Skillkit
The package manager for AI agent skills
301 followers
The package manager for AI agent skills
301 followers
The universal skill platform for AI coding agents. Auto-generate instructions with Primer, persist learnings with Memory, and distribute across Mesh networks. One CLI for Claude, Cursor, Windsurf, Copilot, and 28 more.
Skillkit
Hey Product Hunt! 👋
I'm Rohit, the maker of SkillKit.
The problem I kept running into: My skills for Claude Code were useless in Cursor. My team was on Copilot. Each agent has its own format. Worse: every time I close a session, my AI forgets everything it learned.
So I built SkillKit - a universal platform for AI coding agents that goes way beyond skill management.
What makes it different from "skill installers":
🔄 Cross-Agent Translation (32 agents)
One command. Write once, use in Claude Code, Cursor, Codex, Windsurf, Copilot, Gemini CLI, and 26 more.
🧠 Session Memory That Persists
Your AI agents learn patterns, but that knowledge dies every session. SkillKit captures learnings with semantic embeddings and makes them persistent:
🤖 Multi-Agent Team Orchestration
Spawn teams of AI agents with leader/teammate hierarchies, task assignment, plan approval workflows, and code review stages:
🌐 Mesh Network for Distributed Teams
Your agents can communicate across machines with E2E encrypted P2P:
- Ed25519 cryptography & XChaCha20-Poly1305 encryption
- UDP multicast LAN discovery
- Trust management with fingerprint verification
🎯 AI-Powered Recommendations
📚 Built-in Methodology Packs
TDD, Design-First, Root Cause Analysis, Structured Review - battle-tested development methodologies baked in.
More Features:
- 🧪 Skill Testing Framework with assertions
- 🔧 Auto-generate CI/CD configs (GitHub Actions, GitLab CI)
- 🌳 Hierarchical skill taxonomy with tree navigation
- 📡 Self-host your skills (RFC 8615 well-known URIs)
- 🔌 Plugin system for extensions
- 📊 Quality scoring and security audits
This is for you if:
- You switch between AI coding agents
- Your team uses different tools
- You want your AI to actually remember and learn
- You're building multi-agent workflows
- You want enterprise-grade skill management
Fully open source.
Website: agenstskills.com | Docs: agenstskills.com/docs
I maintain about 15 Claude Code skills for my daily workflow and the portability problem is real. Right now if I want the same behavior in Cursor I'm manually rewriting CLAUDE.md into .cursorrules. The translate command would save me a lot of time.
Curious about the memory feature -- how does it handle conflicting patterns across projects? Like if I have one repo that uses snake_case and another that uses camelCase, does it scope learnings per-project or is it global?
Skillkit
This looks promising! How does Skillkit handle versioning and dependency management for agent skills? Would love to learn more about the workflow.
Skillkit
Skillkit
The cross-agent translation for 32 agents is impressive. I use Claude Code daily and switching context between tools is painful. Curious about the Primer feature — how does auto-generating instructions work in practice? Does it analyze your codebase patterns and suggest skill definitions, or is it more template-based? Also, for team scenarios where different members use different agents (Claude Code vs Cursor vs Copilot), how does skill synchronization work across the mesh network?
Skillkit
That's exactly what I was hoping to hear. Local analysis without external dependencies is the right approach for developer workflows. Looking forward to trying it with my Claude Code setup.
Every time I onboard a new team member, I end up exporting my Claude Code skills as a markdown dump and manually reformatting for whatever agent they picked. Cross-Agent Translation across 32 agents solves the distribution problem. Session Memory is the part I want to stress-test... semantic embeddings sound right, but the failure mode is usually recall quality degrading as the memory store grows. Compression strategy matters a lot there.
Skillkit
@piroune_balachandran That's why you need skillkit
@rohit_ghumare Ha, fair. So with Skillkit Memory, once the semantic store hits a few hundred sessions, embedding drift and stale context blending start creeping in. A pruning or decay layer on top of compression would make recall stick long-term.
Hi Rohit - great to see this launch! The idea of a package manager for agent skills makes a ton of sense given the fragmentation on tooling, and I can easily see how safety/scanning and cross-team mesh sync jump out as areas where a lightweight provenance layer could help. One concrete opportunity I had in mind is signed skill releases plus verifiable attestations (e.g., malware scan/sandbox/CI checks) surfaced right in the CLI before install, so teams can trust what they’re pulling; might also be fun to play around with community-owned registries for this. If you're planning to support paid/private skill packs, there’s also a path to global subscriptions and creator payouts (card + stablecoin options) without changing the core developer workflow. Happy to chat further on this and share a few practical patterns we’ve seen work for registries/marketplaces!