Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Upgrades a raw screen recording (a Loom or similar quick screen-share a rep already made, uploaded or ready to upload) into a polished, on-brand, shareable demo a rep would be comfortable sending straight to a prospect. Pulls the workspace's exact brand palette, logo, and font; cuts the dead time and mouse-wandering that makes a raw capture read as unedited; adds camera motion and callouts on the controls being discussed; decides deliberately whether to keep the rep's real narration or regenerate it; and bookends the result with branded intro and outro cards. Use when the user says "polish this Loom into a branded demo", "clean up my screen recording for a prospect", "make this raw recording look like a real sales asset", or "turn my screen-share into something I can actually send a customer".
Design and produce raster images, native SVG artwork, brand-controlled visuals, and documented image edits with Recraft's API. Use for Recraft model and route selection, exact request construction, image-to-image, inpainting, outpainting, background work, vectorization, remix/exploration, palette and typography control, API migration, safety and rights review, and production QA.
Provider-independent production workflow for assembling generated or sourced media into React/Remotion videos. Use when an agent must plan, build, render, review, variant-render, or hand off Remotion compositions with media custody, captions, audio, animation, accessibility, provenance, QA, and delivery requirements.
Turn a text prompt or script into a finished, multi-shot video with Pexo. Auto-selects the best model across 10+ engines (Seedance, Kling, Veo, Sora), writes the prompts, generates every shot, and returns a publish-ready video with music and subtitles. Use when the user wants a video FROM TEXT: "make a video about X", "turn this script into a video", "text to video", "generate a video from this description". NOT for editing an existing video or turning an image into video (use the image-to-video skill).
Guide for Unreal Engine 5.x PCG (Procedural Content Generation) Python integration. Covers the PCGPythonInterop plugin, the Execute Python Script node, PCG Python API (PCGComponent, PCGBlueprintElement, PCGSpatialData, PCGPointData), editor automation, custom PCG nodes via Python, and known limitations. Use when the user asks about PCG Python, PCGPythonInterop, Execute Python Script node, Python scripting for procedural generation, automating PCG graphs with Python, or creating custom PCG nodes with Python/Blueprint.
Use meitu-cli for video shadow enhancement, night scene brightening, and low-light restoration. Triggered when the user mentions the video is too dark, night scene brightening, low-light enhancement, dark areas being unclear, footage shot too dark at night, or low-light restoration.
Use meitu-cli for multimodal mixed-driven video generation (any combination of audio/video/image/text). Triggered when the user mentions generating with music, referencing a video's camera movement/style/rhythm, audio-driven video, or mixed generation from multiple assets.
Use meitu-cli to convert videos to animated GIFs, supporting standard GIFs (long edge ≤480px) and transparent-background GIFs (240×240px). Triggered when the user says convert video to GIF, make a meme, make an animated image, transparent-background sticker, or floating emoji.
Use this skill when planning, redesigning, or reviewing Xiaohongshu carousel visuals, covers, 3:4 image posts, page-by-page visual direction, image-generation prompts, style selection, layout critique, or XHS captions. It acts as a senior visual director for 小红书图文, not a generic copywriting assistant.
Rewrite text that sounds AI-generated while keeping the writer''s facts, meaning, and voice. Use when editing or reviewing prose for inflated claims, sales language, vague sources, repetitive structure, stock AI words, passive voice, filler, or chatbot artifacts. Based on Wikipedia''s "Signs of AI writing."
Use ACE-Step and ACE-Step 1.5 for local or hosted AI music generation, including text-to-music, lyrics-to-song, instrumental beds, covers, repainting, stem/track extraction, track completion, LoRA personalization, REST/Python/Gradio workflows, rights review, and music integration for video, ads, games, and social content.
Add branded lower-third labels to an existing video - section names, feature names, speaker names - that slide in at the start of each segment. Use when the user says "add lower thirds", "add section labels", "label each part of the video", "add name titles", or "add branded segment titles".
