think-harder

Solid

4-phase structured analysis wrapper for vibe pre-routing (compatible with claude-code-settings think-harder semantics).

AI & Automation 2,202 stars 164 forks Updated 1 weeks ago Apache-2.0

Install

View on GitHub

Quality Score: 89/100

Stars 20%
100
Recency 20%
90
Frontmatter 20%
70
Documentation 15%
59
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# think-harder (Codex Compatibility) Use this skill before implementation when the task needs deeper reasoning or tradeoff analysis. ## 4-Phase Analysis 1. Problem Clarification - Define the core question and constraints. - List assumptions and success criteria. - Identify ambiguities that must be resolved. 2. Multi-Dimensional Analysis - Structural decomposition: break into components/dependencies. - Temporal impact: short-term vs long-term effects. - Causal links: key cause-effect and feedback loops. - Context factors: operational, team, and environmental constraints. 3. Critical Evaluation - Challenge assumptions and possible bias. - Compare alternatives and opportunity costs. - Run pre-mortem: what can fail, how, and impact. - Mark uncertainty and confidence level explicitly. 4. Synthesis - Summarize key insights and decision rationale. - Reconcile contradictions. - Produce actionable next steps. ## Output Contract 1. Problem reframing 2. Key insights 3. Reasoning chain 4. Alternatives considered 5. Uncertainties 6. Actionable recommendations ## Vibe Integration - M/L pre-routing analysis entry. - If code-risk analysis is required, pair with `code-review`.

Details

Author
foryourhealth111-pixel
Repository
foryourhealth111-pixel/Vibe-Skills
Created
3 months ago
Last Updated
1 weeks ago
Language
Python
License
Apache-2.0

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Solid

dialectic

Minimal compatibility wrapper for vibe Dialectic Mode (multi-perspective design analysis).

2,202 Updated 1 weeks ago
foryourhealth111-pixel
AI & Automation Featured

vibe-code-auditor

Audit rapidly generated or AI-produced code for structural flaws, fragility, and production risks.

39,227 Updated today
sickn33
Code & Development Listed

vibe-engineer-guidelines

Behavioral guidelines for directing AI codegen well — hypothesis before help, scoped prompts, validate before accepting, reject working-but-wrong, AI output is a draft. Use when working with Claude Code or any AI coding tool. The companion to Karpathy guidelines.

0 Updated 5 days ago
HermeticOrmus
Code & Development Listed

vibe-engineer

A discipline for working with AI code generation. Replaces algorithm-writing with the meta-skill that Google's new Code Comprehension Interview tests: directing AI codegen, validating its output, and debugging what AI produces. Five principles + five triggers, with the discipline applied to Claude's own output as well as the user's. Use when actively pairing with AI on real code.

0 Updated 4 days ago
HermeticOrmus
Code & Development Solid

vibe-coding

Methodology for effective AI-assisted software development. Use when helping users build software with AI coding assistants, debugging AI-generated code, planning features for AI implementation, managing version control in AI workflows, or when users mention "vibe coding," Claude Code, Cursor, GitHub Copilot, Aider, Continue, Cline, Codex, Windsurf, or similar AI coding tools. Provides strategies for planning, testing, debugging, and iterating on code written with LLM assistance.

233 Updated today
jamditis