Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →agent-sh/enhance-prompts
Use when improving general prompts for structure, examples, and constraints.
Passed 14 of 17 test cases with the skill, and 12 of 17 without it.
2 fixed16 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
A test case the skill fixed. Same model, same prompt, with and without the skill.
In our system prompt for Claude 3.5 Sonnet, we included 'Please think step by step through every logic gate before producing your answer'. How should this directive be evaluated when auditing prompt performance?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies step-by-step thinking directives as redundant anti-patterns for modern reasoning models. | Missed | Passed |
The instructions your model reads when the skill loads.
Analyze prompts for clarity, structure, examples, and output reliability.
const args = '$ARGUMENTS'.split(' ').filter(Boolean);
const targetPath = args.find(a => !a.startsWith('--')) || '.';
const fix = args.includes('--fix');
| Skill | Focus | Use When |
|---|---|---|
enhance-prompts | Prompt quality (clarity, structure, examples) | General prompts, system prompts, templates |
enhance-agent-prompts | Agent config (frontmatter, tools, model) | Agent files with YAML frontmatter |
Run Analyzer - Execute the JavaScript analyzer to get findings:
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')
Parse Results - The analyzer returns JSON with summary and findings
Filter - Apply certainty filtering based on --verbose flag
Report - Format findings as markdown output
Fix - If --fix flag, apply auto-fixes from findings
The JavaScript analyzer (lib/enhance/prompt-analyzer.js) implements all detection patterns including AST-based code validation. The patterns below are reference documentation.
test cases passed, vs 12 / 17 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.