound effects
  6. Post-production — Automatic editing, scene transitions, and final render

What Previously Cost Millions

Traditional ProductionCine-cog
Concept artists, storyboard artistsOne prompt
Character designers ensuring consistencyAutomatic across all scenes
Camera crews, lighting rigsAI cinematography
Composers, sound engineersGenerated score + effects
Weeks of post-productionAutomatic editing and rendering
Budget: $100K - $10M+Budget: One CellCog request

What Cinematics You Can Create

Epic Narrative Films

Grand visual storytelling:

  • Fantasy Epics: "Create a 3-minute cinematic: a lone knight approaches a dragon's lair at sunset"
  • Sci-Fi Visions: "Film a 2-minute sequence: humanity's first steps on Mars, cinematic widescreen"
  • Historical Drama: "Create a cinematic recreation of an ancient Roman triumph"
  • Mythological: "Film the story of Icarus — from workshop to flight to fall — in 90 seconds"

Example prompt:

"Create a 2-minute cinematic film:

Story: A young astronaut sees Earth from space for the first time

Scene 1: Inside the spacecraft — nervous anticipation, checking instruments Scene 2: The hatch opens — light floods in Scene 3: The reveal — Earth in full glory through the viewport Scene 4: Close-up — tears floating in zero gravity, awe on their face

Style: Interstellar meets Gravity. Widescreen 16:9. Music: Orchestral, building from quiet wonder to overwhelming emotion. No dialogue — let the visuals speak."

Brand Cinematics

Premium visual content for brands:

  • Product Films: "Create a 60-second cinematic product reveal for a luxury watch"
  • Brand Stories: "Film a 2-minute origin story for our coffee brand — from bean to cup"
  • Launch Videos: "Create a cinematic launch trailer for our new app"
  • Corporate Films: "Film a 90-second cinematic company vision piece"

Example prompt:

"Create a 90-second cinematic brand film:

Brand: A sustainable fashion company Story: Follow a garment from organic cotton field → artisan workshop → confident person wearing it in the city

Cinematography: Wide establishing shots of nature, intimate close-ups of craftsmanship, urban energy for the finale Color grade: Warm, earthy tones for nature → rich, confident tones for city Music: Acoustic guitar building to modern electronic

End with logo and tagline: 'Worn with purpose.'"

Music Videos

Visual storytelling set to music:

  • Concept Videos: "Create a music video with a surreal dreamscape narrative"
  • Performance Videos: "Film a cinematic performance in an epic location"
  • Lyric Videos: "Create a cinematic lyric video with visual storytelling"
  • Visualizers: "Generate an atmospheric visual accompaniment for this track"

Short Films

Complete narrative filmmaking:

  • Drama: "Create a 3-minute short film about a father and daughter reconnecting"
  • Thriller: "Film a 2-minute suspense sequence in an abandoned building"
  • Comedy: "Create a 90-second comedy sketch with cinematic production value"
  • Experimental: "Film an abstract visual poem about the passage of time"

Cinematic Styles

StyleCharacteristicsReference
Epic/GrandSweeping landscapes, orchestral score, wide shotsLord of the Rings, Dune
IntimateClose-ups, natural light, subtle emotionMoonlight, Lost in Translation
NoirHigh contrast, shadows, moodyBlade Runner, Sin City
NaturalisticGolden hour, flowing camera, poeticTerrence Malick, Studio Ghibli
Hyper-stylizedBold colors, symmetry, precise framingWes Anderson, Wong Kar-wai
DocumentaryObservational, raw, authenticPlanet Earth, Free Solo

Cinematic Specs

FormatDimensionsBest For
Widescreen1920×1080 (16:9)Standard cinematic
Ultra-wide2560×1080 (21:9)Epic scope, letterbox feel
Vertical1080×1920 (9:16)Reels/TikTok cinematics
Square1080×1080 (1:1)Social media

Widescreen (16:9) is the default and recommended format for cinematic content.


Chat Mode for Cinematics

ScenarioRecommended Mode
Short clips, single scenes, thumbnails"agent"
Full narrative films, multi-scene cinematics, brand films"agent team"

Use "agent team" for most cinematic work. Grand cinematics benefit from deep creative deliberation — storyboarding, character consistency, narrative flow, and production design all improve with multiple reasoning passes.

Use "agent" for quick visual assets — individual cinematic frames, thumbnails, or single short scenes.


Example Prompts

Grand cinematic:

"Create a 3-minute cinematic short film:

Title: 'The Last Library' Concept: In a post-apocalyptic world, a child discovers the last remaining library

Scenes:

  1. Desolate landscape — child walking through ruins (30 sec)
  2. Discovery — a door hidden behind rubble, light seeping through (20 sec)
  3. The reveal — vast library interior, books everywhere, dust particles in light beams (30 sec)
  4. Wonder — child touching books, opening one, illustrations come to life (40 sec)
  5. Hope — child carries a book outside, sits and reads as sun sets (30 sec)

Style: Children of Men meets Studio Ghibli Music: Piano and strings, melancholic to hopeful No dialogue."

