AI Agent Tools: Creative Skills

ppt-master76.1k★

PPT Master takes a PDF, Word doc, Markdown file, URL or pasted text and hands you back a native, editable PowerPoint: real shapes, text boxes and slide masters, not pictures of slides. A flag adds a second file with data-backed charts and tables you can open with Edit Data. Free, MIT licensed. It's a skill, not an app: you run it inside Claude Code, Cursor or Codex with Python 3.10+ and one pip install -r requirements.txt. It can also build a template from your brand deck, refill an existing deck, add animations and narrate the speaker notes. The examples gallery holds dozens of single-pass decks, so judge first. Solo builders and small teams turning reports into decks without a designer save hours. Larger teams with a brand group still want a human pass before anything goes external. The catch: quality tracks the model, and the first model the README recommends, Kimi K3, comes from a paying sponsor behind an affiliate link. The README also pushes API relays advertising Claude and GPT at as little as 7% of official rates. Pick the model on merit, and keep client documents away from resellers. The optional PDF converter needs AGPL-licensed PyMuPDF.

diagram-design66.6k★

Diagram-design is an agent skill that makes your coding agent draw diagrams a designer wouldn't wince at. Ask in plain words for an architecture sketch, flowchart, sequence diagram, Sankey or Gantt chart, and it picks from more than 40 types and writes one self-contained HTML file with inline SVG. MIT licensed and free. It's no longer Claude Code only. npx skills add cathrynlavery/diagram-design installs it into Cursor, Codex, Copilot, Gemini CLI, Cline and other skill-aware agents; plugin marketplaces add updates and slash commands. Point it at your website and it pulls your palette and fonts, checks contrast, and every diagram after that matches your brand. It also redraws draw.io, Mermaid and Excalidraw files and exports SVG or PNG. Solo writers and technical bloggers: install it. Small teams: save a brand profile everyone uses. Larger teams with a design system: test it first, because the style is opinionated on purpose (one accent color, hairlines, no shadows). The catch: the output is a finished picture, not a source file. Nothing to diff in a pull request, no canvas to drag, and the same prompt can lay out differently twice. For docs that change every sprint, its own README says Mermaid fits better.

anatomy26.8k★

Anatomy makes Claude explain a technical idea by drawing a machine that does it. Ask how a token-bucket rate limiter works and you get an interactive isometric figure built from dozens of shaded SVG parts, with live numbers from the same model that moves them. WebGL handles fire, water and glow; a beta 3D mode turns parts in true depth. MIT, free, no API keys. Install is one npx skills add line, and it also loads in Codex, OpenCode, Antigravity and MiniMax Code. The kit uses only Node's built-in modules, but the self-checks need Node 20.10+ and Chrome, driven headless to screenshot and audit every joint. Eight examples ship in the repo, from a dial gauge to a Raptor engine. Solo writers, devrel folks and small docs teams: free. Larger teams with designers will still hand final art to an illustrator. The catch is time, which means tokens. The author publishes his own numbers: a watch movement took 1 hour 54 minutes of Claude working, the Raptor engine 10 hours 33 minutes, a turbofan 14 hours. The skill demands at least 40 parts per figure and won't trade detail for speed unless you ask. Ask for a quick figure first.

img2threejs21.2k★

img2threejs takes a reference image and rebuilds the object in it as procedural Three.js code, using primitives and shaders instead of a downloaded mesh. It is an agent skill, not a library: you install it into Claude Code, Codex, or OpenCode and the agent runs the pipeline. Apache 2.0 since July 2026, when it moved off MIT. The design is the interesting part. Deterministic Python scripts handle validation, quality gates, and code generation using only the standard library, while the model's tokens go to the visual judgment steps: look at the image, assess it, review the render. Version 2.0 turned it into a plugin system with an img2 installer, official plugins for characters and Counter-Strike 2 weapons, and a GLB export path. Web developers who need 3D objects and would rather not model them or license assets are the audience, mostly solo and small teams. Subjects are classified as object, character, or hybrid, and characters route through an anatomy-aware track. The catch: it is strongest on hard-surface objects, and the project says so. Characters come out as stylized reconstructions, not photoreal likeness, even with the new opt-in projection path. It is also token-hungry by the README's own admission, estimating roughly 80k to 180k tokens per object. It will tell you when an image cannot reach the fidelity you asked for.

