SkillsBench evaluates how well skills work and how effective agents are at using them.
- Stars
- 1.7K
- Forks
- 357
- Pushed
- 25d ago
Compare adoption and maintenance signals without opening every result.
Popular ranks GitHub matches by stars. Switch sort to inspect forks or recent maintenance.
SkillsBench evaluates how well skills work and how effective agents are at using them.
An extensible benchmark for evaluating large language models on planning
Convert a PDDL domain into an OpenAI Gym environment.
Reasoning with Language Model is Planning with World Model
PDDL4J is an open source library under LGPL license whose purpose of PDDL4J is to facilitate the development of JAVA tools for Automated Planning based on PDDL language (Planning Domain Description Language).
A lightweight STRIPS planner written in Python.
[ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples
A beginner's guide to learning, implementing and using PDDL.
No repository description provided.
ChainReactor is a research project that leverages AI planning to discover exploitation chains for privilege escalation on Unix systems. The project models the problem as a sequence of actions to achieve privilege escalation from initial access to a target system.
CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification — COLM 2026
Official release for SkillRevise: trace-conditioned revision of LLM-authored agent skills
PDDL exercises and coursework assignments.
Code for NeurIPS 2024 paper "AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning"
No repository description provided.
No repository description provided.
Large language models for PDDL domains
No repository description provided.
No repository description provided.
ReCAP: Recursive Context-Aware Reasoning and Planning for Large Language Model Agents, NeurIPS 2025
A benchmark library for Dynamic Algorithm Configuration.
Automatic prompt optimization framework for multi-step agent tasks.
Planning Domain Definition Language (PDDL) samples demonstrating VS Code PDDL extension features
No repository description provided.
No repository description provided.
Source for Action Schema Networks paper (AAAI'18)
No repository description provided.
No repository description provided.
No repository description provided.
No repository description provided.