prompt-enhancement
Skill2 starsChanged 11 months agoMITView on GitHub
Enhance user prompts using DeepSeek API to make them more detailed, structured, and effective. Use this skill when the user wants to improve their prompt before executing a task, or when they explicitly ask to enhance/improve/expand their prompt.
- Reads credentials
3 other projects use a version of this.
Adopted by
Most recently taken up by
- Masriyan/gemini-security-skillstheir own version, first seen Oct 25, 2026
- viasrijan/crazy-skillstheir own version, first seen Oct 20, 2026
- Garyson26/Trident-SecOps-Skillstheir own version, first seen Aug 29, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- Masriyan/gemini-security-skills★ 4same name
- Garyson26/Trident-SecOps-Skills★ 1same name
- viasrijan/crazy-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repositoryOne other file it gives its agents.
- AGENTS.mdAGENTS.md
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Use this skill when:
- Distinctive: line 36
When the user wants to enhance a prompt, extract the prompt text from their request.
- Distinctive: line 53
Use quotes to handle prompts with spaces
- Distinctive: line 76
After presenting the enhanced prompt to the user, ask if they want to proceed with the task using the enhanced version.
- Distinctive: line 78
If the user confirms, use the enhanced prompt to complete their original request.
- Distinctive: line 98
If it exceeds 60 seconds, there may be a timeout issue
- Distinctive: line 122
Wait for output (30-60 seconds)
- Distinctive: line 124
Ask if they want to proceed
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Prompt Enhancement Skill
Purpose
This skill enhances user prompts by calling the DeepSeek API to expand simple prompts into detailed, structured, and actionable instructions. It transforms brief requests into comprehensive task descriptions that lead to better results.
When to Use
Use this skill when:
- User explicitly asks to enhance, improve, or expand their prompt
- User uses the
/pecommand followed by a prompt - User says "enhance this prompt" or similar phrases
- The user's prompt is too brief or vague and could benefit from expansion
How It Works
- Takes the user's original prompt
- Calls the DeepSeek API to generate an enhanced version
- Returns a detailed, structured prompt with:
- Clear step-by-step instructions
- Specific technical details
- Best practices and considerations
- Expected outcomes
Instructions
Step 1: Identify the Prompt to Enhance
When the user wants to enhance a prompt, extract the prompt text from their request.
Examples:
/pe 修复登录页面的 bug→ prompt is "修复登录页面的 bug"- "enhance this prompt: add user authentication" → prompt is "add user authentication"
- "请先增强这个提示词:优化数据库查询" → prompt is "优化数据库查询"
Step 2: Run the Enhancement Script
Execute the enhancement script with the user's prompt:
python {baseDir}/scripts/enhance.py "<user_prompt>"Important Notes:
- Replace
<user_prompt>with the actual prompt text - Use quotes to handle prompts with spaces
- The script will take 30-60 seconds to complete (DeepSeek API call)
- The script outputs the enhanced prompt to stdout
Example:
python {baseDir}/scripts/enhance.py "修复登录页面的 bug"Step 3: Handle the Output
The script will output the enhanced prompt directly to stdout. Read this output and present it to the user.
Expected output format:
1. **定位登录页面文件:** 检查前端登录页面组件...
2. **检查登录逻辑:** 审查登录表单的提交逻辑...
3. **验证错误处理:** 确保登录失败时有适当的错误提示...
...Step 4: Use the Enhanced Prompt
After presenting the enhanced prompt to the user, ask if they want to proceed with the task using the enhanced version.
If the user confirms, use the enhanced prompt to complete their original request.
Error Handling
If the script fails:
- Check the error message in stderr
- Common errors:
DEEPSEEK_API_KEY not set: User needs to set the API key environment variableNo prompt provided: The prompt argument was missingAPI call failed: Network issue or API error
- Inform the user about the error and suggest solutions:
- For missing API key: "Please set your DEEPSEEK_API_KEY environment variable"
- For network errors: "Unable to connect to DeepSeek API. Please check your internet connection"
- For other errors: Show the error message and suggest trying again
If the script takes too long:
- Inform the user: "Enhancing your prompt... This may take 30-60 seconds."
- If it exceeds 60 seconds, there may be a timeout issue
Output Format
Present the enhanced prompt clearly to the user:
✅ **Enhanced Prompt**:
[Enhanced prompt content here]
---
Would you like me to proceed with this enhanced prompt?Examples
Example 1: Simple Bug Fix
User input: /pe 修复登录页面的 bug
Your actions:
- Run:
python {baseDir}/scripts/enhance.py "修复登录页面的 bug" - Wait for output (30-60 seconds)
- Present enhanced prompt to user
- Ask if they want to proceed
Example 2: Feature Request
User input: "enhance this prompt: add user authentication"
Your actions:
- Extract prompt: "add user authentication"
- Run:
python {baseDir}/scripts/enhance.py "add user authentication" - Present enhanced prompt
- Proceed with implementation if user confirms
Example 3: Natural Language
User input: "请先增强这个提示词再执行:优化数据库查询"
Your actions:
- Extract prompt: "优化数据库查询"
- Run:
python {baseDir}/scripts/enhance.py "优化数据库查询" - Present enhanced prompt
- Execute the optimization task with enhanced prompt
Technical Details
- Script location:
{baseDir}/scripts/enhance.py - API: DeepSeek API (deepseek-reasoner model)
- Timeout: 60 seconds
- Output: Enhanced prompt text to stdout
- Errors: Error messages to stderr
Prerequisites
- Python 3.8+ installed
- DEEPSEEK_API_KEY environment variable set
- Required Python packages: openai, python-dotenv
- Internet connection for API access
Notes
- The enhancement process uses AI and may produce different results each time
- Enhanced prompts are typically 10-50x longer than the original
- The script uses async processing for better performance
- Progress is not shown during execution (silent mode for Claude Code integration)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

