Sklm: A CLI tool for centralizing and syncing AI agent skills across projects
By
Victor BEYSSERIAT
Summary
Sklm is a CLI tool that centralizes, scopes, and syncs skills (SKILL.md files) for AI agents. It solves the problem of managing skills across multiple AI agents by providing a global store while allowing per-project scoping, without cluttering agent configurations. The tool supports multi-agent setups, registry discovery, and auto-syncing, and was built as a weekend project by a developer frustrated with existing skill management workflows.
Source
Product HuntSklm: A CLI tool for centralizing and syncing AI agent skills across projectsproducthunt.comKey quotes
· 3 pulledI was fed up with collecting skills across all my agents, which was cluttering up my list in my projects.
So I switched to installing them on a project-by-project basis, but I also got tired of having to remember which skills I'd used previously.
So I coded a tool this weekend, in the form of a CLI.
You might also wanna read
OpenClaw-Skill: A Collective Skill Tree Search Framework for LLM-Based AI Agents
A new research paper introduces OpenClaw-Skill, a Collective Skill Tree Search (CSTS) framework that addresses key limitations in LLM-based
clawbeat.co·2d ago
Skillfile: Declarative Management Tool for AI Skills and Agents Across Coding Platforms
Skillfile is a tool for managing AI skills and agents declaratively, similar to package managers for software dependencies. It allows develo
github.com·3mo ago
Skill-MAS: A Meta-Skill Approach to Improving Multi-Agent Systems Without Retraining
Skill-MAS proposes a novel approach to LLM-based automatic Multi-Agent Systems (MAS) generation that bridges the gap between inference-time
arxiv.org·2d agoSkill-MAS: A Meta-Skill Approach to Improving Multi-Agent Systems Without Retraining
Skill-MAS proposes a novel approach to LLM-based automatic Multi-Agent Systems (MAS) generation that bridges the gap between inference-time
arxiv.org·2d ago
SkillsBench: A Benchmark for Evaluating AI Agent Skills Across Diverse Tasks
SkillsBench is a new benchmark for evaluating how well AI agent skills work across diverse tasks. The benchmark includes 86 tasks across 11
arxiv.org·4mo ago
Claude Code Skills Adopt Standardized SKILL.md Format for GitHub-Based Agent Management
The article discusses the emergence of a structured GitHub mapping system for Claude Code skills, where a `SKILL.md` file within a dedicated
clawbeat.co·2d ago
Agent Skill Studio: A Model-Agnostic Platform for Building Universal AI Skills
Agent Skill Studio is an open, model-agnostic platform that enables developers to create reusable AI agent skills that work across multiple
claudeskills.cc·8mo agoComments
Sign in to join the conversation.
No comments yet. Be the first.