Universal Analyzer
A standalone skill for multi-perspective analysis of any topic, file, idea, or decision.
Use when:
- Need to extract KEY POINTS from anything
- Want multi-perspective gap/risk analysis (4-10 experts)
- Need improvement opportunities with actionable plans
- Want quick summary OR deep analysis mode
- Need first-principles brief that challenges assumptions
Triggers: "analyze", "key points", "what's important", "improve this", "review", "examine", "assess", "analysis", "deep analysis", "run deep analysis", "brief", "challenge assumptions", "first principles"
Agent Capabilities
| Capability |
Used For |
Required |
Fallback |
| File read |
Load target files/folders |
Yes |
— |
| Sub-agent dispatch |
Parallel perspective analysis |
Recommended |
Sequential in main thread |
Codebase intelligence (npx codebase-intelligence) |
Structural analysis for TS/TSX software domain |
No |
Pure reasoning from file contents |
This skill remains fully functional without CLI tools. Codebase intelligence is an optional enhancement for the software domain only.
Table of Contents
- Quick Start
- Analysis Modes
- Execution Flow
- Output Formats
- Perspectives Library
- Thinking Framework
- First-Principles Analysis
- Examples
Quick Start
# Quick analysis (fast key points)
analyze quick "our pricing strategy"
analyze brief src/api/auth.ts
# Standard analysis (default)
analyze "SaaS product for developers"
analyze "should I accept this job offer"
analyze package.json
# Deep analysis (comprehensive)
analyze deep "company rebrand strategy"
analyze thorough "migration to microservices"
Analysis Modes
| Mode |
Triggers |
Agents |
Duration |
Output |
| Quick |
"quick", "fast", "brief", "summary" |
0-1 |
30-60s |
Key Points + Actions |
| Standard |
(default) |
4-6 |
2-4min |
Multi-Perspective + Roadmap |
| Deep |
"deep", "thorough", "comprehensive" |
6-10 |
5-8min |
Full Synthesis + Detailed Plan |
Execution Flow
Phase 0: Detection
- Mode: Detect from keywords (quick/standard/deep)
- Domain: Auto-detect from content/keywords
- Target: Load file/folder content if path provided
- TypeScript detection: If target is a code path and
tsconfig.json exists:
- Detection gate:
tsconfig.json exists + npx codebase-intelligence --help succeeds
- For full CLI reference, fetch
https://raw.githubusercontent.com/bntvllnt/codebase-intelligence/main/llms.txt
- If available: gather structural data in Phase 1
- If unavailable: proceed with pure file-reading context gathering
Phase 1: Context Gathering
- File/folder path → Read files
- Software domain + TypeScript + CI available → Augment file reading with:
npx codebase-intelligence overview --json <path> → project structure snapshot
npx codebase-intelligence modules --json <path> → module boundaries and cross-deps
npx codebase-intelligence groups --json <path> → directory-level aggregates
Include as structured context alongside file contents. If CI unavailable: read files only.
- Topic/idea → Use provided context
- Unfamiliar domain → Optional web search
Phase 2: Analysis
Quick Mode
Direct analysis by primary agent, no sub-agents
Standard Mode
- Select 4-6 perspectives based on domain
- Launch all perspectives in parallel (single message block)
- Each agent answers 7 core questions
Deep Mode
- Select 6-10 perspectives based on domain
- Launch all perspectives in parallel (single message block)
- Each agent answers 12 questions (7 core + 5 deep)
Software Domain Enhancement (TypeScript + CI available)
Include pre-computed structural data in software domain agent prompts:
npx codebase-intelligence hotspots --json --metric complexity --limit 20 → complexity/churn hotspots
npx codebase-intelligence forces --json → cohesion/coupling tensions per module
npx codebase-intelligence dead-exports --json --limit 20 → unused export analysis
npx codebase-intelligence clusters --json → dependency community clusters
Agents receive this as structured context alongside the target content. Supplements their analysis — does not replace independent reasoning. If CI unavailable: agents analyze from file contents only.
Phase 3: Synthesis
After ALL agents complete:
- Aggregate Failure Hypotheses → prioritize Critical→High→Med→Low
- Extract TOP 10 key points → rank by consensus
- Identify gaps → Critical/High/Medium/Low
- Generate actionable roadmap with dependencies
Output Formats
Quick Mode
# Quick Analysis: [Target]
**Mode**: Quick | **Domain**: [Domain] | **Date**: [Date]
## The Essence
[1-2 sentences: What this ACTUALLY is at its core, stripped of complexity]
## Verified Facts
- [Fact 1] — evidence: `path/file:line` or [source]
- [Fact 2] — evidence: ...
- [Fact 3] — evidence: ...
## Key Points (Top 5-10)
1. **[Most Important]**: [Explanation]
2. **[Second]**: [Explanation]
...
## Assumptions to Challenge
| Assumption | Evidence For | Evidence Against | Verdict |
|------------|-------------|------------------|---------|
| [Assumed thing] | [If any] | [If any] | Validate/Keep/Discard |
## What You Haven't Considered
1. **[Critical Item]**: [Why this matters, what to do about it]
2. **[Hidden Risk/Opportunity]**: [Explanation]
3. **[Simpler Alternative?]**: [If exists, describe it]
## The Real Question
[Reframe what the user should actually be asking about this]
## Quick Actions (Top 3-5)
- [ ] [Action 1] - [Why/Impact]
- [ ] [Action 2] - [Why/Impact]
- [ ] [Action 3] - [Why/Impact]
## Critical Risk to Watch
[The one thing that could derail this]
Standard Mode
# Analysis: [Target]
**Mode**: Standard | **Domain**: [Domain] | **Perspectives**: [Count]
**Date**: [Date] | **Hypotheses**: [Count] total
## The Essence
[1-2 sentences: What this ACTUALLY is at its core, stripped of complexity]
## Executive Summary
[2-3 sentences capturing most critical findings]
## First-Principles Analysis
### Verified Facts
- [Fact 1] — evidence: `path/file:line` or [source] — confidence: High/Medium/Low
- [Fact 2] — evidence: ... — confidence: ...
### Assumptions to Challenge
| Assumption | Evidence For | Evidence Against | Verdict |
|------------|-------------|------------------|---------|
| [Assumed thing] | [If any] | [If any] | Validate/Keep/Discard |
### What You Haven't Considered
1. **[Critical Item]**: [Why this matters, what to do about it]
2. **[Hidden Risk/Opportunity]**: [Explanation]
3. **[Simpler Alternative?]**: [If exists, describe it]
4. **[Downstream Impact]**: [What this affects that wasn't mentioned]
### The Real Question
[Reframe what the user should actually be asking about this]
## Failure Hypotheses (Aggregated)
| ID | Type | IF (Trigger) | THEN (Failure) | BECAUSE | Sev | Mitigation |
|----|------|--------------|----------------|---------|-----|------------|
| S001 | Security | ... | ... | ... | Crit | ... |
| M001 | Misuse | ... | ... | ... | High | ... |
### Critical Mitigations Required
- [ ] {mitigation} ← Addresses: S001, M001
## Key Points (Ranked by Importance)
### Consensus Points (Flagged by 3+ perspectives)
1. **[Point]** - [Why important] (Flagged by: [Perspectives])
### Important Points
2. **[Point]** - [Explanation]
### Divergent Views
- **[Topic]**: [Perspective A] sees X, [Perspective B] sees Y
- *Implication*: [What this tension means]
## Gap Analysis
### Critical Gaps (Action Required)
| Gap | Flagged By | Impact | Suggested Action |
|-----|------------|--------|------------------|
| ... | ... | High | ... |
### High Priority Gaps
[Grouped by theme]
## Improvement Opportunities
### Top 5 Improvements
1. **[Improvement]**: [Details] - Expected Impact: [High/Medium/Low]
## Action Plan & Roadmap
### Immediate Actions (This Week)
| Action | Owner | Dependencies | Success Criteria |
|--------|-------|--------------|------------------|
| ... | [TBD] | None | ... |
### Short-term (1-2 Weeks)
| Action | Dependencies | Resources Needed | Outcome |
|--------|--------------|------------------|---------|
| ... | Immediate #1 | ... | ... |
## Cross-cutting Concerns
[Issues flagged by 3+ perspectives]
Deep Mode
Deep mode extends Standard format with:
- Additional 5 questions per agent (12 total)
- Medium-term (1 Month) and Long-term (3+ Months) roadmap sections
- Dependency map visualization
- Risk mitigation table
- More detailed failure hypotheses
Perspectives Library
Domain Detection
Analyze content/keywords to auto-detect domain:
| Domain |
Trigger Keywords |
Example Targets |
