breadth-of-thought
Breadth of Thought Reasoning Methodology
Purpose: Exhaustive exploration of solution spaces through systematic parallel breadth-first reasoning. Maintains multiple hypotheses, explores diverse approaches, and returns 3-5 viable solutions instead of prematurely converging on one.
When to Use Breadth of Thought
✅ Use BoT when:
- Unknown solution space (you don't know what you don't know)
- Multiple valid solutions needed (need 3-5 good options, not just 1 best)
- High-stakes decisions (can't afford to miss viable alternatives)
- Novel problems (no clear best practice exists)
- Debugging complex issues (multiple potential root causes)
- Comprehensive planning (need to evaluate ALL options before deciding)
❌ Don't use BoT when:
- Clear evaluation criteria exist and you need THE single best solution → Use tree-of-thoughts
- Problem requires deep sequential reasoning with dependencies → Use self-reflecting-chain
- Single obvious approach exists → Solve directly
- Time-critical with simple trade-offs → Quick analysis sufficient
More from kimasplund/claude_cognitive_reasoning
self-reflecting-chain
Sequential reasoning with deep self-reflection and backtracking. Use when problems have step-by-step dependencies, need careful logical reasoning, or require error correction. Each step includes self-reflection, and incorrect steps trigger backtracking. Ideal for debugging, mathematical proofs, sequential planning, or causal analysis where order matters.
95agent-memory-skills
Self-improving agent architecture using ChromaDB for continuous learning, self-evaluation, and improvement storage. Agents maintain separate memory collections for learned patterns, performance metrics, and self-assessments without modifying their static .md configuration.
44chromadb-integration-skills
Universal ChromaDB integration patterns for semantic search, persistent storage, and pattern matching across all agent types. Use when agents need to store/search large datasets, build knowledge bases, perform semantic analysis, or maintain persistent memory across sessions.
42integrated-reasoning
Meta-orchestration guide for choosing optimal reasoning patterns. Analyzes problem characteristics and recommends which cognitive methodology to use - tree-of-thoughts (find best), breadth-of-thought (explore all), self-reflecting-chain (sequential logic), or direct analysis. Use when facing complex problems and unsure which reasoning approach fits best.
30document-writing-skills
Teaches document writing patterns and templates that agents apply when generating documentation, reports, contracts, guides, and technical writing. Use when creating API docs, user guides, reports, changelogs, ADRs, or technical documentation.
23error-handling-skills
Universal error handling, exception management, and logging best practices for all development agents across JavaScript/TypeScript, Python, Rust, Go, and Java. Use when implementing error handling, exception management, logging, error recovery, or debugging production issues.
20