Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Verifies that a recorded DecisionRecord still holds — baseline-vs-measure evidence loop with drift detection per FPF Evidence Decay. Make sure to use this skill whenever the user asks "did dec-X work", "is decision Y still valid", "did the prediction come true", "check if the migration held", "is X stale", "measure that decision against reality", "did we actually fix Z", "is our caching decision still right" — or whenever a shipped decision needs a post-implementation reality-check before furthe
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -63% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -61% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -27% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -66% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -68% | 0% |
When an FPF evidence or validity distinction is material, inspect a known SourceID/UnitID with haft_query(action="fpf", mode="inspect", identifier="..."), or query the exact concern and inspect the direct pattern body. Retrieval is not evidence or a verdict.
Recover the exact record and its claims, thresholds, validity window, and planned evidence. Gather current evidence, state context transfer and expiry, and attach it with haft_decision(action="evidence", ...). Surface weakened, refuted, stale, or drifted claims honestly. Any rebaseline, supersede, deprecate, or reopen mutation requires explicit operator action.
Other measured skills in the registry, with their headline benchmark lift.