Provides a structured, industry-neutral taxonomy for AI agent capabilities, complete with schemas, benchmarks, and contribution workflows, addressing both text-based and human-action skills.
Cognitive core skills are the mental operating capabilities an LLM or AI Agent needs to move from chat response to useful digital co-worker. An LLM predicts and generates language. An AI Agent wraps that LLM with memory, planning, tools, integrations, verification, and action control so it can pursue goals inside real workflows.
Cognitive core skills are the agent operating brain: perception to know the situation, memory to preserve continuity, reasoning to judge, planning to sequence work, action selection to execute, verification to confirm progress, learning to improve, and governance to stay safe.
This repository contains a universal, industry-neutral taxonomy package for:
docs/cognitive-core-skills/.data/.Skills/index.md.1.0.015913Skills/: 159 skill cards plus Skills/index.md| System type | Primary strength | Typical limitation without augmentation |
|---|---|---|
| LLM | Broad language understanding, synthesis, reasoning, drafting | Weak continuity and no autonomous bounded action by default |
| SLM | Low-latency, low-cost, private, constrained inference | Narrower transfer and lower open-domain dept |
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.
Similar projects matched by category, topics, and programming language.
Clodex is an open-source, local-first agentic IDE that combines persistent AI tasks, code, terminal, browser, Git, models, memory, and governed execution in one Electron workspace, currently in technical preview.
OpenClaude is an open-source CLI coding agent that runs on any platform and supports a wide range of LLM providers, offering the same tools and workflows as Claude Code.
Ponytail is a plugin for AI coding agents that enforces a disciplined ladder of reuse before writing code, reducing code volume by roughly 54% while preserving safety.