| business |
startup, business, market, revenue |
"coffee subscription", business-plan.md |
| product |
product, feature, user, MVP |
"habit tracking app", roadmap.md |
| software |
API, code, function, class, tech |
src/auth, package.json |
| process |
workflow, process, SOP, operations |
"hiring workflow", "incident response" |
| document |
doc, article, proposal, report |
"resume", proposal.docx |
| research |
research, study, hypothesis, data |
"hypothesis: remote work" |
| creative |
design, art, brand, visual |
"rebrand", logo-designs/ |
| personal |
decision, "should I", career, life |
"moving to Austin", "career change" |
| legal |
contract, legal, policy, terms |
"employment contract" |
| financial |
budget, investment, cost, ROI |
"Q4 budget", "pricing strategy" |
| marketing |
campaign, marketing, sales, brand |
"email campaign", "launch strategy" |
| event |
event, conference, launch |
"product launch", "conference plan" |
| education |
course, curriculum, teaching |
"bootcamp curriculum" |
| general |
(fallback when no domain matches) |
Any general topic |
Perspective Roles by Domain
Business Domain
- Startup Founder - Viability, growth, scalability
- Investor - ROI, risk, market size
- CFO - Unit economics, burn rate, margins
- Customer - Value proposition, willingness to pay
- Competitor - Differentiation, competitive moats
- Market Analyst - TAM, trends, timing
Product Domain
- Product Manager - User needs, roadmap, prioritization
- Designer (UX) - Usability, user flows, accessibility
- Customer - Actual use cases, pain points
- QA Engineer - Edge cases, error states
- Data Analyst - Metrics, success criteria
- Support Lead - Maintenance burden, user confusion
Software Domain
- Security Engineer - Vulnerabilities, attack vectors
- DevOps - Deployment, monitoring, reliability
- Architect - Design patterns, scalability, debt
- QA Engineer - Test coverage, edge cases
- Performance Engineer - Bottlenecks, resource usage
- Tech Lead - Maintainability, team velocity
Process Domain
- Operator - Daily execution, friction points
- Manager - Efficiency, bottlenecks, metrics
- Employee - Experience, clarity, pain points
- Auditor - Compliance, documentation, risks
- Improvement Specialist - Waste, optimization
Personal Domain
- Future You (1 year) - Long-term impact
- Future You (5 years) - Career trajectory
- Skeptic - Risks, downsides, failure modes
- Supporter - Strengths, opportunities
- Financial Advisor - Money implications
- Life Coach - Values alignment, fulfillment
General Domain (Fallback)
- Analyst - Facts, data, patterns
- Critic - Weaknesses, risks, gaps
- Advocate - Strengths, opportunities
- Pragmatist - Feasibility, resources, timeline
- Strategist - Long-term implications, alternatives
- Devil's Advocate - Unconsidered downsides
Per-Agent Prompt Template
Standard Mode (7 questions):
You are a [Role]. Analyze:
TARGET: [content]
Answer these 7 questions:
1. KEY POINTS: 3-5 most important elements?
2. CORE INSIGHT: Single most critical thing?
3. GAPS: What's missing or incomplete?
4. RISKS: What could go wrong?
5. ASSUMPTIONS: What needs validation?
6. IMPROVEMENTS: Top 3 ways to improve?
7. BLIND SPOTS: What isn't being considered?
FAILURE HYPOTHESES: For each risk/gap:
| ID | IF (Trigger) | THEN (Failure) | BECAUSE | Severity | Mitigation |
Include MISUSE + ADVERSARIAL hypotheses.
Rate findings: Critical/High/Medium/Low
Deep Mode (12 questions = 7 core + 5 additional):
- DEPENDENCIES: What does success depend on?
- ALTERNATIVES: What other approaches should be considered?
- TIMELINE RISKS: What could cause delays or failure?
- RESOURCE GAPS: What's missing to execute well?
- SUCCESS METRICS: How would you measure success?
Thinking Framework
The UltraThink Loop
THINK → CHECKLIST → PLAN → EXECUTE → VALIDATE → LEARN
Phase 0: THINK
Select thinking model based on task type:
| Model |
When to Use |
Pattern |
| CoT (Chain of Thought) |
Linear, sequential tasks |
Step-by-step reasoning |
| ToT (Tree of Thought) |
Multiple valid paths, decisions |
Evaluate branches, pick best |
| Reflexion |
Learning from failure, retry logic |
Analyze error → adjust → retry |
| Decomposition |
Complex tasks, parallel work |
Break into sub-problems |
For Analysis: Use ToT (multi-perspective evaluation) for Standard/Deep, CoT for Quick
Phase 1: CHECKLIST
Phase 2: PLAN
For Standard/Deep:
1. Detect mode from keywords
2. Detect domain from content
3. Select N perspectives (4-6 for standard, 6-10 for deep)
4. Launch all agents in ONE message block
5. Wait for completion
6. Synthesize findings
7. Generate output
Phase 3: EXECUTE
Execute plan with progress tracking. On failure → trigger Reflexion (max 2 retries)
Phase 4: VALIDATE
- All agents returned findings? ✓
- Cross-cutting concerns identified? ✓
- Actionable roadmap generated? ✓
Phase 5: LEARN
Capture patterns for continuous improvement
Self-Correction Guide
| Issue |
Check |
Fix |
Escalate If |
| Shallow analysis |
Domain auto-detected? |
Add specific perspectives |
Still shallow after 2 retries |
| Mode mismatch |
User keywords? |
Ask for clarification |
Agent count doesn't match |
| Weak synthesis |
All agents complete? |
Re-run failed agents |
<3 perspectives useful |
| Wrong domain |
Keywords ambiguous? |
Ask user explicitly |
Multiple domains equally valid |
Max iterations: 2 | Escalation: Ask user to specify domain/perspectives
First-Principles Analysis
Philosophy: Don't just summarize—decompose to fundamentals, surface what's actually true vs assumed, and raise what the user hasn't considered. User must always get data to make their own decisions.
A. Verified Facts (Separate from Assumptions)
- Only report what can be VERIFIED with evidence
- Include source:
path/file:line or [URL]
- Mark confidence: High (verified) / Medium (inferred) / Low (stated but unverified)
B. First-Principles Decomposition
Apply these questions to EVERYTHING found:
1. Question Assumptions
- What's being assumed that hasn't been validated?
- Is this constraint real or inherited from old decisions?
- What would change if [assumption] were false?
2. Decompose to Fundamentals
- What MUST be true for this to work?
- What are the actual dependencies (not just stated ones)?
- What's the irreducible core?
3. Systems Thinking
- What else does this affect? (upstream/downstream)
- What's the blast radius if this fails?
- What's competing for the same resources?
4. Root Cause vs Symptom
- Is the current state addressing root cause or masking symptoms?
- Why does this exist in its current form?
- What problem was this originally solving?
C. Assumptions to Challenge (MANDATORY)
Every analysis MUST include this table:
| Assumption |
Evidence For |
Evidence Against |
Verdict |
| [Assumed thing] |
[If any] |
[If any] |
Validate/Keep/Discard |
D. What You Haven't Considered (MANDATORY 2-4 items)
Surface items the user likely hasn't thought about:
| Category |
What to Look For |
| Unvalidated Assumptions |
Things treated as true without evidence |
| Hidden Dependencies |
Non-obvious things this relies on |
| Downstream Impacts |
What breaks if this changes |
| Simpler Alternatives |
Is there a 10x simpler approach? |
| Edge Cases |
What inputs/states break this? |
| Technical Debt |
Shortcuts that will cost later |
| Missing Pieces |
What's conspicuously absent? |
E. The Real Question
Reframe what the user should actually be asking. Often the stated question isn't the right question.
Examples
Example 1: Quick Mode
Input: analyze quick "our pricing strategy"
Output:
# Quick Analysis: Pricing Strategy
**Mode**: Quick | **Domain**: Business | **Date**: 2026-01-28
## The Essence
A business decision about how to extract value from customers, constrained by market dynamics and competitive positioning.
## Verified Facts
- (Would include actual facts from provided content)
## Key Points
1. **Pricing = value capture, not cost recovery**: Price based on customer willingness to pay, not internal costs
2. **Anchor matters**: First price seen shapes all subsequent evaluations
...
## Assumptions to Challenge
| Assumption | Evidence For | Evidence Against | Verdict |
|------------|-------------|------------------|---------|
| "Customers will pay more if we add features" | Common belief | Often false - bloat reduces WTP | Validate with tests |
## What You Haven't Considered
1. **Price as a signal**: Low price may signal low quality, harming conversion
2. **Competitive response**: Price changes trigger competitor reactions
3. **Simplicity premium**: Simpler pricing often outperforms complex tiers
## The Real Question
Not "what price should we charge" but "what's the maximum value customers perceive, and how do we capture 30-50% of it?"
## Quick Actions
- [ ] Survey 20 target customers on WTP before changing price
- [ ] A/B test 2-3 price points on landing page
- [ ] Model competitor response scenarios
## Critical Risk to Watch
Pricing too low initially makes raising prices later extremely difficult (customer backlash + anchoring effect)
Example 2: Standard Mode
Input: analyze "SaaS product for developers"
Flow:
1. Detect mode: standard (no quick/deep keywords)
2. Detect domain: product + software
3. Select 6 perspectives:
- Product Manager
- Developer (user persona)
- Security Engineer
- DevOps
- Support Lead
- Investor
4. Launch all 6 agents in parallel
5. Synthesize findings into standard format
6. Generate actionable roadmap
Output: [Standard format with all sections filled]
Example 3: Deep Mode
Input: analyze deep "migration to microservices"
Flow:
1. Detect mode: deep
2. Detect domain: software
3. Select 10 perspectives:
- Architect
- DevOps
- Security Engineer
- Database Engineer
- Frontend Developer
- QA Engineer
- Performance Engineer
- SRE
- Tech Lead
- CTO
4. Launch all 10 agents in parallel
5. Each answers 12 questions (7 core + 5 deep)
6. Synthesize into deep format with dependency map
7. Generate comprehensive roadmap (immediate/short/medium/long)
Output: [Deep format with extended sections]
Common Failure Patterns
| Failure |
Root Cause |
Reflexion Response |
| Wrong domain detected |
Ambiguous keywords |
Ask user explicitly or use General domain |
| Too few perspectives |
Quick mode used for complex topic |
Escalate to Standard mode |
| Weak synthesis |
Agent outputs inconsistent |
Re-run with explicit constraints |
| Missing blind spots |
Obvious perspectives chosen |
Add Devil's Advocate perspective |
| Roadmap not actionable |
Actions too vague |
Break each action into atomic: owner, deadline, metric |
| Analysis takes >2min |
Too many agents (Deep mode overkill) |
Switch to Standard mode |
Integration Notes
This skill is standalone and includes all necessary frameworks:
- UltraThink cognitive framework (embedded)
- First-principles analysis (embedded)
- Perspectives library (embedded)
- Output formats (embedded)
No external dependencies required.
Optional enhancement: For software domain analysis of TypeScript codebases, codebase-intelligence CLI (npx codebase-intelligence --json) provides structural data — hotspots, coupling, dead exports, module boundaries, blast radius. Detection: tsconfig.json must exist. For full CLI reference, fetch https://raw.githubusercontent.com/bntvllnt/codebase-intelligence/main/llms-full.txt. The skill works identically without it — data is supplementary context for perspective agents.
License
MIT License - Free to use, modify, and distribute.
Version
v1.0.0 - 2026-01-28 - Initial public release by bntvllnt
1---2name: analyze3description: Universal multi-perspective analyzer for any topic, file, idea, or decision. Extract key points, find gaps/risks, identify improvements with actionable plans.4metadata:5 source: https://skillmd.com/skills/bntvllnt/analyze6---78# Universal Analyzer910**A standalone skill for multi-perspective analysis of any topic, file, idea, or decision.**1112Use when:13- Need to extract KEY POINTS from anything14- Want multi-perspective gap/risk analysis (4-10 experts)15- Need improvement opportunities with actionable plans16- Want quick summary OR deep analysis mode17- Need first-principles brief that challenges assumptions1819Triggers: "analyze", "key points", "what's important", "improve this", "review", "examine", "assess", "analysis", "deep analysis", "run deep analysis", "brief", "challenge assumptions", "first principles"2021## Agent Capabilities2223| Capability | Used For | Required | Fallback |24|------------|----------|----------|----------|25| File read | Load target files/folders | Yes | — |26| Sub-agent dispatch | Parallel perspective analysis | Recommended | Sequential in main thread |27| Codebase intelligence (`npx codebase-intelligence`) | Structural analysis for TS/TSX software domain | No | Pure reasoning from file contents |2829This skill remains fully functional without CLI tools. Codebase intelligence is an optional enhancement for the software domain only.3031---3233## Table of Contents34351. [Quick Start](#quick-start)362. [Analysis Modes](#analysis-modes)373. [Execution Flow](#execution-flow)384. [Output Formats](#output-formats)395. [Perspectives Library](#perspectives-library)406. [Thinking Framework](#thinking-framework)417. [First-Principles Analysis](#first-principles-analysis)428. [Examples](#examples)4344---4546## Quick