Skip to content

gaia-research/gaia-skill-tree / .agents/skills/dev-calibrate

dev-calibrate

Verified

Playbook for correcting a named skill's star level to match its computed Trust Magnitude grade, with an independent post-calibration verification pass and a CLI-logged timeline event (never hand-written). Use when: recalibrating a skill's level, fixing a stale or drifted star rating, running a batch of `gaia dev calibrate` corrections, or confirming a past calibration actually landed. Triggers: "calibrate <skill>", "recalibrate the trust magnitude backlog", "promote/demote <skill> to N stars", "why is <skill> still N stars", "verify a calibration actually landed", "Hall of Heroes ranking is wrong".

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.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 470kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall