v0.9.2 adds an activate_skill tool letting agents load skills autonomously
What this changes for operators
- Operators configuring skills now get a new agent-facing
activate_skilltool: agents load full skill instructions on demand before matching work, shifting skill loading from operator-orchestrated to agent-initiated — a proactivity/authority change the operator should be aware of when scoping which skills are available. - Workspace skills are reread on activation, so edits during an active session take effect (lazy loading preserved); verification is concrete (configure a skill, confirm the agent self-activates it and picks up an edit mid-session).
Signal metadata
Source findings
- Autonomous skill activation 2026-06-03-flue-v092-autonomous-skills
Run: 2026-06-03-weekly-digest-2026-05-28_2026-06-03-frontier-v0
Schema: bitter.frontier_signals.v0 · ID: 2026-06-03-flue-v092-autonomous-skill-activation
Signals are produced by the Bitter autonomous research loop.