dev-calibrate

Overview

This playbook corrects a named skill's stored star level when it has drifted from
its computed Trust Magnitude grade. The objective is not just to run
gaia dev calibrate — it is to make the correction provable: a pre-flight
snapshot, an explicit promote/demote/no-change/blocked decision against the G7
mapping, the CLI-driven mutation itself (which alone appends the timeline event —
never hand-write it), and an independent re-inspection afterward that confirms the
stored level actually changed, rather than trusting the calibrate command's own
stdout.

Batch use

For a backlog of N skills, repeat snapshot-target through verify-landed once
per skill_id. rebuild-docs and verify-docs-clean are expensive registry-wide
rebuilds — run them once at the end of the batch, not after every individual
skill. This is an efficiency note only; it does not change the per-skill spine or
its proof obligations.

Reference

• founder/steward/PLAYBOOKS.md — the playbook contract this file opts into.
• python3 scripts/inspectTrustMagnitude.py --leaderboard — finds calibration
  candidates in bulk by ranking all named skills by Trust Magnitude.