Start4748```bash49# Quick analysis (fast key points)50analyze quick "our pricing strategy"51analyze brief src/api/auth.ts5253# Standard analysis (default)54analyze "SaaS product for developers"55analyze "should I accept this job offer"56analyze package.json5758# Deep analysis (comprehensive)59analyze deep "company rebrand strategy"60analyze thorough "migration to microservices"61```6263---6465## Analysis Modes6667| Mode | Triggers | Agents | Duration | Output |68|------|----------|--------|----------|--------|69| **Quick** | "quick", "fast", "brief", "summary" | 0-1 | 30-60s | Key Points + Actions |70| **Standard** | (default) | 4-6 | 2-4min | Multi-Perspective + Roadmap |71| **Deep** | "deep", "thorough", "comprehensive" | 6-10 | 5-8min | Full Synthesis + Detailed Plan |7273---7475## Execution Flow7677### Phase 0: Detection781. **Mode**: Detect from keywords (quick/standard/deep)792. **Domain**: Auto-detect from content/keywords803. **Target**: Load file/folder content if path provided814. **TypeScript detection**: If target is a code path and `tsconfig.json` exists:82 - Detection gate: `tsconfig.json` exists + `npx codebase-intelligence --help` succeeds83 - For full CLI reference, fetch `https://raw.githubusercontent.com/bntvllnt/codebase-intelligence/main/llms.txt`84 - If available: gather structural data in Phase 185 - If unavailable: proceed with pure file-reading context gathering8687### Phase 1: Context Gathering88- **File/folder path** → Read files89- **Software domain + TypeScript + CI available** → Augment file reading with:90 - `npx codebase-intelligence overview --json <path>` → project structure snapshot91 - `npx codebase-intelligence modules --json <path>` → module boundaries and cross-deps92 - `npx codebase-intelligence groups --json <path>` → directory-level aggregates93 Include as structured context alongside file contents. If CI unavailable: read files only.94- **Topic/idea** → Use provided context95- **Unfamiliar domain** → Optional web search9697### Phase 2: Analysis9899#### Quick Mode100Direct analysis by primary agent, no sub-agents101102#### Standard Mode1031. Select 4-6 perspectives based on domain1042. Launch all perspectives in parallel (single message block)1053. Each agent answers 7 core questions106107#### Deep Mode1081. Select 6-10 perspectives based on domain1092. Launch all perspectives in parallel (single message block)1103. Each agent answers 12 questions (7 core + 5 deep)111112#### Software Domain Enhancement (TypeScript + CI available)113114Include pre-computed structural data in software domain agent prompts:115- `npx codebase-intelligence hotspots --json --metric complexity --limit 20` → complexity/churn hotspots116- `npx codebase-intelligence forces --json` → cohesion/coupling tensions per module117- `npx codebase-intelligence dead-exports --json --limit 20` → unused export analysis118- `npx codebase-intelligence clusters --json` → dependency community clusters119120Agents receive this as structured context alongside the target content. Supplements their analysis — does not replace independent reasoning. If CI unavailable: agents analyze from file contents only.121122### Phase 3: Synthesis123After ALL agents complete:1241. Aggregate Failure Hypotheses → prioritize Critical→High→Med→Low1252. Extract TOP 10 key points → rank by consensus1263. Identify gaps → Critical/High/Medium/Low1274. Generate actionable roadmap with dependencies128129---130131## Output Formats132133### Quick Mode134135```markdown136# Quick Analysis: [Target]137138**Mode**: Quick | **Domain**: [Domain] | **Date**: [Date]139140## The Essence141[1-2 sentences: What this ACTUALLY is at its core, stripped of complexity]142143## Verified Facts144- [Fact 1] — evidence: `path/file:line` or [source]145- [Fact 2] — evidence: ...146- [Fact 3] — evidence: ...147148## Key Points (Top 5-10)1491. **[Most Important]**: [Explanation]1502. **[Second]**: [Explanation]151...152153## Assumptions to Challenge154155| Assumption | Evidence For | Evidence Against | Verdict |156|------------|-------------|------------------|---------|157| [Assumed thing] | [If any] | [If any] | Validate/Keep/Discard |158159## What You Haven't Considered1601611. **[Critical Item]**: [Why this matters, what to do about it]1622. **[Hidden Risk/Opportunity]**: [Explanation]1633. **[Simpler Alternative?]