Tree Of Thoughts
Skill Verifiziert AktivExecute tasks through systematic exploration, pruning, and expansion using Tree of Thoughts methodology with meta-judge evaluation specifications and multi-agent evaluation
To provide a structured and systematic approach for tackling complex reasoning tasks that require exploring multiple solution paths before committing to a final implementation.
Funktionen
- Systematic exploration of solution space
- Pruning of unpromising branches
- Expansion of viable approaches
- Meta-judge evaluation specifications
- Multi-agent evaluation and synthesis
Anwendungsfälle
- Tackling complex coding challenges requiring exploration of different architectural patterns.
- Designing novel algorithms where multiple approaches need to be evaluated.
- Synthesizing best solutions from diverse ideas in research and development.
- Generating detailed technical specifications through iterative refinement and evaluation.
Nicht-Ziele
- Performing simple, direct tasks that do not benefit from multi-path exploration.
- Replacing human decision-making entirely; acts as an AI assistant.
- Providing generic code generation without a structured reasoning process.
Workflow
- Phase 1: Exploration (Propose Approaches) by 3 independent agents.
- Phase 1.5: Dispatch Pruning Meta-Judge to generate criteria.
- Phase 2: Pruning (Vote for Top 3 Candidates) by 3 independent judges.
- Phase 2b: Select Top 3 Proposals based on aggregated votes.
- Phase 3: Expansion (Develop Full Solutions) by 3 independent agents.
- Phase 3.5: Dispatch Evaluation Meta-Judge to generate criteria.
- Phase 4: Evaluation (Judge Full Solutions) by 3 independent judges.
- Phase 4.5: Adaptive Strategy Selection (SELECT_AND_POLISH, REDESIGN, or FULL_SYNTHESIS).
- Phase 5: Synthesis (if FULL_SYNTHESIS selected) - Combine best elements.
Praktiken
- Agent Orchestration
- Structured Reasoning
- Meta-Evaluation
Installation
Zuerst Marketplace hinzufügen
/plugin marketplace add NeoLabHQ/context-engineering-kit/plugin install sadd@context-engineering-kitQualitätspunktzahl
VerifiziertVertrauenssignale
Ähnliche Erweiterungen
Ccg
99Claude-Codex-Gemini tri-model orchestration via /ask codex + /ask gemini, then Claude synthesizes results
External Context
100Invoke parallel document-specialist agents for external web searches and documentation lookup
Swarm Orchestration
100Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing complex workflows, or building distributed AI systems.
Ux Research
100Plan and execute user research including research planning, recruiting, interview design, qualitative synthesis, and translating findings into product decisions. Use this skill whenever the user wants to plan user research, design interviews, recruit participants, conduct discovery, run formative research, or synthesize qualitative findings. Triggers on user research, UX research, user interviews, discovery research, generative research, formative research, qualitative research, user insights, research synthesis, recruitment, interview guide, jobs to be done. Also triggers when product decisions are being made without user input and the user wants to fix that.
Notion Research Documentation
100Durchsucht Ihren Notion-Arbeitsbereich, synthetisiert Erkenntnisse aus mehreren Seiten und erstellt umfassende Research-Dokumentationen, die als neue Notion-Seiten gespeichert werden. Verwandelt verstreute Informationen in strukturierte Berichte mit ordnungsgemäßen Zitaten und umsetzbaren Erkenntnissen.
Omc Plan
99Strategic planning with optional interview workflow