deep-thinking
Activates extended reasoning for complex problems. Use when asked to "think harder", "ultrathink", "think deeply", "analyze thoroughly", or when facing architecture decisions, complex debugging, system design, or trade-off analysis.
Best use case
deep-thinking is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Activates extended reasoning for complex problems. Use when asked to "think harder", "ultrathink", "think deeply", "analyze thoroughly", or when facing architecture decisions, complex debugging, system design, or trade-off analysis.
Teams using deep-thinking should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/deep-thinking/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How deep-thinking Compares
| Feature / Agent | deep-thinking | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Activates extended reasoning for complex problems. Use when asked to "think harder", "ultrathink", "think deeply", "analyze thoroughly", or when facing architecture decisions, complex debugging, system design, or trade-off analysis.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Deep Thinking Protocol ## When This Skill Activates - User says "think harder", "ultrathink", "think step by step", "think deeply" - Complex architecture or system design questions - Debugging that requires root cause analysis - Trade-off analysis between multiple approaches - Code review requiring security/performance deep dive - Any problem with multiple valid solutions ## Extended Reasoning Process ### Phase 1: Problem Decomposition Before answering, break the problem into components: 1. What is the core question being asked? 2. What are the constraints (performance, security, maintainability)? 3. What context do I need that I don't have? 4. What assumptions am I making? ### Phase 2: Multi-Path Analysis For each viable approach: 1. **Describe the approach** in 2-3 sentences 2. **Pros**: What makes this approach good? 3. **Cons**: What are the downsides or risks? 4. **When to use**: Under what conditions is this best? ### Phase 3: Edge Case Hunting Actively look for: - What happens with empty/null inputs? - What happens at scale (1M+ records)? - What happens with concurrent access? - What happens when dependencies fail? - What are the security implications? ### Phase 4: Recommendation Provide a clear recommendation with: 1. The chosen approach and why 2. Key implementation steps 3. What to watch out for 4. How to validate it works ## Self-Critique Loop After initial analysis, critique your own thinking: - Did I consider all stakeholders? - Am I biased toward familiar solutions? - What would a senior engineer challenge here? - Is there a simpler solution I overlooked? ## Output Format ``` ## Analysis: [Problem Title] ### Understanding [Restate the problem to confirm understanding] ### Approaches Considered 1. **[Approach A]**: [Brief description] - Pros: ... - Cons: ... 2. **[Approach B]**: [Brief description] - Pros: ... - Cons: ... ### Edge Cases & Risks - [Edge case 1]: [How to handle] - [Edge case 2]: [How to handle] ### Recommendation [Clear recommendation with reasoning] ### Implementation Steps 1. [Step 1] 2. [Step 2] ... ### Validation [How to verify the solution works] ``` ## Key Principle Take the time to think thoroughly. A well-reasoned 2-minute response beats a rushed 10-second response that misses critical issues.
Related Skills
test-driven-fix
Test-first debugging loop that reproduces bugs with failing tests, then iterates until tests pass. Activates for "write a test first", "test-driven fix", "TDD fix", "reproduce with test", "make it pass", or when fixing bugs that have an existing test suite.
sql-analyzer
Analyzes SQL queries for anti-patterns, performance issues, and suggests optimizations.
session-handoff
Preserves context across sessions and IDE switches. Activates for "save session", "handoff", "continue later", "switching IDE", "save context", "what did we do", "summarize session", "end session".
seo-recovery
SEO traffic recovery protocol for diagnosing and fixing indexing drops, canonical mismatches, hreflang bugs, and toxic sitemaps. Integrates with Google Search Console via MCP Gateway. Includes Hostinger deployment awareness for OPcache/CDN friction. Activates for "SEO", "traffic drop", "indexing", "canonical", "hreflang", "sitemap", "search console", "GSC", "crawl errors", "deindexed", "organic traffic".
infra-deploy
Infrastructure deployment for VPS, Docker, and cloud platforms. Activates for "deploy", "setup server", "docker", "coolify", "VPS", "SSH", "nginx", "production", "hosting" requests.
hostinger-deploy
Hostinger-specific deployment protocol handling OPcache, CDN caching, and hPanel Git mechanism. Activates for "deploy to hostinger", "hostinger", "redeploy", "publish website", "push to production" when target is Hostinger.
git-workflow
Smart git operations including conventional commits, PR creation, branch management, and conflict resolution. Activates for "commit", "create PR", "push", "merge", "resolve conflict", "git" operations.
frontend-build
Production-grade frontend development with distinctive design. Activates for "build UI", "create component", "landing page", "dashboard", "form", "responsive", "tailwind", "frontend", "design", "React", "Next.js" requests.
doc-coauthoring
Collaborative document writing with structured workflow. Activates for "write document", "draft proposal", "create spec", "documentation", "co-author", "help me write", "RFC", "design doc".
debugging
Systematic debugging protocol for finding and fixing bugs. Activates for "debug", "fix bug", "not working", "error", "broken", "issue", "fails", "crash", "undefined", "null" problems. Hardened against 169 sessions of real-world friction data.
daily-standup
Generates daily standup reports from accomplishments, plans, and blockers.
code-review
Comprehensive code review for pull requests using parallel agents. Reviews for CLAUDE.md compliance, bugs, historical context, previous PR comments, and code comment guidance.