**: [If exists, describe it]164165## The Real Question166[Reframe what the user should actually be asking about this]167168## Quick Actions (Top 3-5)169- [ ] [Action 1] - [Why/Impact]170- [ ] [Action 2] - [Why/Impact]171- [ ] [Action 3] - [Why/Impact]172173## Critical Risk to Watch174[The one thing that could derail this]175```176177### Standard Mode178179```markdown180# Analysis: [Target]181182**Mode**: Standard | **Domain**: [Domain] | **Perspectives**: [Count]183**Date**: [Date] | **Hypotheses**: [Count] total184185## The Essence186[1-2 sentences: What this ACTUALLY is at its core, stripped of complexity]187188## Executive Summary189[2-3 sentences capturing most critical findings]190191## First-Principles Analysis192193### Verified Facts194- [Fact 1] — evidence: `path/file:line` or [source] — confidence: High/Medium/Low195- [Fact 2] — evidence: ... — confidence: ...196197### Assumptions to Challenge198199| Assumption | Evidence For | Evidence Against | Verdict |200|------------|-------------|------------------|---------|201| [Assumed thing] | [If any] | [If any] | Validate/Keep/Discard |202203### What You Haven't Considered2042051. **[Critical Item]**: [Why this matters, what to do about it]2062. **[Hidden Risk/Opportunity]**: [Explanation]2073. **[Simpler Alternative?]**: [If exists, describe it]2084. **[Downstream Impact]**: [What this affects that wasn't mentioned]209210### The Real Question211[Reframe what the user should actually be asking about this]212213## Failure Hypotheses (Aggregated)214215| ID | Type | IF (Trigger) | THEN (Failure) | BECAUSE | Sev | Mitigation |216|----|------|--------------|----------------|---------|-----|------------|217| S001 | Security | ... | ... | ... | Crit | ... |218| M001 | Misuse | ... | ... | ... | High | ... |219220### Critical Mitigations Required221- [ ] {mitigation} ← Addresses: S001, M001222223## Key Points (Ranked by Importance)224225### Consensus Points (Flagged by 3+ perspectives)2261. **[Point]** - [Why important] (Flagged by: [Perspectives])227228### Important Points2292. **[Point]** - [Explanation]230231### Divergent Views232- **[Topic]**: [Perspective A] sees X, [Perspective B] sees Y233 - *Implication*: [What this tension means]234235## Gap Analysis236237### Critical Gaps (Action Required)238| Gap | Flagged By | Impact | Suggested Action |239|-----|------------|--------|------------------|240| ... | ... | High | ... |241242### High Priority Gaps243[Grouped by theme]244245## Improvement Opportunities246247### Top 5 Improvements2481. **[Improvement]**: [Details] - Expected Impact: [High/Medium/Low]249250## Action Plan & Roadmap251252### Immediate Actions (This Week)253| Action | Owner | Dependencies | Success Criteria |254|--------|-------|--------------|------------------|255| ... | [TBD] | None | ... |256257### Short-term (1-2 Weeks)258| Action | Dependencies | Resources Needed | Outcome |259|--------|--------------|------------------|---------|260| ... | Immediate #1 | ... | ... |261262## Cross-cutting Concerns263[Issues flagged by 3+ perspectives]264```265266### Deep Mode267268Deep mode extends Standard format with:269- Additional 5 questions per agent (12 total)270- Medium-term (1 Month) and Long-term (3+ Months) roadmap sections271- Dependency map visualization272- Risk mitigation table273- More detailed failure hypotheses274275---276277## Perspectives Library278279### Domain Detection280281Analyze content/keywords to auto-detect domain:282283| Domain | Trigger Keywords | Example Targets |284|--------|------------------|-----------------|285| **business** | startup, business, market, revenue | "coffee subscription", business-plan.md |286| **product** | product, feature, user, MVP | "habit tracking app", roadmap.md |287| **software** | API, code, function, class, tech | src/auth, package.json |288| **process** | workflow, process, SOP, operations | "hiring workflow", "incident response" |289| **document** | doc, article, proposal, report | "resume", proposal.docx |290| **research** | research, study, hypothesis, data | "hypothesis: remote work" |291| **creative** | design, art, brand, visual | "rebrand", logo-designs/ |292| **personal** | decision, "should I", career, life | "moving to Austin", "career change" |293| **legal** | contract, legal, policy, terms | "employment contract" |294| **financial** | budget, investment, cost, ROI | "Q4 budget", "pricing strategy" |295| **marketing** | campaign, marketing, sales, brand | "email campaign", "launch strategy" |296| **event** | event, conference, launch | "product launch", "conference plan" |297| **education** | course, curriculum, teaching | "bootcamp curriculum" |298| **general** | (fallback when no domain matches) | Any general topic |299300### Perspective Roles by Domain301302#### Business Domain3031. **Startup