video-shotcraft18.9k★

video-shotcraft is a skill for Claude Code or Codex that turns your coding agent into a motion-design studio. Ask for a product video and it storyboards, animates real page captures with 2.5D camera moves, syncs cuts to a beat and adds sound design, then renders everything locally through Remotion. No AI video APIs, no API keys, no per-clip cost. Apache 2.0. It installs with npx skills add and runs inside the agent and Remotion toolchain you already have. After delivery it opens a local browser workbench for tweaking the result, and it can export a project to JianYing (CapCut's Chinese edition), tested on macOS only. Headless rendering on Linux needs a Chrome headless binary and low concurrency on small machines. The assets are the value: 157 shot recipes, a couple hundred Remotion motion demos and 149 sound effects, so the agent isn't improvising from scratch. Solo developers and companies of up to three people pay nothing. At four or more, Remotion requires a company license, starting at $25 a month per seat. The skill itself stays free. The catch: the skill tells your agent to describe the finished video as free for commercial use, but the author's own attribution file lists five bundled sound effects whose source couldn't be traced and says to confirm them before commercial use. Swap those out before client work. Only one finished template (Ink Press) ships so far, and the skill nudges you to tag the author on social media when it's done.

huashu-art-motion6.8k★

huashu-art-motion teaches a coding agent to animate paintings in code. Ask for a Van Gogh clip and it paints the scene on a canvas, makes the brushstrokes move, and renders an MP4 through headless Chromium. It ships 36 art-style recipe cards with 35 ready scene files, plus 9 explainer grammars modeled on Kurzgesagt, Vox, 3Blue1Brown and whiteboard videos. MIT and free. Install is one npx skills add line, but rendering needs uv, ffmpeg and Playwright Chromium. A QA script scores motion and smoothness, and the delivery script refuses to export a film that's basically a slideshow. Cloned voices bill your own ByteDance Volcengine account; macOS system voices cost nothing. Solo creators and small teams making explainer clips: free, plus your agent's usage. Studios doing client work: stick with After Effects or Remotion. The catch: the skill itself is written in Chinese. SKILL.md and the recipe cards are Chinese: your agent reads them fine, you won't when a render breaks. The showcase also leans on characters nobody here owns (a Super Mario level, a Rick and Morty style, Anthropic's mascot), and the author's own character art is carved out of the MIT grant. Restyle before you publish anything commercial.

logo-design-skill6.7k★

logo-design-skill teaches an AI agent to design logos the way a studio does: brief first, about three concepts, then it stops and waits for you to pick a direction before refining. It works in Claude Code, Claude.ai, Gemini CLI and Codex, and ships 14 reference guides (principles, mark types, color, type, SVG construction), nine Python scripts and a library of 1,432 real-world logos to study. MIT licensed. Install is a Claude Code plugin command, or a zip upload to Claude.ai (a lite version drops the logo library). The scripts use only Python's standard library: they audit an SVG for production problems, build test sheets down to favicon size, render client presentation boards and export the full icon set. No network calls. It works best with a model that can see images, because it checks its own drafts. Founders and small teams who need a first logo and would otherwise reach for Looka or Canva's logo maker should try this first. It costs nothing beyond your agent plan. A brand with real stakes still deserves a designer; use this to write them a sharper brief. The catch: output is only as good as your model's SVG skills, and every example in the README is the author's own run on made-up brands. The 1,432 reference logos are other companies' trademarks, included for study and outside the MIT license, so don't ship anything that leans too close to one. It's days old, from an author with no prior track record.

