Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
comfyui-h3-editor
SkillsA timeline video editor for MiniMax H3 inside ComfyUI: write shots, render them on your own GPU, cut picture and sound together, or let an agent make the video.
git clone https://github.com/igorls/comfyui-h3-editor.git -
Humanizer
SkillsEdits AI-written text so it reads like a person wrote it, based on Wikipedia's guide to the signs of AI writing.
-
mcode-stack
SkillsThe workflows and skills the MiniMax Code team uses to build MiniMax Code. Open source, install and use.
git clone https://github.com/MiniMax-AI/mcode-stack.git -
awesome-minimax-h3-skills
SkillsMiniMax H3 官方 Skills 的可视化发现与参考站点 · A visual discovery & reference index for the official MiniMax H3 Skills (independent community project)
git clone https://github.com/gordonlu/awesome-minimax-h3-skills.git -
infinite-creation
Skillsinfinite-creation 是一个通过提交小说/剧本,本地ComfyUI-MiniMaxH3+Agent+Skill技能全自动无限生产视频,不限时长。
git clone https://github.com/SwotAtmk/infinite-creation.git -
talking-avatar-video-skill
SkillsTalking avatar video agent skill for Claude Code, Cursor, Codex, Windsurf, Cline & OpenClaw: turn one portrait and a script or voice track into an AI presenter video for explainers, lessons, and product messages. 数字人口播视频 · 照片说话
git clone https://github.com/beatra-ai/talking-avatar-video-skill.git -
awesome-short-drama-skills
SkillsAI 短剧 · 漫剧 Skill(技能包)精选:剧本、改编、分镜、Seedance / 可灵 / MiniMax 视频提示词,千问、豆包、龙虾 OpenClaw、WorkBuddy、Claude Code、Codex 等智能体可用 | Curated agent skills for AI short drama, micro drama / microdrama, vertical drama and manju (AI comic drama): screenwriting, storyboards, Seedance / Kling / MiniMax video prompts
git clone https://github.com/UnderleveledBuilder/awesome-short-drama-skills.git -
auto-edit-workspace
SkillsAI 自動剪輯工作區:放好素材,用白話文跟 Claude Code、Codex、MiniMax Code、Cursor 說「剪乾淨」「做成片」,自動剪 NG、照講稿上字幕、加資訊卡與情境動畫、配音效。Open-source AI video editing workspace for talking-head videos, built on HyperFrames.
git clone https://github.com/dean9703111/auto-edit-workspace.git -
claude-codex-settings
SkillsBattle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.
git clone https://github.com/fcakyon/claude-codex-settings.git -
unslop-ui
SkillsAgent skill that cuts AI tells from interface and chart copy: eyebrow labels, 01/02/03 numbering, botsplaining captions, decorative badges and status dots.
git clone https://github.com/felipebasurto/unslop-ui.git -
viral-video-remake-skill
SkillsViral video remake agent skill for Claude Code, Cursor, Codex, Windsurf, Cline & OpenClaw: break a short video that worked into its hook, beats, and call to action, then rebuild it around your own subject as a shot list, beat frames, narration, and a vertical clip or segmented sources. 爆款视频拆解 · 短视频复刻
git clone https://github.com/beatra-ai/viral-video-remake-skill.git -
Loop
SkillsAn operator desk for self-updating agent skills. track sources, refresh with agents, version every change. Built with Vercel AI Gateway + Sandboxes + Queues.
git clone https://github.com/Kevin-Liu-01/Loop.git -
modlens
SkillsThe first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件,为 DeepSeek、GLM 等纯文本模型外挂视觉能力,粘贴图片即得结构化 JSON 证据(OCR、版面、语义)。
git clone https://github.com/liustack/modlens.git -
claude-code-video-toolkit
SkillsMake videos with Claude Code: script, AI voiceover, music, video clips and render, on open-source models that cost cents
git clone https://github.com/digitalsamba/claude-code-video-toolkit.git -
SkillOpt
SkillsSkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
git clone https://github.com/microsoft/SkillOpt.git -
ru-text
SkillsRussian text quality for AI agents — neuroslop cleanup, typography, information style, editorial standards, UX writing, business correspondence. Scores text 0–10. 2,000+ linguistic atoms.
git clone https://github.com/talkstream/ru-text.git -
AVA
Skills👾 AI-native Visual Analytics framework build for agents.
git clone https://github.com/antvis/AVA.git -
Papermorph
SkillsAn AI skill that turns books into animated, narrated, interactive web experiences
git clone https://github.com/DozenTwelve/Papermorph.git -
GPT-Image2-Skill
SkillsGPT Image 2/2.5 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing
git clone https://github.com/wuyoscar/GPT-Image2-Skill.git -
pr-lens
SkillsThe fastest way to understand code
git clone https://github.com/coldteadotai/pr-lens.git -
anti-slop
SkillsRules for an AI coding agent to filter out generic AI-generated UI designs, text, and code.
git clone https://github.com/miqdadbadjuber/anti-slop.git -
lemo-opuscar
SkillsA toolbox of film styles made in code for Claude Code: 66 ready to use, and your own. Each style is a style prompt plus a demo film made entirely in code by Claude Opus 5.5, with no video model. By Lemomo. · 一套用代码做片的风格工具箱:66 种现成风格,也能做出你自己的
git clone https://github.com/lemomo-ai/lemo-opuscar.git -
ste80-humanizer
SkillsSTE80 Humanizer: agent skill that removes AI tells and rewrites text 80% of the way to ASD-STE100 (Simplified Technical English), the method Andrej Karpathy shared.
git clone https://github.com/Dodaios/ste80-humanizer.git -
agent-vision-toolkit
Skills为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode
git clone https://github.com/Anionex/agent-vision-toolkit.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.