← ClaudeAtlas

gaia-auditlisted

Use when the user asks to audit, check, or review a Gaia component (an agent or a skill) against its standard and its live implementation -- "audita este skill", "chequea este agente", "¿está bien esta skill con la implementación?", "¿cómo mejoro este agente?"
metraton/gaia · ★ 3 · AI & Automation · score 76
Install: claude install-skill metraton/gaia
# Gaia Audit The discipline for auditing one Gaia component -- an agent or a skill -- against its type standard AND the live implementation it describes, and returning an enumerated proposal to discuss. The user reaches for this when they point at a single component and ask "how do I improve this? is it still right with the implementation?". The audit reads; it proposes; it does not mutate. The orchestrator enumerates the proposal back to the user, who decides what lands. ## Core principle An audit is worthless if it grades the component against its own claims. The component is a declaration; the value of the audit is anchoring every claim to the **implementation** -- the actual files and symbols the component describes -- and surfacing where the two have drifted apart. Three forces shape it: - **The standard is owned by the creator, not by this skill.** What a *good* agent or skill looks like lives in `agent-creation` (for agents) and `skill-creation` (for skills). Load the creator for the component's type before judging it; this skill carries the audit cycle, not the type standard. - **Claims anchor to symbols, or they are unverified.** A reference to a field, module, table, or function is real only if it exists by that name in code (`activate_db_pending_by_prefix`, `_is_protected`), not by a line number that drifts on every edit. Hunt phantom references, dead instructions, and schema/contract drift by opening the implementation and matching symbol-for