baoyu-design6.4k★

Baoyu-design takes the design engine behind Anthropic's claude.ai/design and runs it inside the coding agent you already use. Ask Claude Code, Cursor or Codex for a mockup, prototype, wireframe, landing page or deck, and it writes self-contained HTML into your repo. MIT-licensed and free. Version 2.0 shipped this week as five skills. The original makes HTML designs; four new ones port claude.ai's slides, design canvas, design system and dashboard formats, each with a local editor so you and the agent take turns. Install is one npx skills add JimLiu/baoyu-design; the editors need Node 20 or newer. Exports cover PDF, editable PowerPoint, and handoff to Figma or Canva. The bill is the model: it's tuned for Claude Opus 5.5, so free assumes you already pay for an agent. Solo and small teams: free, install it and go. Larger teams: good for first drafts, but it won't replace Figma for collaboration, and v0 wins when you want a deployed app. The catch is provenance. The README says it repackages Anthropic's Claude Design nearly word for word, unaffiliated and unendorsed. MIT covers Jim Liu's packaging, not Anthropic's prompts. Expect churn too: four releases landed in one day.

lottie5.7k★

This turns "make me a loading spinner animation" into actual Lottie code through your AI coding agent. Lottie is the format apps use for lightweight vector animations, and creating them normally means After Effects and a plugin. diffusionstudio/lottie installs as a skill for agents like Claude Code, then converts an SVG or a plain-text description into working animation code you can drop into web, React Native, iOS, Android, or Flutter. Setup is one command, npx skills add diffusionstudio/lottie, and you're generating animations by prompting. There's nothing to host and no account. Because it produces standard Lottie JSON, the output plugs into the same players and tooling you'd already use. The whole thing is MIT-licensed and free. Developers who need simple animations but don't have a motion designer, or don't want to learn After Effects, are the target. It won't replace a real animator for complex, hand-crafted motion work. For spinners, icon transitions, and straightforward UI animation, it's a fast path from idea to code without leaving your editor. The catch: it leans on your AI agent, so the quality of what you get tracks the quality of your prompt and your model. Intricate animation is still beyond what a text prompt produces cleanly, this shines on the simple-to-moderate stuff. Think of it as a head start, not a finished motion-design studio.

scroll-craft5.0k★

scroll-craft is an agent skill that builds scroll-driven landing pages: video that scrubs as you scroll, sections that pin, headlines that assemble line by line. It installs as a Claude Code plugin and also works in Codex or any agent that can edit files, run commands and drive a browser. MIT licensed and free. The value is the rulebook: eight page grammars that exclude each other, a typography and spacing floor, a refuse list (gradient text, fake dashboards, AI-purple gradients), and a fingerprint gate that makes each build differ from your earlier ones on at least 4 of 6 dimensions. A headless browser then checks the finished page for dead scroll and weak contrast. Setup needs Node 18+, a full ffmpeg build and playwright-core. Your own photos and footage cost nothing. Generated images and video bill kie.ai credits on your own key, around 520 for a modest page. Solo builders and small studios: free. Teams: point it at a brand kit and your rules win. The catch: the author says it has only ever been run on Windows. It's also one person's taste turned into hard rules, and it will argue with you about your page.

drama-skills4.1k★

Drama Skills is a ten-skill pipeline for producing AI short dramas and motion comics, the vertical-video serial format that is enormous in China and creeping into Western apps. Hand it an idea or a long source text and it carries the work through episode scripts, visual continuity, storyboards, image and video prompts, generation, and a cut list that renders into a finished film. MIT, Python 3.9 or newer, running inside Claude Code, Codex, or any runtime that supports Agent Skills. The interesting part is where it came from. The team ran a motion-comic studio through more than a thousand projects and roughly 80,000 lines of in-house GUI tooling, then threw the GUI away and distilled the whole line into skills that operate on plain Markdown. Each episode is five files. Confirmation comes before production: prompts land in files first, and the production skill shows you the exact count, references, parameters, and adapter before it executes anything. Anyone producing serialized AI video at volume should look hard at this. Everyone else probably should not. The value is workflow discipline, not any individual prompt, and that only pays off past a certain output rate. Free at every team size. The catch is language and the bill behind the pipeline. Project files are named in Chinese by default and the primary README is Chinese, with the English translation trailing it. The skills are free but the pixels are not: the production step drives external adapters with bundled profiles for Seedance, GPT Image 2, MiniMax video, and MiniMax Music, every one of them billed to your own keys. That confirmation gate exists because those runs cost real money.