Weather effects in Blender — looping Geometry Nodes rain, snow, dust, ash, and embers with ground hits and splashes, wet surfaces, puddles with animated ripples, wall streaks, snow cover (shader + real snow geometry), storm lightning with multi-stroke flashes and bolts, and engine-ready weather masks. Use for rain, storm, snow, wet street, puddle, dust, or ember scenes
Transform brain dumps into polished blog posts in Nick Nisi's voice. Use when the user wants to write a blog post with scattered ideas, talking points, and conclusions that need organization into a cohesive narrative with Nick's conversational, authentic, and thoughtful tone.
Cuts a full multi-persona demo down to only the screens relevant to one specific buyer in a deal (admin console, end-user experience, analytics and reporting, whatever applies) by transcribing the demo's structure, confirming with the user exactly which sections this persona cares about, duplicating the project to keep the full demo intact, then removing the irrelevant sections at clean boundaries and checking that transitions still read naturally. This is subtraction, not reframing: no new narration is written beyond trimming a seam. Use when the user says "cut this demo down to just the admin screens", "trim this to only what this buyer cares about", "remove the parts of this demo not relevant to this persona", or "make a shorter version of this demo for this buyer that skips a section".
Fix mispronounced product names, acronyms, and jargon in a video's voiceover by respelling them phonetically and regenerating only the affected lines. Use when the user says "it's pronouncing our product name wrong", "fix the pronunciation of X", "the voiceover says the acronym weirdly", "make it say KYOO-bee not cube", or points at specific words the narration gets wrong.
Search oip-visual-v2 for traceable prompt-image pairs and open local result galleries. Use when finding, inspecting, comparing, browsing, or copying real image-generation references or exact source prompts. After references are selected, adapt them into a derived bilingual prompt when requested; use img-gen-taste first when the visual direction is still unclear.
Develop art direction for image generation with curated style cards distilled from Open Image Prompts. Use when choosing or comparing visual directions, improving an existing generation prompt, or translating a subject, use case, or supplied image into a compact creative spec. Use img-gen-prompts for real archive examples, exact source prompts, or gallery browsing.
Automatically identify illustration positions in long technical articles by 林月半子(LQ) and generate 16:9 concept diagrams, flowcharts, comparison charts, and architecture diagrams. Supports seven styles: hand-drawn grid notebook (notebook), professional flat infographic (infographic), modern high-end tech business (executive-tech), warm hand-drawn cards (cozy-handdrawn), technical doodle (tech-doodle), cartoon infographic (cartoon-infographic), and whiteboard sketch (whiteboard-sketch). Use when the user needs illustrations for an already-written article, wants to add images, optimize layout, or make a long article less monotonous. Trigger words include: 加插图, 配图, 加几张图, 让文章更生动, 排版优化, 文章太单调了, 给文章画几张手绘图, 手绘示意图, 信息图, 商务风配图, 科技商务风. The core value of this skill is "intelligently identifying which paragraphs in an article deserve an illustration" — prioritizing four categories: abstract concepts, process loops, comparisons and classifications, and architecture components, rather than mechanically adding an image to every paragraph. Generated with the MuleRun Nano Banana 2 Generation API, and supports switching visual styles via --style. Do not use for cover images (use the cover skill), screenshot replacement, pure code display, or meme generation.
Provider-independent localization and dubbing production direction for AI agents producing translated videos, dubbed ads, social clips, explainers, avatar videos, documentaries, training media, and multi-market campaigns. Use when planning or reviewing subtitle-versus-dub strategy, translation adaptation, glossary/style-guide setup, casting or voice matching, lip-sync or phrase-sync direction, synthetic dubbing boundaries, captions/subtitles handoff, accessibility, platform delivery, client review, or localization QA.
Plan and direct Midjourney Video V1 image-to-video work through the official website or Discord, with human operator handoff, motion prompts, start/end frames, loops, extensions, resolution and batch budgeting, privacy, rights, safety, and delivery QA. Use when creating Midjourney videos or when determining whether a requested API, automation, plan, or production workflow is supported.
Write mockumentary screenplays in Fountain format with proper documentary conventions, talking head formatting, and comedic dialogue. Use when user needs to write screenplay pages, format talking heads, write verite scenes, craft dialogue, or convert outline to script. Triggers on screenplay writing, Fountain formatting, dialogue writing, scene writing, or drafting for mockumentary projects.
A natural-language workflow from literary works (novels, stories, scripts, a single sentence, and so on) to film and video, chaining multiple skills to turn novel content into a complete video. Use this skill when the user needs to turn a novel, story, or literary work into video.
Turn one feature recording into three launch deliverables in a single pass: a polished launch-style video, a short written changelog blurb, and a vertical or square social cutdown clip. All three are derived from the same extracted "aha" moment so they stay consistent with each other, rather than being built as three disconnected projects. Use when the user says "turn this feature recording into a launch video, changelog, and social clip", "give me everything I need to announce this feature", "one recording, three deliverables for launch", or "I need to launch this feature everywhere".
Convert a written sales playbook or SOP (objection handling, discovery scripts, onboarding checklists, escalation procedures) into a narrated training video. Playbooks are usually procedural or branching ("if the prospect says X, do Y"), not a single narrative, so this skill diagnoses that structure before scripting and stages decision points as an animated fork rather than a wall of bullets. Use when the user says "turn our sales playbook into a training video", "convert this SOP doc into a video", "make a video version of our objection-handling playbook", or pastes a procedural or sales document and asks for a video.
Generate, differentiate, rank, and expand Point paid social and digital ad concepts into production-ready creative briefs and draft creative asset or design directions. Use for campaign brainstorming, concept territories, hooks, UGC or testimonial ideas, static or motion concepts, rough asset concepts, visual direction, cutdowns, test plans, brief writing, on-asset disclosure planning, or reviews of whether a Point social ad idea is distinct, brand-aligned, testable, legally reviewable, and feasible.
Provider-independent production guidance for converting observed video into precise, objective, temporally ordered language. Use for shot descriptions, searchable metadata, dataset captions, reference logs, generation-prompt handoffs, and analysis across subject, scene, motion, spatial, and camera aspects; not for deciding what to shoot, accessibility captions, creative interpretation, or provider-specific video analysis APIs.
Turns a product walkthrough recording into an RFP-response video plus a written requirements matrix. Maps each requirement or question from the RFP's actual requirements list to the specific moment(s) in the recording that address it, trims the video down to just that RFP-relevant content with restrained captions naming which requirement each segment demonstrates, and flags any requirement the recording doesn't cover before anything gets built. The matrix is authored on the project's live article and also handed back as text in the response. Use when the user says "turn this demo recording into an RFP response video", "build our RFP video and reference doc from this walkthrough", "map this recording to our RFP requirements", or "we need a video and a requirements matrix for this RFP response".
Use when exploring several Seedance video takes before paying for a final: cheap 480p previews, variations of one shot to compare, reviewing and ranking takes before a pick, or finalizing a chosen preview to 1080p without regenerating it, including within its 7-day window. Keywords: Seedance draft, draft mode, draft complete, finalize, 480p preview, variations, takes, review, rank, pick, Seedance 2.5.
Generates images and game sprites through GPT or Grok with guided provider choices, separate saved defaults, automatic cleanup and optional curation. Handles sprite requests, ordinary image generation/editing, standalone image-to-video clips (i2v, animate this still, 그록 영상, 이매진 비디오, 스틸 움직여줘, first/last frame, reference-to-video, 영상 이어붙이기, 영상 편집, extend/edit a clip), chroma removal, animation atlases, video loops, 큐레이션뷰, image candidates, 팔레트 스왑, palette swap, recolor, rig layers, engine exports, repeating backgrounds, projected shadows, motion/contact inspection and optional scene composition from existing assets.
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.
Use when the user wants to view AI conversation token usage as a receipt, invoice, checkout slip, token bill, usage receipt, cost snapshot, or creative monospace thermal-paper artifact. Always consider this skill for Chinese prompts like 查看本次对话 Token 消耗, 生成 token 小票, 对话发票, AI 用量账单, 把这次对话打成小票, 看看这轮 token 消耗, or any request to make token/context usage visually shareable.
