Loading
Run bounded, evidence-backed improvement experiments with fixed evaluators, repeated baselines, protected confirmation, budgets, and recovery.
npx skills add Reactive-Skills/skills --skill experiment-loopnpx -y @reactive-skills/axi invoke experiment-loop17
Hierarchical nodes
INIT
Bootstrap entrypoint
0
Whitelisted for safety
3
Automated projections
Visual state machine topology parsed directly from the official STATECHART.md in Reactive-Skills/skills:
Each state is an isolated operational slice. Transitions occur only when typed signals satisfy programmatic guard conditions.
Operational state INIT
Outgoing Transitions
Operational state ACTIVE
Outgoing Transitions
Operational state ACTIVE.INTAKE
Outgoing Transitions
Operational state ACTIVE.CONTRACT
Outgoing Transitions
Operational state ACTIVE.CALIBRATE
Outgoing Transitions
Operational state ACTIVE.BASELINE
Outgoing Transitions
Operational state ACTIVE.TRIAL
Outgoing Transitions
Operational state ACTIVE.TRIAL.DIAGNOSE
Outgoing Transitions
Operational state ACTIVE.TRIAL.PROPOSE
Outgoing Transitions
Operational state ACTIVE.TRIAL.RUN
Outgoing Transitions
Operational state ACTIVE.TRIAL.ASSESS
Outgoing Transitions
Operational state ACTIVE.CONFIRM
Outgoing Transitions
Operational state ACTIVE.FINALIZE
Outgoing Transitions
Operational state PAUSED
Outgoing Transitions
Operational state COMPLETE
Operational state BLOCKED
Operational state BYPASS_DETECTED
Inspect or drive this state machine directly via the token-efficient AXI CLI:
Check state:
Inspect hierarchy:
Tail events:
Read models automatically rendered upon transition:
Add to your Claude Desktop, Cursor, or VS Code settings:
{
"mcpServers": {
"reactive-skills": {
"command": "npx",
"args": [
"-y",
"@reactive-skills/axi",
"mcp"
]
}
}
}