Agent skill for producing threat models for open-source projects

Agent skill that rewrites rough prompts into polished, model-specific prompts — grounded in the official Anthropic prompting guides

Thinking partner skill for AI agents — 150+ mental models, orientation detection, cognitive operations. Works with Claude Code, Cursor, Windsurf, Cline, GitHub Copilot.

Agentic, long-horizon visual generation: a fuzzy story → a cross-model-audited image-based movie. Brings ARIS's research-wiki + multi-agent debate to multimodal generation (intelligence lives in the agent; the diffusion model just renders). Image-based today, video next.

Agent Skill that silently refines prompts for the currently running model

Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.

28 eval-informed mental models and critical-thinking skills for Claude Code, GitHub Copilot, Codex, Cursor, and other Agent Skills-compatible tools

Collection of Claude Skills for DSPy framework - program language models, optimize prompts, and build RAG pipelines systematically

Connect Claude to image generation with Agent Skills. Three levels: a zero-cost code-based design engine, a Three.js 3D renderer, and a real diffusion model on Cloudflare. Plus an AI Storybook pipeline that turns a plain-English story into an illustrated, narrated HTML book.

A universal, industry-neutral taxonomy of cognitive core skills (perception, memory, reasoning, planning, action, verification, learning, governance) for LLMs, SLMs, AI agents, and world models — with schemas, 159 skill cards, benchmarks, and CI.

MIDI Agent Skill is Agent Skills that enables AI models to generate MIDI files from text-based music data. This tool allows for programmatic creation of musical compositions through a standardized interface.

Claude-type skills for institutional equity research — 25 AI agent skills with SEC filings, XBRL financials, earnings calendars, DCF/comps/LBO models, and PPT generation. Powered by agentii.ai data plane. Works with Claude Code, OpenCode, Codex, OpenClaw, Goose.

A Claude Code skill where learning is the goal and building is the test — AI writes the code, you build the mental model.

The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.

From text & real sources to maintainable .drawio architecture models: Diagram IR with source-kind profiles, incremental sync preserving manual layout, multi-view projection, architecture-as-test with a CI action, query/review, what-if, accessible Story Mode, and a built-in MCP server

Agentic coding skills for backtesting trading strategies using VectorBT. Supports Indian, US, and Crypto markets with realistic transaction cost modeling, TA-Lib indicators, QuantStats tearsheets, and 12 ready-made strategy templates.

An awesome Claude skill for structured marketing research system. Covers competitor analysis, avatar profiling, positioning, value propositions, and mental models.

Agent skills for Qdrant vector search: scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage across Python, TypeScript, Rust, Go, .NET, Java

Turn Claude Code into its own Meta-Harness — a skill that evolves the scaffolding around a fixed model (memory, retrieval, context, prompts) via a native propose→score→Pareto loop. Native reimplementation of Meta-Harness (Lee et al. 2026).

C.O.N.T.EX.T is designed to compress complex, multi-domain conversations into machine-optimized "Carry-Packets." These packets achieve a crystallization point of 0.15 entity/token, ensuring that a receiving model can reconstruct the original context with near-perfect fidelity.

Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded in 2025-2026 research on model laziness, underthinking and premature completion.

Kunpeng-Skill is a powerful multimodal distillation toolkit that transforms high-value insights from repositories, websites, UIs, videos, images, and documents into reusable methodologies, model-agnostic regeneration specifications, and more.

94 specialist Blender skills for Cursor, Claude Code, Kiro & Codex -> MCP-powered production pipeline from blockout to engine export.

Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.