Use meitu-cli to overlay Logo/watermark images on the four corners of a video, with support for transparent-background PNG. Triggered when the user mentions adding watermarks, adding a Logo, stamping a Logo, labeling, adding corner marks, compositing watermarks, overlaying a Logo, video branding, or brand marks.
Write Blender 5.2 add-ons as extensions — blender_manifest.toml, operators/panels/menus/property groups/preferences, bpy.props rules after 5.0, undo/redo, modal and timer patterns, GPU drawing (no bgl), bundling Python wheels, CLI validation/build/install, headless testing, and extensions platform publishing. Use when creating or fixing a Blender add-on, tool, or UI
Produces branded visual identity elements — logo concepts, icon sets, seamless patterns, brand illustrations, and textures — as generation-ready prompt specs, and generates them via FAL.ai fal-ai/nano-banana-pro when the automation is configured. Use when the user says 'design a logo', 'I need icons', 'brand pattern / texture', 'brand illustrations', 'visual identity elements', or 'make my brand assets'. Produces one prompt-spec block per asset (asset type, style, palette with hex, composition, negative constraints), a variant plan for user selection, file-naming conventions, and a brand-guidelines entry for each approved asset; runs docs/creative_cli.py brand when FAL_API_KEY is set.
Pull the single best interaction from a video as a crisp looping GIF - delivered through a Clueso article/document, or as a short looping video clip if that fits the destination better - for changelogs, newsletters, and in-app tooltips. Use when the user says "make a GIF of this moment", "extract a GIF from this video", "I need a looping clip of the key interaction", "GIF for the changelog", or "grab the money shot as a GIF".
Turns a community or forum text answer into a shareable how-to video. Source is a Q&A-style thread - someone asked a specific question, someone answered with text steps - and the output preserves that "direct answer to your exact question" framing rather than being smoothed into a generic tutorial. Use when the user says "turn this forum answer into a video", "make a how-to video from this community post", "this Q&A thread would make a good short video", pastes a forum or community thread and asks for a video, or points at a support-forum answer they want turned into something shareable.
When the user wants to write the first 30 seconds of a YouTube video, create retention hooks, improve video openings, or reduce early drop-off. Also use when the user says 'write a hook,' 'video intro,' 'opening for my video,' 'first 30 seconds,' 'retention hook,' 'stop the scroll,' 'my videos have bad retention at the start,' 'viewers are leaving in the first minute.' For full script structure, see script-structure. For title/thumbnail pairing, see title-craft and thumbnail-design.
Turns any request for an AI-generated image into precise, generation-ready prompt specs and — when the FAL.ai automation is configured — the generated files themselves, using the single model fal-ai/nano-banana-pro. Use whenever the user asks to 'generate an image', 'make a picture of X', 'create a thumbnail / hero image / illustration / infographic', 'write me a prompt for this image', or any visual that isn't specifically product photography, a social-platform graphic, or a brand mark (hand those to the sibling skills). Produces one prompt-spec block per asset (subject, style, composition, lighting, mood, aspect ratio, negative constraints) plus file-naming and variant conventions, and runs docs/creative_cli.py to generate when a FAL_API_KEY is available.
Reframe a landscape video into a 9:16 vertical cut for social and mobile - recompose every scene around the action area and turn captions on for sound-off viewing. Use when the user says "make a vertical version", "reframe this for Reels/Shorts/TikTok", "9:16 cut of this video", "make this portrait for LinkedIn", or "turn this into a mobile-friendly cut".
Adds translated, timed on-screen caption text in one or more target languages to an existing Clueso video while leaving the original spoken audio completely untouched, then exports a caption-only version per language. Captions are built as styled text elements synced to the real word-level timing of the existing narration. Use when the user says "add German and Japanese captions, no dub", "I need multilingual subtitles burned in", "captions in Spanish and French but keep the English audio", "burn in translated subtitles without changing the voiceover", or "subtitle this video in multiple languages".
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.