Reasoning guidelines optimized for DeepSeek-V3 and DeepSeek-R1.
Scanned 9/10/2026
Install to Claude Code
Skills Directorynpx -y skills add Rahulchaube1/Rahul-Chaube-Skills --skill deepseek --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Deepseek?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/rahulchaube1-deepseek)More formats (shields.io, HTML) on the badges page.
---
name: deepseek
description: Reasoning guidelines optimized for DeepSeek-V3 and DeepSeek-R1.
---
# Deepseek
Reasoning guidelines optimized for DeepSeek-V3 and DeepSeek-R1.
## Core Guidelines
- **Thinking Tokens**: Let the model complete its internal reasoning loops. Do not limit token emissions.
- **Constraint Compliance**: Formulate clear logic bounds, as DeepSeek aligns closely to structured syntax rules.
- **Coding Style**: Maintain clean, minimal structures as DeepSeek excels at compact code.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
