Launching today
Skillbox
One library for your AI skills, synced to every agent
53 followers
One library for your AI skills, synced to every agent
53 followers
Skillbox keeps your AI skills in one library and syncs them to Claude Code, Cursor and Codex. Follow GitHub sources, review diffs, and scan each version for prompt injection. Trim shortens noisy command output so sessions last longer.
Free Options
Launch Team / Built With
LoomShow, don't just tell with Loom
Promoted
Hi Product Hunt, I'm Adenekan Wonderful, the maker of Skillbox.
I built this because my AI skills were everywhere. A few lived in GitHub repos, some sat inside project folders, and some were installed for Claude Code but missing from Cursor. A better version of one would turn up and I'd have no idea. Copying files was easy. Knowing what I had, where it came from, whether it had changed, and whether it was safe was the hard part.
So Skillbox does four things:
One library, and a smaller active set. Keep everything you've collected, and deliver only what each tool or project needs. Every skill your agent loads costs context, so we don't treat "saved" as "installed".
Sources stay attached. Skills added from GitHub or GitLab keep following their source. When one changes, you see the diff and decide whether to take it.
Trust, per version. Each version is scanned for prompt injection, data exfiltration, command injection, hardcoded secrets and obfuscated code, including by Cisco's Skill Scanner. Approval is tied to the exact content that was reviewed, so it doesn't carry over silently when a skill changes. A passing check is evidence, not a guarantee.
Trim. It shortens noisy test, git and build output before your agent reads it. The full output stays one command away, and your sessions last longer.
It syncs across Claude Code, Cursor and Codex. Trim currently covers more than that, but session insights are deepest on Claude Code.
There's a permanent free plan for the library, sync, updates and Trust. Trim and AI features are on Individual, with a 7-day trial.
I'd love to hear how your skills are scattered today, and what would make you trust a skill you didn't write. I'm here all day and will reply to everything.
We have one skill that only makes sense in one repo, it's about our deploy scripts. Can I keep it active there and nowhere else?
We publish skills for coding agents, and besides the skill files, each agent wants the MCP server the skills use declared in its own way: Claude Code with "type": "http", Cursor with just the address, Codex with "streamable-http" in an mcp.json.
Does Skillbox carry a skill's server entry across tools, or only the skill files?
Thanks for the comment, @philippstaudt not today. Skillbox syncs a skill’s files to each tool, but it doesn’t carry the skill’s MCP server entry across tools.
The only MCP config Skillbox writes is its own control-plane server, “skillbox”. It writes that one in each tool’s own format: "type": "http" for Cursor and Claude Code, a [mcp_servers.skillbox] TOML table for Codex, and so on. It doesn’t read a server declaration from a skill and write it out for each tool. The docs also treat MCP install as separate from file delivery.
So for now, keep documenting the per-tool server setup in the skill’s README or SKILL.md. A skill-level server declaration that Skillbox translates per tool would be a new feature, not something it already does.