onetake4.0k★

onetake is a Claude skill that makes short product launch films, 10 to 30 seconds, in one continuous camera move: every scene grows out of the one before instead of cutting to the next slide. Your agent builds each film as an animated web page, then renders it frame by frame to MP4 with a headless browser and ffmpeg. No video model, no API keys, no Remotion. It is not open source, though. The license is PolyForm Noncommercial. Install is a git clone into your skills folder, then a heavier local toolchain: Python with Playwright and Chromium, numpy, scipy, Pillow and a few more, plus ffmpeg and Node. Optional narration uses local Kokoro text-to-speech and faster-whisper for subtitles. A checker scores whether each shot actually carries into the next and fails renders with uniform pacing or clipped audio. Finals render at 4K60, so expect long renders on a laptop. Hobbyists, students and anyone making a film for a personal project can use it free. Companies can't: a launch video for a product you sell is commercial use, the author offers no commercial license, and the one person who asked hasn't heard back. Vincentwei1021/video-shotcraft covers similar ground under Apache 2.0, with Remotion's own license on top. The catch beyond the license: the public version is deliberately trimmed (a commit removed tuned defaults), the showcase films ship without their source, and an open pull request says the skill's description runs past the spec's 1,024-character limit, which can stop agents from loading it. The project is days old.

sepia3.8k★

sepia is a writing skill that attacks AI tells at the structural layer instead of the word layer. Most humanizers swap vocabulary and shuffle syntax. sepia cites StoryScope, a 2026 study of 61,608 stories, which found a classifier using narrative-structure features alone identifies AI fiction at 93.2% macro-F1 and barely drops when surface style is edited away. So it works on the architecture: narrators who explain the theme, causally tidy single-track plots, emotion rendered only as bodily sensation, no real-world references, endings resolved by growth and acceptance. MIT licensed. It installs as a portable Agent Skill, so any agent speaking that spec can load it, with native plugin packaging verified on Claude Code, Codex, Grok Build and Antigravity. One canonical SKILL.md, no per-platform forks. Four operations: write, review (diagnose only), refactor (minimal edits), and recreate (full rewrite). Professional prose gets its own rule files per venue, covering release notes, PR replies, postmortems, tickets and technical articles. Free with no tiers. Anyone whose drafts come out sounding like a model wrote them gets real value, especially on the professional side where the rules are concrete: answer first, cite file and line, no reflex praise, length proportional to stakes. The catch is that this is a prompt, not a guarantee. It calibrates toward the human distribution rather than inverting the AI one, which is the right instinct, but nothing here beats an actual detector and treating it as a compliance tool would be a mistake.

anything2explainer3.2k★

anything2explainer turns a topic into a narrated motion-graphics explainer video. It is a skill for Claude Code or Codex, not an app: the agent researches with sources, writes the script, generates voiceover, storyboards every shot, then writes each shot as a Remotion component. You get a 720p MP4 with subtitles, chapter cards and a progress bar, in English or Chinese. Setup is real. You need Node 18+, ffmpeg, a Python environment with edge-tts, and kokoro plus espeak-ng for English voices. A 3 to 5 minute film takes about two hours with eight build agents working in parallel, and around 2 GB of disk. It stops at four checkpoints for your sign-off, including a 30-second preview before the full build. Solo creators and educators who want explainers without learning After Effects get a lot here, and every shot is code you can fix one file at a time. Hours of parallel agents also means a real model bill. The same author's video-shotcraft covers product videos under Apache 2.0. The catch is two licenses. The skill is PolyForm Noncommercial, so commercial use needs the author's permission. Remotion underneath needs a paid license, $25/mo per seat, once your company passes three employees.

oil-motion2.9k★

Oil-motion is an agent skill that manufactures scroll-driven web animations using AI video generation. The agent locks keyframes, has a video model fill the motion between them, reviews the frames, and ships a sprite sheet or chroma-keyed MP4 wired to scroll position. At 30% scroll you see frame 30. MIT licensed, but the workflow requires a paid ZenMux API key, so every animation costs real money per generation. Setup is Python, Pillow, and ffmpeg plus the key, and the pipeline expects a human to approve keyframes and review output. The skill's docs are in Chinese, which matters since the agent reads them to do the work. Its own docs draw the right line: for ordinary translation, scale, and rotation, write code; GSAP and Motion do that deterministically and free. The paid generation only earns its cost for what it calls semantic motion, product teardowns and material changes that CSS transforms can't fake. The catch: output is baked at build time, regeneration can drift your product's proportions, and days-old viral projects have no track record. A hand-built GSAP timeline is still the default answer.

