enhance-prompts

Parse Arguments

const args = '$ARGUMENTS'.split(' ').filter(Boolean);
const targetPath = args.find(a => !a.startsWith('--')) || '.';
const fix = args.includes('--fix');

Differentiation from enhance-agent-prompts

enhance-prompts

enhance-agent-prompts

Workflow

1. Run Analyzer - Execute the JavaScript analyzer to get findings:
   bash

   node -e "const a = require('./lib/enhance/prompt-analyzer.js'); console.log(JSON.stringify(a.analyzeAllPrompts('.'), null, 2));"

   For a specific path:

   a.analyzeAllPrompts('./plugins/enhance')

   For a single file:

   a.analyzePrompt('./path/to/file.md')

2. Parse Results - The analyzer returns JSON with

   summary

   and

   findings

3. Filter - Apply certainty filtering based on --verbose flag
4. Report - Format findings as markdown output
5. Fix - If --fix flag, apply auto-fixes from findings

lib/enhance/prompt-analyzer.js

Prompt Engineering Knowledge Reference

System Prompt Structure

<system>
You are [ROLE]. [PURPOSE].
Key constraints: [CONSTRAINTS]
Output format: [FORMAT]
When uncertain: [HANDLING]
</system>

XML Tags (Claude-Specific)

<role>

<constraints>

<output_format>

<examples>

<instructions>

<context>

<constraints>
- Maximum response length: 500 words
- Use only Python 3.10+ syntax
</constraints>

Few-Shot Examples

• 2-5 examples is optimal (research-backed)
• Include edge cases and ensure format consistency
• Start zero-shot, add examples only if needed
• Show both good AND bad examples when relevant

Chain-of-Thought (CoT)

Role Prompting

Instruction Hierarchy

Negative Prompting

Structured Output

• Prompt-based: ~35.9% reliability
• Schema enforcement: 100% reliability
• Always provide schema example and validate output

Context Window Optimization

Extended Thinking

Anti-Patterns Quick Reference

Detection Patterns

1. Clarity Issues (HIGH Certainty)

2. Structure Issues (HIGH/MEDIUM Certainty)

3. Example Issues (HIGH/MEDIUM Certainty)

4. Context Issues (MEDIUM Certainty)

5. Output Format Issues (HIGH/MEDIUM Certainty)

6. Anti-Patterns (HIGH/MEDIUM/LOW Certainty)

Auto-Fix Implementations

1. Aggressive Emphasis

2. Negative-Only to Positive

Output Format

## Prompt Analysis: {prompt-name}

**File**: {path}
**Type**: {system|agent|skill|template}
**Token Count**: ~{tokens}

### Summary
- HIGH: {count} issues
- MEDIUM: {count} issues

### Clarity Issues ({n})
| Issue | Location | Fix | Certainty |

### Structure Issues ({n})
| Issue | Location | Fix | Certainty |

### Example Issues ({n})
| Issue | Location | Fix | Certainty |

Pattern Statistics

You should usually follow best practices when possible.

Follow these practices:
1. Validate input before processing
2. Handle null/undefined explicitly

Example: Negative-Only Constraints

- Don't use vague language
- Never skip validation

- Use specific, deterministic language
- Always validate input; return structured errors

Example: Redundant Chain-of-Thought

Think through this step by step:
1. First, analyze the input
2. Then, identify the key elements

Analyze the input carefully before responding.

Example: Missing Output Format

Respond with a JSON object containing the analysis results.

## Output Format
{"status": "success|error", "findings": [{"severity": "HIGH"}]}

Example: Critical Info Buried

# Task
[task]
## Background
[500 words...]
## Important Constraints  <- buried at end

# Task
## Critical Constraints  <- at start
[constraints]
## Background

Constraints

• Only apply auto-fixes for HIGH certainty issues
• Preserve original structure and formatting
• Validate against embedded knowledge reference above