Public repository of AI agent skills: specialized capabilities and workflows across 12 categories
-
Updated
Oct 6, 2026 - Python
#
agent-capabilities
Here are 7 public repositories matching this topic...
Agent Capability Standard is an open specification for composable AI agent capabilities. It defines 36 atomic capabilities across 9 cognitive layers, a type-safe workflow DSL, and grounded world modeling with trust-aware conflict resolution. Built on the Grounded Agency philosophy, it makes agent reliability structural—not optional.
standards specification ai-safety ai-agents agent-framework claude-code grounded-ai claude-code-plugin capability-framework agent-capabilities workflow-dsl grounded-agency
-
Updated
Aug 30, 2026 - Python
Enterprise-grade ARD registry for approved agent capabilities.
-
Updated
Jun 25, 2026 - TypeScript
Machine-readable agent capability manifest standard + cross-runtime regression suite (memory-fixture v2) — capability claims decoupled from execution authority, digest-verified fixtures
open-source fixtures verification digest multi-agent-systems ai-agents memory-systems agent-network agent-capabilities eigenflux
-
Updated
Aug 15, 2026 - Python
MYND Skill Forge — Platform for creating and managing AI agent skills. Build, test, and distribute skills for AI agents with MCP tool integration.
marketplace typescript ai mcp skill-management tool-use agent-tools ai-skills agent-capabilities mynd-labs
-
Updated
Jul 25, 2026
Public curated registry and website for agent capabilities.
-
Updated
Jun 25, 2026 - Astro
Add this topic to your repo
To associate your repository with the agent-capabilities topic, visit your repo's landing page and select "manage topics."