huashu-motion2.7k★

huashu-motion turns your coding agent into a launch-video studio. Ask Claude Code or Codex for a 30-second product film and it pitches three directions, builds the film as browser code, writes its own score, then opens an editor where you click a frame and type what to change. It was built to match Anthropic's Claude Motion, a Team and Enterprise beta at launch. This one is MIT and free. Install with npx skills add alchaincyf/huashu-motion, plus Node 22+, Chrome and FFmpeg. No video model, no paid API: code draws every frame and the music is generated locally. The README is Chinese-first with a full English version. Your only bill is model tokens. The author made a 22-second film on DeepSeek V4.1 Flash for ¥1.95 (under 30 US cents). Solo founders and small teams: free, a launch video without hiring a motion designer. Larger teams: good for drafts, a designer still finishes. The catch: it can't hear, so the final listen on the music is yours. No real people or footage, only code-drawn visuals plus your own assets. Quality tracks the model. It's five days old, and Windows renders sometimes come out as zero-byte MP4s.

pixel2motion2.6k★

Pixel2motion takes a static logo and turns it into an animated SVG, through your AI coding agent. Hand it a PNG, JPG, or WebP and it produces a smooth animated vector, an interactive HTML demo, GIF and video previews, and automated checks on the animation quality. It is aimed squarely at brand and logo motion work, MIT-licensed and free. Setup is heavier than most agent skills. The rendering and QA run locally and lean on a real toolchain: Python 3.10+, Pillow, NumPy, and Playwright driving a headless Chrome. So 'install and go' here means installing that stack first. It is also young, around twenty commits, and tied to running inside Claude Code or Codex rather than working standalone. This is for designers and developers who already live in an AI agent and want logo animation without opening After Effects. Solo or team, it is free. Skip it if you do not work inside an agent, or if you only need a single animation, in which case a motion designer or a one-off tool is less setup than standing up Playwright and Chrome. The catch is the toolchain and the maturity. The idea is sharp and the built-in QA step is a nice touch, but you pay for it in local dependencies and early-project rough edges. For polished, hand-crafted brand motion, this is a starting point, not a replacement for a real animator.

holo-card-studio2.1k★

Describe a card and get back a holographic collectible that shimmers as you drag it around the browser. holo-card-studio is an agent skill rather than an app: the agent paints four layers (subject, background, line art, text), builds a Blender scene with parallax and foil and sparkle, exports the geometry, and assembles a Three.js page that rebuilds the same look in the browser. MIT, and the skill itself is just scripts and text. Setup is lighter than it sounds. You need Python with Pillow and Node with npm. Blender it fetches on its own, pulling an official portable build into the project folder and verifying the SHA-256, so nothing lands system-wide. It ships as a Codex skill and leans on the agent's built-in image generation, and its instructions explicitly forbid quietly substituting a paid image API. Solo and hobbyist: this is the fun one. Small teams have real uses, character cards for a game, conference giveaways, onboarding cards for new hires. Large teams: no. The catch: the Blender file and the web page are two separate implementations of one effect. glTF does not carry a custom shader graph, so the Three.js viewer rebuilds it with matching UV math. Edit the materials in the .blend and the page will not follow you.

dimensional-drawing2.1k★

dimensional-drawing turns a UI component into an engineering-style spec sheet. It's two free, MIT-licensed agent skills: one teaches Claude (or Codex, Cursor, Gemini CLI) to measure a card or dialog and draw it like Apple's accessory dimensional drawings, with paddings, gaps, corner radii and layers labeled; the other animates the sheet into a short film of a pen drawing it. Install is a copy into ~/.claude/skills/, or npx skills add enesozturk/dimensional-drawing for other agents. Point it at a component file, Storybook story or screenshot and you get one self-contained HTML file. Dimensions are variables (S1, R2) with value tables, and anything it can't measure is marked [TBD] instead of guessed. The motion skill is tuned for Claude's Motion artifact; the headless path needs Node, Playwright and ffmpeg. Nothing to host and no paid tier; you pay for the agent running it. Solo designers and small teams documenting a design system: free. Larger teams: a handoff artifact that sits next to Figma, not instead of it. The catch: it's one commit from one developer, under a week old. Accuracy depends on your agent actually rendering and measuring the component, so check the numbers before you hand the sheet to anyone.

