Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Carefully human hand written llm jailbreaks for the latest models that are available on the market. GPT-6 Astra, GPT-6.1 SoL, Opus 4.7, Opus 4.6, Sonnet 4.6, Haiku 4.5, Deepseek V4, Deepseek Flash, DeepSeek V4.1 Pro / Flash, Qwen 3.8 MAX, Qwen 3.8 Omni-Flash, Qwen 3.7 etc
git clone https://github.com/motan1337/universal-bypass-for-claude-chatgpt-qwen-deepseek-llm-claude-code-codex.git -
MODEL RED MIAU
PromptsSTYLE / AESTHETIC: High-fashion editorial, luxury commercial photography, hyperrealistic 3D render aesthetic, mythological afrofuturism, opulent dark fantasy, perfectly symmetrical composition. SUBJECT: ANATOMY: 1girl…
-
cheap-ag
MCP servers50x your usage with cheap-ag. Opus/Astra plans, a dirt-cheap model writes every line, and tests decide what ships. Your $20 plan stops hitting limits. One MCP server for Claude Code & Codex.
git clone https://github.com/muaaz9329/cheap-ag.git -
javascript-animation-skills
SkillsEvery frame drawn in JavaScript — the Opus 5.5-style animation technique as agent skills: hand-drawn canvas animation, zero image assets, code-synthesized soundtrack, A/V sync check.
git clone https://github.com/iart-ai/javascript-animation-skills.git -
a-fable-of-codexes
SkillsClaude Code skills that make Claude (Fable) the conductor of AI worker fleets: many parallel OpenAI Codex workers plus Opus design agents, organized into campaigns, waves, squads, and review gates.
git clone https://github.com/jvogan/a-fable-of-codexes.git -
UnrealGenAISupport
MCP serversUnreal Engine plugin for LLM/GenAI models & MCP UE5 server. OpenAI GPT-5, Deepseek R1, Claude Opus/Sonnet, Gemini 3, Grok 4, Alibaba Qwen, Kimi, ElevenLabs TTS, Inworld, OpenRouter, Groq, GLM, Ollama, Local, Meshy, Tripo, Hunyuan3D, Rodin, fal, Dashscope, Seedream. NPC AI, agentic, chat, 3D gen, TTS, multimodal, image gen. UnrealMCP/UnrealClaude
git clone https://github.com/prajwalshettydev/UnrealGenAISupport.git -
product-launch-motion
SkillsClaude Code skill for Dribbble-level product launch videos from code. One shape that never cuts, springs, a cursor that drives every change, beat-synced SFX, 60 fps motion blur. v2: use with Claude Opus 5.5.
git clone https://github.com/AbubakrChan/product-launch-motion.git -
claude-opus-4-6-high leads Arena coding at 1535. Anthropic has held #1 for 280 days, but Z.ai.
-
claude-opus-4-5-20251101-high-32k is #49 overall but #14 in coding. gpt-5.6-terra-xhigh is #52.
-
Qwen3.8-Max rates within 30 Arena points of Claude Opus 5.5 for 3.3× less per output token..
-
nativeprompt
PromptsПроверяет промпты и файлы инструкций (CLAUDE.md, AGENTS.md, скиллы) по правилам вашей модели: Claude Fable 5.2, Opus 5.5, Sonnet 5.5, Haiku 5.5, GPT-6 и 6.1, Codex, Gemini CLI. Советует уровень усилий. Каждый совет со ссылкой на документацию вендора. Без API-ключей и зависимостей, офлайн.
git clone https://github.com/edvardgrishin27/nativeprompt.git -
3DSceneRenderer
SkillsPhotoreal first-person tram ride through a procedural city, rendered live in the browser with three.js. Inspired by Jerusalem's Jaffa Road. Built with Claude Opus 5.5.
git clone https://github.com/vladi21k/3DSceneRenderer.git -
Continue and Recap Assistant
PromptsAct as Opus 4.5, a Continue and Recap Assistant. You are a detail-oriented model with the ability to remember past interactions and provide concise recaps. Your task is to continue a previous task or project by: -…
-
premium-saas-web-skill
SkillsAgent Skill (SKILL.md) for Claude Code, Codex, Cursor & Antigravity that builds premium SaaS landing pages: sculpted glows, glass, bento grids, GSAP motion. Before/after tested with Claude Opus 5.5. By Vantle, design & development studio (vantle.studio).
git clone https://github.com/MiddleSugar7000/premium-saas-web-skill.git -
delegate-router
SkillsClaude Code and Codex CLI skill: an LLM router that delegates bulk, already-decided coding tasks to another model you already pay for (GPT via Codex, Gemini via agy, a Claude Opus subagent), on another subscription first. Benchmark-checked routes, cost per task measured on a bench, cross-model review. The host verifies every diff.
git clone https://github.com/pvjbuilds/delegate-router.git -
claude-api
SkillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never…
/plugin marketplace add anthropics/skills
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.