Agent pack · Skills bundle
TypeSafe Agent Skills
One Agent Skills document that tells a coding agent how to design and write software against TypeSafe's System One API, shipped with the Claude Code plugin and marketplace manifests that install it.
- Steward
- TypeSafe AI (typesafe-ai)
- Hosts
- Claude Code
- Install
- Host marketplace
- Licenses
- MIT License
- Status
- Active
- Installs
- One skill directory, skills/typesafe-ai/, holding one SKILL.md and a copy of the licence. Two manifests under .claude-plugin/ wrap it for Claude Code: marketplace.json names one plugin, typesafe, whose source is the repository root, and plugin.json gives that plugin a version and declares no commands, agents, hooks, or servers, so Claude Code discovers the single skill from the skills/ folder and offers it as /typesafe:typesafe-ai. The README installs it with claude plugin marketplace add typesafe-ai/skills followed by claude plugin install typesafe@typesafe-ai. It also gives npx skills add typesafe-ai/skills --skill typesafe-ai for other agents and says to select an agent when prompted; that names no host and documents no host-specific install, so only Claude Code is recorded. The skill's text points the agent at TypeSafe's live documentation index and cookbooks and describes the three question types and how to compose them; it carries no reference files of its own.
Open in the directory → Open repository ↗
Editorial ratings appear in the directory beside the profile they belong to and are never compared across collections.