dream-loop2.0k★

dream-loop makes AI coding agents better at visuals by giving them a picture to aim at. The agent first generates an image of what the finished scene should look like, builds toward it, then a separate critic agent compares a live screenshot against that target and sends notes. It loops until the critic is satisfied. MIT licensed, installed as a skill. Install with npx skills add achimala/dream-loop or clone it into your skills folder. Your agent needs image generation, either built in like Codex or through an API key such as Gemini, plus vision input and ideally subagents. Blender is optional for custom 3D models, and the author prefers the Blender MCP over computer use. Developers building browser games, 3D demos or visually heavy pages get the most from it. The showcase is a Three.js isometric fantasy scene from a one-hour, time-boxed prompt, with a live demo you can click around. The skill is free, but every loop spends image generation and model calls. The catch is testing. The README says it has only been run with GPT-6 Astra in Codex, so on any other agent you are the test case. It is also a new repo from one developer.

beautify-github-readme2.0k★

beautify-github-readme is an agent skill that redesigns your project's README. It reads the actual repository first, works out what the project does and what evidence exists that it works, then builds a page around that: custom SVG title art, a real content hierarchy, and embedded proof. Install with npx skills add oil-oil/beautify-github-readme. MIT licensed. Two modes: a full README redesign, or assets only when you just want a hero image or a diagram and intend to write the copy yourself. The constraint that matters is that it keeps text in Markdown rather than baking it into images, so the README stays searchable and diffable. Plenty of pretty-README templates fail exactly there. Maintainers of small and mid-size open source projects get the most out of this, especially anyone whose README is currently a wall of installation steps. Larger projects usually have design help already. Free, with the cost being whatever agent you run it through. The catch: the entire pitch is that it derives a project-native look rather than stamping one template, and the four sample heroes genuinely do look nothing alike. Whether that holds after a few thousand repos push their READMEs through the same skill and the same model is the open question, and nobody knows yet. Use it for structure and hierarchy, which is where the value sits either way, and give the generated art a hard look before you ship it.

reelmimic1.9k★

ReelMimic copies a video's style, not its footage. Show it a reference clip (a file, a screen recording or a YouTube link) plus a one-line brief, and it breaks down the pacing, shot lengths, colors and transitions, proposes a storyboard for you to approve, then has up to six Claude Code or Codex agents build an original 2D animated video in that style. MIT licensed. It runs locally on Node 22.18+, Python 3.10+, FFmpeg, Chrome and a logged-in Claude Code or Codex CLI. There's no API bill of its own because all the work spends your existing subscription. That's the real cost: a 30 to 60 second video takes 1 to 3.5 hours of agent time. The agents get broad access too: Claude runs with Bash allowed, and Codex defaults to full-access mode with no approval prompts. Solo creators already paying for a top-tier Claude or ChatGPT plan who want explainer or social animations get the most here. Anyone on an entry plan will feel the quota drain. For code-driven video you control line by line, Remotion (remotion-dev/remotion) is the established option, with its own commercial license; HyperFrames (heygen-com/hyperframes) powers ReelMimic's vector engine. The catch: it's a solo project launched in late September 2026 with no releases, tested mostly on Windows, and five of its seven drawing styles are self-described as young. Pulling references from YouTube links via yt-dlp also runs against YouTube's terms, so stick to local files when that matters.

