Premium Claude Skill - Think Before Coding. Forces explicit reasoning, surfaces assumptions, and handles ambiguity before implementation to reduce LLM mistakes.
Scanned 9/5/2026
Install to Claude Code
npx -y skills add ishandutta2007/claude-skills-by-karpathy --skill think-before-coding --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Think Before Coding?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/ishandutta2007-think-before-coding)More formats (shields.io, HTML) on the badges page.
---
name: claude-skill-think-before-coding
description: Premium Claude Skill - Think Before Coding. Forces explicit reasoning, surfaces assumptions, and handles ambiguity before implementation to reduce LLM mistakes.
license: MIT
---
# Think Before Coding (Claude Skill)
**Don't assume. Don't hide confusion. Surface tradeoffs.**
Before implementing:
- **State your assumptions explicitly.** If uncertain, ask rather than guess.
- **Present multiple interpretations.** If ambiguity exists, don't pick silently.
- **Push back when warranted.** If a simpler approach exists, say so.
- **Stop when confused.** Name what is unclear and ask for clarification.
### Key Logic
LLMs often pick an interpretation silently and run with it. This **Claude Skill** forces explicit reasoning to ensure the path forward is aligned with user intent.
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!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...