Menú
Assemble a dashboard-ready snapshot from the canonical state.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
| name | dashboard-snapshot |
| description | Assemble a dashboard-ready snapshot from the canonical state. |
Goal:
Inputs:
CoScientistStaterun_idupdated_atOutputs:
dashboard/SNAPSHOT.jsonContext Loading:
skills/shared-references/artifact-contract.md so the dashboard artifact stays downstream of canonical run artifacts.packages/dashboard_contracts/snapshot_projection.py before rebuilding dashboard/SNAPSHOT.json.packages/dashboard_contracts/dashboard.py when the dashboard-facing snapshot field layout needs to be checked.Execution Contract:
from tools import build_dashboard_snapshot.packages/dashboard_contracts/snapshot_projection.py.Execution Steps:
skills/shared-references/artifact-contract.md, then read packages/dashboard_contracts/snapshot_projection.py.dashboard/SNAPSHOT.json.Completion Rule:
dashboard/SNAPSHOT.json has been rebuilt from canonical state through the shared deterministic builder surface.Run the full Co-Scientist pipeline for one research run.
Evaluate whether a hypothesis newly entered the current top-k set and update the convergence counter deterministically.
Choose exactly one concrete evolution strategy for the active evolution round.
Run the assumption decomposition and deep verification review for a hypothesis.
Run the iterative evolution loop from the current persisted run state until convergence.
Generate exactly one child hypothesis that improves logical coherence, causal consistency, and assumption hygiene.