We build a Graph of public Skills
Embeddings + vector search on AI skill graph—but is this a demo or a product you can actually use?

Typed edges in skill graphs let agents traverse knowledge relationships at runtime.
AI agent developers, teams building agent workflows
Cursor · Continue · Sourcegraph Cody
we built a solution
our assumptions: - skills should be easy to manage and share - skills belong together, some need to reference others - harnesses should know how to create, edit, and link together skills, following best practices - harnesses know how to use skills, not other higher abstractions like complex skill graphs - managing skills with your team should be easy
we achieved all that with better skills
website: https://better-skills.dev repo: https://github.com/leonardotrapani/better-skills
Embeddings + vector search on AI skill graph—but is this a demo or a product you can actually use?
Real-time fleet view with heartbeat monitoring, drag-and-drop task kanban, and a unified agent chat paired to a one-click skill store and 80/20 creator split — that combo is useful and not something you see everywhere. Practical execution looks solid from the UI, but the product’s reach depends on OpenClaw adoption and how comfortable folks are exposing gateway URLs and installing third-party skills.
Visual knowledge graph navigation beats pure Q&A, but Cursor already exists.
Markdown knowledge graph replaces scattered PLAN.md files with structured protocol.
Turns PDFs and videos into shareable agent skills—but competitors already exist.
Unified dashboard for Claude Code, Codex, and Hermes when each has different configs.