Library
86,689 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
mcp
MCP serversAuthorize consequential AI agent actions before execution
@decionis/mcp@0.6.0 -
Actenon Kernel
MCP serversVerify consequential AI actions before they execute.
actenon-kernel@1.2.1 -
TwitterAPIs
Public APIsTwitter / X data API: search, profiles, timelines, followers, DMs, write actions
-
Qwen2.5-7B-Instruct
Modelstext generation model by Qwen · transformers
Qwen/Qwen2.5-7B-Instruct -
NeoHorse-1-4B
Modelstext generation model by TokenRhythm · transformers
TokenRhythm/NeoHorse-1-4B -
Act as a cinematic environment designer who writes image-ready and motion-ready scene briefs. Help me design one hero shot of a vintage steam train crossing a tall stone railway viaduct over a river valley, which will…
-
Act as a cinematic environment designer who writes image-ready and motion-ready scene briefs. Help me design one hero shot of a lantern-lit river running through a historic Vietnamese old town at dusk, inspired by the…
-
Act as a cinematic landscape designer who writes image-ready and motion-ready scene briefs. Help me design one hero shot of a small white wooden church with a red roof standing on a grassy headland above an Icelandic…
-
Act as a cinematic landscape scene designer who writes image-ready and motion-ready scene briefs. Help me design one hero shot of dozens of colorful hot-air balloons rising over the fairy chimneys and rock pinnacles of…
-
cifar10
Datasets & benchmarksHugging Face dataset by uoft-cs
uoft-cs/cifar10 -
dissect
SkillsReverse-engineer any video (YouTube, TikTok, Reels, X...) into a reusable blueprint for making similar videos. A Claude Code skill.
git clone https://github.com/0xpratzyy/dissect.git -
RuiC-pixel-explainer
Skills像素游戏化讲解片生成产线(Agent Skill):给一段口播文案,产出 1920×1080/30fps 的像素 RPG 讲解短片。角色分两条路线——有生图用参考图生成 4×4 透明动作表与半身表情,没生图直接代码绘制半身+Q 版小人;章节轨 + 单行字幕 + 语义组件,逐帧导出、逐帧可复现
git clone https://github.com/HRuiCcc/RuiC-pixel-explainer.git -
bloom
Modelstext generation model by bigscience · transformers
bigscience/bloom -
falcon-40b
Modelstext generation model by tiiuae · transformers
tiiuae/falcon-40b -
Qwen3-8B
Modelstext generation model by Qwen · transformers
Qwen/Qwen3-8B -
easyeda-agent
MCP servers嘉立创EDA专业版(EasyEDA Pro)自动化:给 AI harness 装上画板的「手」—— 一套 typed 原理图/PCB 动作,CLI / Agent Skill / stdio MCP 三形态融合接入。承接嘉立创「不以卖板赚钱,以培养中国工程师为己任」 | EasyEDA Pro automation: the hands of your AI harness — typed schematic/PCB actions via CLI, Agent Skill and stdio MCP.
git clone https://github.com/zhoushoujianwork/easyeda-agent.git -
edit-reel
SkillsClaude skills that edit your reels for you: karaoke subtitles in any language, retakes and silence cut, zooms, SFX. I haven't edited a video by hand in 8 months.
git clone https://github.com/artemisln/edit-reel.git -
ElevenLabs
MCP serversElevenLabs MCP server: TTS, music, sound effects, voices, and audio transcription
@mindstone/mcp-server-elevenlabs@0.7.0 -
dvlt
Modelsimage to 3d model by nvidia · dvlt
nvidia/dvlt -
autonomous-dev-team
SkillsTurns issues into merged PRs/MRs with zero human intervention — supports GitHub and GitLab, and Claude Code, Codex CLI, Kiro CLI, Antigravitiy CLI, opencode, and other agent CLIs.
git clone https://github.com/zxkane/autonomous-dev-team.git -
claude-image-gen
SkillsAI-powered image generation using Google Gemini or OpenAI (gpt-image-2), integrated with Claude Code via Skills or Claude.ai via MCP (Model Context Protocol).
git clone https://github.com/guinacio/claude-image-gen.git -
Llama-2-7b-hf
Modelstext generation model by meta-llama · transformers
meta-llama/Llama-2-7b-hf -
DeepSeek-V4-Flash-0731
Modelstext generation model by deepseek-ai · transformers
deepseek-ai/DeepSeek-V4-Flash-0731 -
claude-skills
Skills13 Claude Code skills for video production (transcribe / translate / dub / multicam / subtitles / reframe) + WeChat publishing. Compatible with Claude Code, OpenAI Codex CLI, Cursor, Gemini.
git clone https://github.com/jianshuo/claude-skills.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.