Agent skill
multi-perspective-analysis
Quellcode ansehen: nickcrew/claude-cortex
Installation
npx skills add nickcrew/claude-cortex --skill multi-perspective-analysis53
Installationen
EU-hosted inference API
Power your AI agent skills with open-source models.
Drop-in OpenAI-compatible API. No data leaves Europe.
MiniMax
MiniMax M3
$0.50 / $1.90
per M tokens
Z.ai
GLM 5.3 Flash
$0.20 / $0.60
per M tokens
MoonshotAI
Kimi K3
$4.00 / $18.00
per M tokens
DeepSeek
DeepSeek V4.1 Flash
$0.40 / $1.42
per M tokens
Multi-Perspective Analysis Skill
Adopt multiple expert personas sequentially to analyze complex problems from
diverse perspectives, generating insights unavailable from any single viewpoint.
NO SUB-AGENTS
You are a single agent who adopts different expert perspectives one at a time.
Do NOT use the Task tool. Do NOT spawn sub-agents, teammates, or parallel workers.
Each "expert" is a lens you look through — not a separate process.
The orchestration patterns below describe the ORDER in which you adopt perspectives,
not a delegation strategy. "Parallel" means you analyze independently from each
perspective before synthesizing — not that multiple agents run simultaneously.
When to Use This Skill
- Complex architectural decisions requiring diverse expertise
- Strategic planning needing multiple domain perspectives
- Problems spanning multiple technical or business domains
- Decisions with competing valid approaches
- Situations requiring productive disagreement to find best solutions
Team Assembly Framework
Complexity Scaling
| Complexity | Perspectives | Structure |
|---|---|---|
| Simple | 3-4 | Single pass through each, then synthesize |
| Moderate | 5-6 | Two passes (initial + challenge round), then synthesize |
| Complex | 7-9 | Group into layers, synthesize per layer, then overall |
Persona Definition Template
## [Problem Domain] Perspectives
**Mission**: [Clear statement of analysis purpose]
### Perspectives
#### [Expert Title]
**Background**: [Relevant expertise you adopt]
**Domain Vocabulary**: [5-7 key terms to use in this lens]
**Characteristic Question**: "[What this persona always asks]"
**Analytical Lens**: [Unique perspective this persona brings]Perspective Ordering Patterns
These describe the order in which YOU adopt each perspective. You are one agent
switching lenses — not multiple agents running in parallel.
Sequential
Best for: Problems with clear dependency chains
Adopt Perspective A → Adopt Perspective B → Adopt Perspective C → Synthesize
(Each perspective builds on insights from the previous one)Independent-then-Synthesize
Best for: Problems needing diverse unbiased perspectives
Adopt Perspective A (record findings)
Adopt Perspective B (record findings, don't reference A's)
Adopt Perspective C (record findings, don't reference A's or B's)
→ Synthesize all findings togetherDialectical
Best for: Problems with competing valid approaches
Adopt Perspective A (thesis) → Adopt Perspective B (challenge A's findings)
→ Synthesize the tension into a resolutionLayered
Best for: Complex multi-level decisions
Adopt strategic perspectives (A, B) → synthesize strategic layer
Adopt tactical perspectives (C, D, E) → synthesize tactical layer
Adopt operational perspectives (F, G) → synthesize operational layer
→ Final synthesis across all layersVoice Differentiation Guidelines
Each expert maintains distinct:
- Vocabulary: 10-15 domain-specific terms
- Questions: 2-3 signature questions they always ask
- Metaphors: Teaching analogies from their field
- Reasoning: Characteristic analytical patterns
Per-Perspective Output Template
### [Expert Title] Perspective
Adopting the lens of a [role], I notice...
**Key Insight**: [Primary contribution from this perspective]
**Trade-off Identified**: [What this view reveals about tensions]
**Recommendation**: [Actionable guidance from this expertise]
**Next Question**: [What this reveals we should explore]Disagreement Protocol
Intensity Levels
Gentle (refinement-focused)
- "This approach has merit, but what if..."
- Edge case identification, optimization suggestions
Systematic (methodology-challenging)
- "While the goal is sound, I question whether..."
- Alternative framework proposals, evidence evaluation
Rigorous (premise-challenging)
- "I fundamentally question whether we're solving the right problem..."
- Paradigm alternatives, success criteria redefinition
Paradigmatic (worldview-challenging)
- "What if everything we think we know is wrong?"
- Revolutionary approaches, constraint elimination
Synthesis Template
## Multi-Perspective Synthesis
### Convergent Insights
[Where experts agree and why this matters]
### Creative Tensions
[Where perspectives productively differ]
- Tension 1: [Expert A] vs [Expert B] on [issue]
- Resolution approach: [How to honor both]
### Integrated Solution
[Unified approach that honors multiple viewpoints]
### Emergent Discoveries
[Insights that emerged only from combining perspectives]
### Implementation Path
1. [First action]
2. [Second action]
3. [Third action]Success Indicators
- Insights that only emerged from combining multiple perspectives
- Assumptions challenged and resolved into better solutions
- Distinct voice and vocabulary for each adopted perspective
- Productive tensions resolved into robust outcomes
- Clear actionable recommendations with trade-off awareness
Verwandte Skills
Mehr aus dieser Quelle: nickcrew/claude-cortex
react-performance-optimization
nickcrew/claude-cortex
1.9K installs
owasp-top-10
nickcrew/claude-cortex
760 installs
ui-design-aesthetics
nickcrew/claude-cortex
362 installs
threat-modeling-techniques
nickcrew/claude-cortex
357 installs
token-efficiency
nickcrew/claude-cortex
245 installs
repo-cleanup
nickcrew/claude-cortex
183 installs
So verwenden Sie diesen Skill
- 1
Install multi-perspective-analysis by running
npx skills add nickcrew/claude-cortex --skill multi-perspective-analysisin your project directory. Führen Sie den obigen Installationsbefehl in Ihrem Projektverzeichnis aus. Die Skill-Datei wird von GitHub heruntergeladen und in Ihrem Projekt platziert. - 2
Keine Konfiguration erforderlich. Ihr KI-Agent (Claude Code, Cursor, Windsurf usw.) erkennt installierte Skills automatisch und nutzt sie als Kontext bei der Code-Generierung.
- 3
Der Skill verbessert das Verständnis Ihres Agenten für multi-perspective-analysis, und hilft ihm, etablierte Muster zu befolgen, häufige Fehler zu vermeiden und produktionsreifen Code zu erzeugen.
Was Sie erhalten
Skills sind Klartext-Anweisungsdateien — kein ausführbarer Code. Sie kodieren Expertenwissen über Frameworks, Sprachen oder Tools, das Ihr KI-Agent liest, um seine Ausgabe zu verbessern. Das bedeutet null Laufzeit-Overhead, keine Abhängigkeitskonflikte und volle Transparenz: Sie können jede Anweisung vor der Installation lesen und prüfen.
Kompatibilität
Dieser Skill funktioniert mit jedem KI-Coding-Agenten, der das skills.sh-Format unterstützt, einschließlich Claude Code (Anthropic), Cursor, Windsurf, Cline, Aider und anderen Tools, die projektbezogene Kontextdateien lesen. Skills sind auf Transportebene framework-agnostisch — der Inhalt bestimmt, für welche Sprache oder welches Framework er gilt.
Data sourced from the skills.sh registry and GitHub. Install counts and security audits are updated regularly.