home/writing/fix-prompt-generation-5

Fix Prompt Generation

GPTClaudeGemini··165 copies·updated 2026-07-14
fix-prompt-generation-5.prompt
# Tuner LLM Fix Prompt Generation

**Purpose:** Tuner-specific action verbs, suppression cases, template fields, and worked example for the `## LLM Fix Prompt` block at the end of every Tuner performance report.
**Read when:** You are writing the `## LLM Fix Prompt` block for a Tuner report, choosing an action verb, or deciding whether to suppress.

> Universal authoring rules and prompt structure: `_common/LLM_PROMPT_GENERATION.md`.
> This file documents only Tuner-specific verbs, suppression cases, template fields, and an example.

## Contents

- Tuner action verbs
- Verb selection heuristic
- Tuner-specific suppression cases
- Per-finding fix prompt template (Tuner-specific fields)
- Worked example

---

## Tuner Action Verbs

Each fix prompt declares one verb at the top of `# Your task`.

| Verb | When to use | Receiving agent |
|------|-------------|----------------|
| `OPTIMIZE-QUERY` | Query plan fix (rewrite, hint, parameterization, JOIN order, predicate pushdown) | Builder |
| `ADD-INDEX` | Schema-level index addition (single/composite/partial/covering); coordinate with Schema for migration | Schema → Builder |
| `BREAKING-OPTIMIZE` | Query/schema change with API or contract impact (response shape, pagination semantics) | Builder + Guardian + Launch |
| `MIGRATE-WORKLOAD` | Structural — different query pattern needed (batched fetch, materialized view, denormalization) | Atlas + Builder + Schema |
| `INVESTIGATE-FURTHER` | EXPLAIN ANALYZE inconclusive; need production trace (pg_stat_statements, slow log) before deciding | Beacon (data collection) or Tuner re-entry |
| `MITIGATE` | Cache layer / materialized view / read replica routing while query is fixed | Builder + Bolt |

---

## Verb Selection Heuristic

when to use it

Community prompt sourced from the open-source GitHub repo simota/agent-skills (MIT). A "Fix Prompt Generation" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.

tags

writingcommunitygeneral

source

simota/agent-skills · MIT