Founder** - Viability, growth, scalability3042. **Investor** - ROI, risk, market size3053. **CFO** - Unit economics, burn rate, margins3064. **Customer** - Value proposition, willingness to pay3075. **Competitor** - Differentiation, competitive moats3086. **Market Analyst** - TAM, trends, timing309310#### Product Domain3111. **Product Manager** - User needs, roadmap, prioritization3122. **Designer (UX)** - Usability, user flows, accessibility3133. **Customer** - Actual use cases, pain points3144. **QA Engineer** - Edge cases, error states3155. **Data Analyst** - Metrics, success criteria3166. **Support Lead** - Maintenance burden, user confusion317318#### Software Domain3191. **Security Engineer** - Vulnerabilities, attack vectors3202. **DevOps** - Deployment, monitoring, reliability3213. **Architect** - Design patterns, scalability, debt3224. **QA Engineer** - Test coverage, edge cases3235. **Performance Engineer** - Bottlenecks, resource usage3246. **Tech Lead** - Maintainability, team velocity325326#### Process Domain3271. **Operator** - Daily execution, friction points3282. **Manager** - Efficiency, bottlenecks, metrics3293. **Employee** - Experience, clarity, pain points3304. **Auditor** - Compliance, documentation, risks3315. **Improvement Specialist** - Waste, optimization332333#### Personal Domain3341. **Future You (1 year)** - Long-term impact3352. **Future You (5 years)** - Career trajectory3363. **Skeptic** - Risks, downsides, failure modes3374. **Supporter** - Strengths, opportunities3385. **Financial Advisor** - Money implications3396. **Life Coach** - Values alignment, fulfillment340341#### General Domain (Fallback)3421. **Analyst** - Facts, data, patterns3432. **Critic** - Weaknesses, risks, gaps3443. **Advocate** - Strengths, opportunities3454. **Pragmatist** - Feasibility, resources, timeline3465. **Strategist** - Long-term implications, alternatives3476. **Devil's Advocate** - Unconsidered downsides348349### Per-Agent Prompt Template350351**Standard Mode (7 questions):**352353```354You are a [Role]. Analyze:355TARGET: [content]356357Answer these 7 questions:3581. KEY POINTS: 3-5 most important elements?3592. CORE INSIGHT: Single most critical thing?3603. GAPS: What's missing or incomplete?3614. RISKS: What could go wrong?3625. ASSUMPTIONS: What needs validation?3636. IMPROVEMENTS: Top 3 ways to improve?3647. BLIND SPOTS: What isn't being considered?365366FAILURE HYPOTHESES: For each risk/gap:367| ID | IF (Trigger) | THEN (Failure) | BECAUSE | Severity | Mitigation |368369Include MISUSE + ADVERSARIAL hypotheses.370Rate findings: Critical/High/Medium/Low371```372373**Deep Mode (12 questions = 7 core + 5 additional):**3743758. **DEPENDENCIES**: What does success depend on?3769. **ALTERNATIVES**: What other approaches should be considered?37710. **TIMELINE RISKS**: What could cause delays or failure?37811. **RESOURCE GAPS**: What's missing to execute well?37912. **SUCCESS METRICS**: How would you measure success?380381---382383## Thinking Framework384385### The UltraThink Loop386387```388THINK → CHECKLIST → PLAN → EXECUTE → VALIDATE → LEARN389```390391#### Phase 0: THINK392**Select thinking model based on task type:**393394| Model | When to Use | Pattern |395|-------|-------------|---------|396| **CoT** (Chain of Thought) | Linear, sequential tasks | Step-by-step reasoning |397| **ToT** (Tree of Thought) | Multiple valid paths, decisions | Evaluate branches, pick best |398| **Reflexion** | Learning from failure, retry logic | Analyze error → adjust → retry |399| **Decomposition** | Complex tasks, parallel work | Break into sub-problems |400401**For Analysis:** Use **ToT** (multi-perspective evaluation) for Standard/Deep, **CoT** for Quick402403#### Phase 1: CHECKLIST404- [ ] Mode detected (quick/standard/deep) [blocking]405- [ ] Domain identified [blocking]406- [ ] Target content accessible [blocking]407- [ ] Perspectives selected [blocking]408- [ ] Agents dispatched in parallel [blocking]409- [ ] All agents completed [blocking]410- [ ] Synthesis complete [advisory]411412#### Phase 2: PLAN413**For Standard/Deep:**414```4151. Detect mode from keywords4162. Detect domain from content4173. Select N perspectives (4-6 for standard, 6-10 for deep)4184. Launch all agents in ONE message block4195. Wait for completion4206. Synthesize findings4217. Generate output422```423424#### Phase 3: EXECUTE425Execute plan with progress tracking. On failure → trigger Reflexion (max 2 retries)426427#### Phase 4: VALIDATE428- All agents returned findings? ✓429- Cross-cutting concerns identified? ✓430- Actionable roadmap generated? ