Joyst

Blog

Ideas on governing AI capability — skills, prompts, agents, MCPs, and secrets.

Blog
Product

What Claude Agent Skills mean for teams

Anthropic donated Agent Skills to the Agentic AI Foundation. What Claude Agent Skills mean for teams that share one skill across several AI tools.

Security

Secrets sprawl in AI teams

Secrets sprawl scatters API keys across chats, env files and agent configs. Store them in a vault and refer by name. Packages never carry values.

Security

Agent credentials without pasting keys

Agent credentials belong in a vault, not in prompts. Packages carry name hints. Controlled substitution is designed to keep values out of model context.