Product cinematic:

"Create a 45-second cinematic product film for wireless headphones:

Open: Extreme macro of the headphone surface, light reflecting Build: Person puts them on in a busy city — the world goes quiet Showcase: Music fills the frame — visualize the audio quality cinematically Close: Product shot, floating, clean background

Cinematography: Macro lens → wide → intimate → product Color grade: Cool urban → warm personal → clean product Music: Something that makes you FEEL the audio quality"

Short film:

"Create a 2-minute cinematic short:

Story: An old man sits alone at a café, looking at an empty chair across from him. Through subtle flashbacks, we see decades of conversations at that same table. End: A young couple sits down at the next table, beginning their own story.

Style: Wong Kar-wai color palette, intimate framing Music: Solo piano, gentle Let the visuals and music tell the story — minimal or no dialogue."


Tips for Better Cinematics

  1. Think in scenes, not descriptions: Break your vision into shots. "Wide establishing → medium → close-up" gives CellCog clear cinematic language.

  2. Reference real films: "Blade Runner lighting" or "Wes Anderson framing" communicates more than paragraphs of description.

  3. Specify emotion, not just action: "She looks out the window" is flat. "She looks out the window — longing, resignation, the smallest hint of hope" gives CellCog the emotional palette.

  4. Music direction matters: The score transforms everything. Specify mood, instruments, and arc: "Builds from quiet uncertainty to confident resolution."

  5. Let silence work: Not every scene needs dialogue. Some of the most powerful cinema is purely visual.

  6. Trust widescreen: 16:9 is your default. It's how cinema is meant to be experienced.

Individual skills in this repo

This repo contains 13 individual skills — each has its own dedicated page.

modbender/skill-library-mcp

Native video analysis using Google Gemini API. Upload and analyze video files — describe scenes, extract text/UI, answer questions about content, transcribe speech, identify objects and actions. Use when: (1) User sends a video file and wants it analyzed, (2) Video summarization or description needed, (3) Extracting text, UI elements, or information from screen recordings, (4) Answering questions about video content, (5) Comparing multiple videos, (6) Analyzing tutorials, demos, or walkthroughs.

modbender/skill-library-mcp

Borrow from Aave via credit delegation. Agent self-funds by borrowing against delegator collateral. Supports borrow, repay, health checks. Works on Aave V2/V3.

modbender/skill-library-mcp

Create AI avatar and talking head videos with OmniHuman, Fabric, PixVerse via inference.sh CLI. Models: OmniHuman 1.5, OmniHuman 1.0, Fabric 1.0, PixVerse Lipsync. Capabilities: audio-driven avatars, lipsync videos, talking head generation, virtual presenters. Use for: AI presenters, explainer videos, virtual influencers, dubbing, marketing videos. Triggers: ai avatar, talking head, lipsync, avatar video, virtual presenter, ai spokesperson, audio driven video, heygen alternative, synthesia alternative, talking avatar, lip sync, video avatar, ai presenter, digital human

modbender/skill-library-mcp

AI代码编辑器规则模板集合 - 为Cursor、Windsurf、Claude Code、Cline等AI编辑器提供项目规则配置。适用于需要配置AI编码助手规则的开发者,包含全栈Web、移动端、Vue3+SpringBoot等技术栈模板。

modbender/skill-library-mcp

Generate landing page code from product descriptions

modbender/skill-library-mcp

Create AI marketing videos for ads, promos, product launches, and brand content. Models: Veo, Seedance, Wan, FLUX for visuals, Kokoro for voiceover. Types: product demos, testimonials, explainers, social ads, brand videos. Use for: Facebook ads, YouTube ads, product launches, brand awareness. Triggers: marketing video, ad video, promo video, commercial, brand video, product video, explainer video, ad creative, video ad, facebook ad video, youtube ad, instagram ad, tiktok ad, promotional video, launch video

modbender/skill-library-mcp

Generate AI music videos end-to-end. Creates music with Suno (sunoapi.org), generates visuals with OpenAI/Seedream/Google/Seedance, and assembles into music video with ffmpeg. Supports timestamped lyrics (auto SRT), Suno native music video generation, slideshow/video/hybrid modes. Token-based cost tracking per generation.

modbender/skill-library-mcp

Generate AI-powered notes from videos (document, outline, or graphic-text formats)

modbender/skill-library-mcp

The video AI notes tool is provided by Baidu. Based on the video download address provided by the user, it downloads and parses the video, and finally generates AI notes corresponding to the video (a total of three types of notes can be generated: document notes, outline notes, and image-text notes).

modbender/skill-library-mcp

Lead strategy with competitive analysis, strategic planning, growth roadmaps, and business portfolio management.

modbender/skill-library-mcp

Build high-converting landing pages with proven structure, persuasive copy, and conversion optimization.

modbender/skill-library-mcp

Web SaaS service decomposition and AI internalization development plan generation. Analyze existing SaaS to identify functions replaceable by AI agents and establish skill-based internalization roadmap. Triggered by 'SaaS analysis', 'service decomposition', 'internalization', 'decompose', 'SaaS replacement', 'build this service with AI', etc.

modbender/skill-library-mcp

Long-form AI video production: the frontier of multi-agent coordination. CellCog orchestrates 6-7 foundation models to produce up to 4-minute videos from a single prompt — scripted, filmed, voiced, lipsync'd, scored, and edited automatically. Create marketing videos, product demos, explainer videos, educational content, spokesperson videos, training materials, UGC content, news reports.

Skills relacionados