think
Deep multi-framework reasoning using Gemini. Use for complex problem analysis, challenging ideas, and evaluating multiple options with structured thinking.
- Installs
- 258
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/johnlindquist/claude --skill think- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads think automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Think - Structured Reasoning
Apply structured thinking frameworks to complex problems.
Prerequisites
Gemini CLI installed:
pip install google-generativeai
export GEMINI_API_KEY=your_api_key
CLI Reference
All commands use Gemini with structured prompts:
gemini -m pro -o text -e "" "Your prompt"
Thinking Operations
Deep Analysis
Multi-framework reasoning on complex problems:
gemini -m pro -o text -e "" "Analyze this problem using multiple thinking frameworks:
PROBLEM: [Your problem]
Apply these frameworks:
1. First Principles - Break down to fundamental truths
2. Systems Thinking - Map components and interactions
3. Inversion - What would make this fail?
4. Second-Order Effects - What happens after the obvious?
For each framework:
- Key insights
- Blind spots it reveals
- Actionable implications
Synthesize into a coherent recommendation."
Quick Think
Fast reasoning on simpler questions:
gemini -m pro -o text -e "" "Think through this question step by step:
[Your question]
Provide:
1. Initial reaction
2. Key considerations
3. Potential pitfalls
4. Recommended approach"
Challenge an Idea
Stress-test a proposal:
gemini -m pro -o text -e "" "Challenge this idea rigorously:
IDEA: [The idea to challenge]
CONTEXT: [Relevant context]
Apply these challenges:
1. Steel man the counterargument
2. Identify hidden assumptions
3. Find edge cases that break it
4. Consider who might disagree and why
5. What evidence would change your mind?
Conclude with: Should we proceed, modify, or abandon?"
Evaluate Options
Compare multiple choices:
gemini -m pro -o text -e "" "Evaluate these options for: [Decision question]
OPTIONS:
1. [Option A]
2. [Option B]
3. [Option C]
CRITERIA:
- [Criterion 1]
- [Criterion 2]
- [Criterion 3]
For each option:
- Score against each criterion (1-5)
- Key advantages
- Key risks
- Hidden costs
Provide a clear recommendation with reasoning."
Thinking Frameworks
First Principles
gemini -m pro -o text -e "" "Apply first principles thinking to: [problem]
1. What do we know for certain? (facts, not assumptions)
2. What are we assuming? (challenge each)
3. What's the simplest explanation?
4. Build up from fundamentals"
Pre-Mortem
gemini -m pro -o text -e "" "Conduct a pre-mortem for: [project/decision]
Imagine this has completely failed. Working backward:
1. What went wrong?
2. What warning signs did we ignore?
3. What assumptions proved false?
4. What can we do NOW to prevent this?"
Opportunity Cost
gemini -m pro -o text -e "" "Analyze opportunity costs for: [decision]
If we choose this:
1. What are we NOT doing?
2. What resources are locked up?
3. What options are foreclosed?
4. What's the cost of reversing?"
Second-Order Effects
gemini -m pro -o text -e "" "Explore second-order effects of: [action/decision]
First-order effect: [The obvious outcome]
Now trace the chain:
- What does that cause?
- Who responds and how?
- What unintended consequences emerge?
- What feedback loops are created?"
Use Cases
Architecture Decisions
gemini -m pro -o text -e "" "Evaluate architecture options:
CONTEXT: Building a real-time collaborative editor
OPTIONS:
1. Operational Transform (OT)
2. CRDTs
3. Custom sync engine
CRITERIA:
- Correctness guarantees
- Performance at scale
- Implementation complexity
- Offline support
Provide detailed analysis and recommendation."
Code Design
gemini -m pro -o text -e "" "Think through this design decision:
PROBLEM: Where to put validation logic - in the controller, service, or model?
Consider:
- Separation of concerns
- Testability
- Maintainability
- Real-world examples
- What experienced developers prefer and why"
Debugging Strategy
gemini -m pro -o text -e "" "Help me think through debugging this issue:
SYMPTOM: [What's happening]
CONTEXT: [System description]
TRIED: [What you've already attempted]
1. What does this symptom tell us?
2. What's the most likely root cause?
3. What's the most costly root cause?
4. What's the quickest diagnostic test?
5. In what order should I investigate?"
Best Practices
- Be specific - Vague problems get vague analysis
- Provide context - Include constraints and requirements
- Request structure - Ask for frameworks, criteria, scores
- Challenge the output - Use follow-up questions
- Capture reasoning - Save good analyses for future reference
FAQ
What does the think skill do?
Deep multi-framework reasoning using Gemini. Use for complex problem analysis, challenging ideas, and evaluating multiple options with structured thinking.
How do I install think?
Run npx skills add https://github.com/johnlindquist/claude --skill think in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/think/ (personal) or .claude/skills/think/ (project).
Which AI agents can use think?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is think safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains think?
It is published by johnlindquist in johnlindquist/claude. It has 258 recorded installs.
More from johnlindquist/claude
gemini-image
johnlindquist/claude
Analyze images using Gemini's vision capabilities. Use for image analysis, text extraction from screenshots, and visual content understanding.
memory
johnlindquist/claude
Persistent knowledge storage using basic-memory CLI. Use to save notes, search memories semantically, and build context for topics across sessions.
brainstorm
johnlindquist/claude
Generate ideas and explore possibilities with AI. Use for creative problem solving, generating alternatives, and expanding on concepts.
deepwiki
johnlindquist/claude
Query DeepWiki for repository documentation and structure. Use to understand open source projects, find API docs, and explore codebases.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available