agami-save-correction
starsforks
How to install agami-save-correction?
agamiai/agami-core/agami-save-correction
$npx -y skills add AgamiAI/agami-core --skill agami-save-correctionSaves a user correction so future queries learn from it. Always appends a (question, corrected_sql) pair to the subject area's example library under <artifacts_dir>/<profile>/prompt_examples/<area>/. Additionally, classifies the correction and — when applicable — applies a surgic
SKILL.md
| 1 | # agami save-correction |
| 2 | |
| 3 | **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. |
| 4 | |
| 5 | You are recording a user correction. Goal: persist the fix so similar questions get better answers next time. |
| 6 | |
| 7 | This skill does two things, in this order: |
| 8 | |
| 9 | 1. **Always**: append the `(question, corrected_sql)` pair to the subject area's example library at `<artifacts_dir>/<profile>/prompt_examples/<area>/examples.yaml`. |
| 10 | 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). |
| 11 | |
| 12 | For the model format: [`semantic_model/__init__.py`](../../../../packages/agami-core/src/semantic_model/__init__.py) (layout) + `packages/agami-core/src/semantic_model/models.py`. The curation engine is `packages/agami-core/src/semantic_model/curate.py`. |
| 13 | For SQL safety: [`shared/sql-generation-rules.md`](../../shared/sql-generation-rules.md). |
| 14 | For dialect rules: [`shared/dialect-rules.md`](../../shared/dialect-rules.md). |
| 15 | For DB error classification: [`shared/db_error_classifier.md`](../../shared/db_error_classifier.md). |
| 16 | |
| 17 | --- |
| 18 | |
| 19 | ## Phase −1: Plan-mode check |
| 20 | |
| 21 | Run the detection + ask logic from [`shared/plan-mode-check.md`](../../shared/plan-mode-check.md). agami-save-correction needs Write (examples + model edits) and Bash (EXPLAIN-validation) — both are blocked in plan mode. |
| 22 | |
| 23 | **If plan mode is active and the user picks `Stay in plan mode` (or this skill is invoked under an active plan-mode context):** refuse and end the turn. **DO NOT write a plan file. DO NOT call `ExitPlanMode`.** Refusal text (verbatim): |
| 24 | |
| 25 | > I can't save corrections in plan mode — switch to **Auto** or **Edit Automatically** mode (Shift+Tab to cycle) and re-invoke. The correction won't persist otherwise. |
| 26 | |
| 27 | If plan mode is not active, skip this phase silently and go to Phase 1. |
| 28 | |
| 29 | --- |
| 30 | |
| 31 | ## Phase 1: Identify the correction |
| 32 | |
| 33 | ### 1a — resolve the active profile and artifacts_dir |
| 34 | |
| 35 | Resolve `<profile>` in this order: `AGAMI_PROFILE` env var → `active_profile` field in `<artifacts_dir>/local/.config` → literal string `"default"` (legacy fallback). |
| 36 | |
| 37 | Resolve `<artifacts_dir>` per [`shared/file-layout.md → Configuring artifacts_dir`](../../shared/file-layout.md#configuring-artifacts_dir): `AGAMI_ARTIFACTS_DIR` env var → `<artifacts_dir>/local/.config.artifacts_dir` → default `$HOME/agami-artifacts`. All examples / model / ORGANIZATION.md paths in this skill resolve under `<artifacts_dir>/<profile>/`. USER_MEMORY.md is at `<artifacts_dir>/USER_MEMORY.md` (top-level, cross-database). |
| 38 | |
| 39 | For v1.0 / v1.1 fallback paths (`<artifacts_dir>/local/<profile>.yaml`, `<artifacts_dir>/local/<profile>-examples.yaml`, `<artifacts_dir>/<profile>/`), only read; never write. Migration is agami-connect's job — this skill assumes the user has already migrated by the time they're saving corrections. |
| 40 | |
| 41 | ### 1b — find the most recent query |
| 42 | |
| 43 | Read the last entry in `<artifacts_dir>/local/query_log.jsonl`. Need `question` and `sql`. |
| 44 | |
| 45 | If the log is empty: "I don't have a recent query to attach this correction to. Ask the question first, then save the correction." Stop. |
| 46 | |
| 47 | # |
People who liked this also viewed
6 picksType
- azure-storageAzure Storage Services including Blob Storage, File Shares, Queue Storage, Table Storage, and Data Lake. Answers questions about storage access tiers (hot, cool, cold, archive), when to use each tier,SkillsJul 2026
- supabase-postgres-best-practicesPostgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations.SkillsJul 2026
- supabaseUse when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, SkillsJul 2026
- convex-quickstartCreates or adds Convex to an app. Use for new Convex projects, npm create convex@latest, frontend setup, env vars, or the first npx convex dev run.SkillsJul 2026
- convex-performance-auditAudits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.SkillsJul 2026
- convex-setup-authSets up Convex auth, identity mapping, and access control. Use for login, auth providers, users tables, protected functions, or roles in a Convex app.SkillsJul 2026
