SkillX: Automatically Constructing Skill Knowledge Bases for Agents

Declarative management of Agent Skills on Nix

Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning

SkillOpt 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.

A Python framework for modular, self-contained skill management for machines.

This package implements Agent Skills (https://agentskills.io) support with progressive disclosure for Pydantic AI. Supports filesystem and programmatic skills.

A framework for discovering, compiling, and validating reusable skills for scientific agents.

Agent Skills implementation for Strands Agents SDK

AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution

Open-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no target-task supervision. (Code coming soon.)

The first open-source agent skills builder. Define skills by vibe workflow, run on Claude Code, Cursor, Codex & more. Build Clawdbot 🦞· APIs for Lovable · Bots for Slack & Lark/Feishu · Skills are infrastructure, not prompts.

[ICML 2026] Meta Context Engineering via Agentic Skill Evolution

Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support

AI agents and Nix: parametrable skills/instructions and tools, packaged together in a reproducible and modular fashion

Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.

Typed React command-center components, live examples, and a portable coding-agent skill.

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.

OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

Java AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java26. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.

Compound Engineering Framework for Alpha Feature Research in Quant Finance

Fluent argument validation for fluent software development.

AtlasClaw is an enterprise agent framework supporting mutliple users and multi system integration.

LLM agents as your hyperparameter optimizer.

Connect AI agents across any network — zero config, encrypted, skill-based routing