multi-perspective-analysis
Adopt multiple expert personas sequentially for complex problem analysis from diverse perspectives. Single-agent only — do NOT spawn sub-agents.
What this skill does
# 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 ```markdown ## [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 together ``` ### Dialectical Best for: Problems with competing valid approaches ``` Adopt Perspective A (thesis) → Adopt Perspective B (challenge A's findings) → Synthesize the tension into a resolution ``` ### Layered 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 layers ``` ## Voice 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 ```markdown ### [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 1. **Gentle** (refinement-focused) - "This approach has merit, but what if..." - Edge case identification, optimization suggestions 2. **Systematic** (methodology-challenging) - "While the goal is sound, I question whether..." - Alternative framework proposals, evidence evaluation 3. **Rigorous** (premise-challenging) - "I fundamentally question whether we're solving the right problem..." - Paradigm alternatives, success criteria redefinition 4. **Paradigmatic** (worldview-challenging) - "What if everything we think we know is wrong?" - Revolutionary approaches, constraint elimination ## Synthesis Template ```markdown ## 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
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.