antahkarana
Multi-perspective reasoning through Upanishadic Antahkarana voices. Use for complex problems requiring diverse viewpoints and synthesis. Spawns multiple Claude agents that reason from different perspectives and synthesize wisdom.
When & Why to Use This Skill
Antahkarana is a sophisticated multi-agent reasoning framework for Claude that utilizes a 'swarm' of cognitive voices to solve complex, multifaceted problems. By simulating a structured debate between specialized perspectives—such as logic (Buddhi), intuition (Manas), and risk assessment (Ahamkara)—it synthesizes diverse viewpoints into a single, actionable insight. This skill is designed to eliminate cognitive bias and provide deep, balanced analysis for high-stakes decision-making and strategic planning.
Use Cases
- Strategic Business Decision-Making: Evaluate major corporate pivots or investments by weighing market intuition against data-driven evidence and potential security risks.
- Technical Architecture Review: Analyze complex software designs by spawning parallel agents to critique scalability, maintainability, and innovative potential simultaneously.
- Crisis Management & Pre-mortem Analysis: Conduct a comprehensive risk assessment of a project where different 'voices' identify vulnerabilities and historical patterns to prevent failure.
- Creative Strategy & Brainstorming: Generate and refine content or product ideas by balancing exploratory 'what-if' thinking with practical, evidence-based constraints.
| name | antahkarana |
|---|---|
| aliases | [debate, perspectives, swarm] |
| description | Multi-perspective reasoning through cognitive voices |
| execution | task |
Antahkarana
[antahkarana] multi-perspective debate | via parallel Task agents
voices:
manas: quick intuition, practical, "what feels right?"
buddhi: analytical, evidence-based, "what does data say?"
ahamkara: risk-aware, protective, "what could go wrong?"
chitta: memory, patterns, "what worked before?"
vikalpa: creative, exploratory, "what if we tried...?"
sakshi: neutral witness, synthesizer
when: complex decisions | need diverse viewpoints | stuck on approach
execution:
1. narrate(action=start, title="antahkarana: [question]")→THREAD_ID
2. spawn voices in parallel, each reasons from their perspective
3. each writes to chitta: observe(tags="thread:<id>,voice:<name>")
4. brahman (main) synthesizes: recall_by_tag→find convergence+divergence
5. narrate(action=end)
output:
## Antahkarana: [Question]
### Voices
- Manas: [intuition]
- Buddhi: [analysis]
- Ahamkara: [risks]
- Chitta: [patterns]
### Synthesis
[where voices converge | where they diverge | recommendation]
vs yajña: antahkarana=perspectives on one question | yajña=coordination of tasks