gbro-collage-broll1.9k★

gbro-collage-broll is an agent skill that turns a five-second voiceover line into a matching B-roll clip in an editorial halftone paper-collage style. Clone it into your agent skills directory and it walks a three-gate workflow: confirm the visual metaphor as text, approve a static frame, then generate the video. MIT licensed. Those gates are the design decision worth noting. Video generation is the expensive step, so the skill makes you sign off on the concept and then the still image before it spends anything. Requirements are a Codex environment, a Gemini API key, Python 3.10+, google-genai, and ffmpeg. Gate 2 leans on Codex's built-in image_gen tool for the static frame, so this is a Codex skill first even though it drops into any skills directory. Output is a silent 720x1280 nine-by-sixteen MP4 at 24fps. Solo creators and small video teams producing short vertical content are the audience. The skill itself costs nothing. Google's video generation API is where the money goes, and at five seconds a clip a finished video means a lot of calls, so price that out before you build a workflow around it. The catch: one aesthetic. Halftone paper collage is a strong look and a narrow one, and every clip you make will match every clip anyone else makes with this skill. Output is also silent by design, so audio stays your problem. Useful as one texture in an edit, not as your whole visual language.

reelbench-skills1.2k★

reelbench-skills is a set of three Claude Code and Codex skills for people who work with video. video-shots breaks a finished film into a shot-by-shot table: duration, shot size, camera move, frame description, and rhythm. video-sync composites the footage with that shot data alongside it, switching at every cut. video-scrub rebuilds a file with only picture and sound, leaving GPS, device, and account metadata behind. Apache 2.0 and free. Install is a git clone and one script that symlinks the skills into your Claude Code or Codex skills folder, so a git pull updates them. Requirements are Node 18 or later plus ffmpeg and ffprobe. No npm dependencies and no API keys, because the model work runs on the agent session you already have. ffmpeg does the measuring and the model only makes the judgment calls. Free at every size. Editors, film students, and anyone studying how a video is cut get the most from video-shots, whose output is a single offline HTML report with a player, a pace strip, and a searchable shot list. video-scrub is for anyone publishing footage who does not want to leak where and on what it was shot. The catch: it is one person's project, the primary README is Chinese with an English translation alongside, and the author promotes a paid WeChat community in it. Shot analysis also spends your agent's tokens on every run.

lanshu-animated-architecture-diagram1.0k★

This is a skill for coding agents that turns a JSON spec into a hand-drawn-style architecture diagram, the kind you see in polished technical explainers. Feed it a description of your system and it renders three things at once: an editable Excalidraw file, a static PNG, and an animated GIF with flowing connection lines. It runs locally with Pillow, no external API, no headless browser, and it's MIT licensed. Setup is about as light as it gets. Python and Pillow, no GPU, no Docker, no keys. The AI half runs inside whatever agent you already use, Codex or Claude Code, so the skill itself adds nothing to your bill. It even does a frame-diff check to confirm the GIF actually animates, which is a small touch that shows the author cared. Set your expectations to match the scope. This is a single-author micro-tool with one fixed layout preset and a narrow job: making one specific style of dark-canvas diagram look good. If that's the look you want for a blog post or docs, it's a fast way to get there. If you need flexible diagramming, Excalidraw itself, Mermaid, or D2 give you far more control. Use this when you want the animated explainer aesthetic without hand-placing every box, and nothing more.

handdraw-story-video810★

handdraw-story-video turns a set of 7 to 9 hand-drawn illustrations into a 35 to 45 second vertical video where the line art draws itself in and then fills with color, left to right. It is a real build pipeline you clone and run, not a hosted service. MIT on the code. Setup is the heaviest thing about it. Python 3.10+, Node 18+, FFmpeg, plus HyperFrames and GSAP from npm. You configure a story JSON with your scene data, run a script that extracts line art from your color images, drop the assets into place, then build and render. The render pipeline needs no API keys and no external services, which is unusual in this space right now, though in practice most people will generate the color master images with an image model first. Illustrators and small content teams making short-form vertical video are the fit. The repo root conforms to the Codex Skill structure, so you can install it into your skills directory and trigger it from an agent instead of running the commands yourself. Free at every size, since the only compute is your own machine. The catch: it does exactly one visual effect. Line reveal, then gradual coloring, vertical format, fixed length band. That is a template, and templates go stale fast on the platforms this targets. The MIT license also covers code only, so the fonts, music, and any generated images you feed it carry their own terms.