// Analyzes and optimizes prompts using BP-001~008 patterns and 3-step flow (detect, optimize, balance). Use when "optimize this prompt", "review prompt quality", "analyze prompt issues", or creating/reviewing rashomon skill content.
Project-specific prompt optimization knowledge management. Use when storing or retrieving learned patterns from comparisons. Provides schema, extraction criteria, capacity management, and retention scoring.
Git worktree management for isolated parallel prompt execution. Use when creating isolated environments for prompt comparison or managing worktree lifecycle. Provides creation, cleanup, and orphan detection scripts.
Creates or updates Claude Code skills through interactive dialog, then evaluates effectiveness by parallel execution comparison. Use when creating new skills, updating existing skills, or evaluating skill quality.
Compares original and optimized prompts by parallel execution in git worktrees. Use when evaluating prompt improvement effects or learning prompt engineering through concrete examples.
| name | prompt-optimization |
| description | Analyzes and optimizes prompts using BP-001~008 patterns and 3-step flow (detect, optimize, balance). Use when "optimize this prompt", "review prompt quality", "analyze prompt issues", or creating/reviewing rashomon skill content. |
references/execution-quality.yaml over_optimization criteria)High confidence research evidence for negative impact.
| ID | Pattern | Research Basis |
|---|---|---|
| BP-001 | Negative Instructions | Attention focuses on forbidden content, increasing violation probability. Inverse scaling confirmed |
| BP-002 | Vague Instructions | Primary failure cause. 40% of performance variance |
| BP-003 | Missing Output Format | Directly linked to hallucination reduction |
Consistent improvement when addressed.
| ID | Pattern | Research Basis |
|---|---|---|
| BP-004 | Unstructured Prompt | "Structure > Length" confirmed |
| BP-005 | Missing Context | "More context = higher accuracy" confirmed |
| BP-006 | Complex Task Without Decomposition | ICLR 2023: 28% error reduction with decomposition |
Incremental improvements in specific contexts.
| ID | Pattern | Research Basis |
|---|---|---|
| BP-007 | Biased Examples | 40% of few-shot effectiveness depends on exemplar selection |
| BP-008 | No Uncertainty Permission | Allowing "I don't know" reduces hallucination |
Input: Target prompt
Process: Detect patterns (BP-001 through BP-008)
Output: .claude/.rashomon/step1-analysis.md
Contents:
Input: Step 1 analysis Process:
.claude/.rashomon/step2-optimized.mdContents:
Input: Step 2 output Process:
references/execution-quality.yamlreferences/execution-quality.yaml over_optimization)
Output: Final optimized prompt. Clean up temporary files (.claude/.rashomon/step1-*.md, step2-*.md) after completion.Apply 4-block pattern IF:
Skip when:
Decompose IF:
Key Insight: Goal is EVALUABLE GRANULARITY with QUALITY CHECKPOINTS, not decomposition itself.
| Classification | Definition | Interpretation |
|---|---|---|
| Structural | Prompt structure, clarity, specificity improvements | Prompt writing technique |
| Context Addition | Project-specific information added from codebase investigation | Information advantage |
| Expressive | Different phrasing, equivalent substance | Neutral |
| Variance | Within LLM probabilistic variance | Original prompt sufficient |
Principle: Distinguish between prompt writing improvements (Structural) and information additions (Context Addition).
Reference: references/execution-quality.yaml for detailed criteria.
references/patterns.yaml - Detailed pattern definitionsreferences/execution-quality.yaml - Quality evaluation criteriareferences/skills.md - Skill-specific optimization (BP adaptation, 9 editing principles, progressive disclosure, grading)