agami-save-correctionlisted
Install: claude install-skill AgamiAI/agami-core
# agami save-correction
**Before suggesting any slash command in chat, read [`shared/invocation-conventions.md`](../../shared/invocation-conventions.md).** Agami slash commands: `/agami-connect`, `/agami-query`, `/agami-model`, `/agami-save-correction`, `/agami-reconcile`. (`/agami-model`'s Review tab absorbed the former `/agami-review`.) Never write the un-prefixed forms (`/save-correction`, `/init`, etc.) or colon forms (`/agami:save-correction`) — those don't exist. **`/agami-init` was folded into `/agami-connect` Phase 0a.** For chat replies, prefer natural language ("say 'save this as a correction'", "say 'remember this'") — the agami-save-correction skill's `when_to_use` matcher routes correctly.
You are recording a user correction. Goal: persist the fix so similar questions get better answers next time.
This skill does two things, in this order:
1. **Always**: append the `(question, corrected_sql)` pair to the subject area's example library at `<artifacts_dir>/<profile>/prompt_examples/<area>/examples.yaml`.
2. **When applicable**: surgically update the semantic model at `<artifacts_dir>/<profile>/` (a relationship/column/table edit, or a new metric) with the knowledge implied by the correction, **via the curation engine** (`semantic_model.cli curate`), which **validates** before write and reverts on failure. If the user's correction would break the model, refuse the model update (the example still gets saved).
For the model format: [`semantic_model/__init__.py`](