typesafe-ai ships open-source agent skills pack bringing typed decision loops to Codex, Cursor and Claude Code
multiply_matrix · x · 2026-09-20
typesafe-ai/skills is an open-source skill pack for TypeSafe's System One API that plugs into Codex, Cursor, Claude Code and other agents, giving them typed decide, tool and evaluate loops (1000 GitHub stars).
- Install: claude plugin marketplace add typesafe-ai/skills for Claude Code, or npx skills add typesafe-ai/skills --skill typesafe-ai for other agents (project-local by default, -g for global).
- Usage: prompt your agent directly, e.g. "Use TypeSafe to route support tickets by department with human review for uncertain decisions"; invoke via /typesafe:typesafe-ai in Claude Code.
- MIT-licensed; the skill guides agents through workflow design, docs/cookbooks, and composing typed judgments in code.
More from coding & agent
- Elvis Saravia auto-curates an 'Awesome Jev Collection' of trending use cases — omarsar0 · 2026-09-21
- 'Agent Experience' emerges as a new UX theme: some of your users are agents now — YvesMulkers · 2026-09-21
- Anacondahood launches: Python research, AI agents and trading workflows in one env — teoliphant · 2026-09-20
- Dev Uses Computer-Use Agent to Install/Uninstall 300+ Mac Apps, Adds 90 Cleanup Rules — vista8 · 2026-09-20
- carter-mcp: open-source MCP server that builds native iOS UIs via AI agents — Voyager_Ten · 2026-09-20
- Spotify ships Xirp, a Mac app born from 36,000 AI coding sessions — shashib · 2026-09-20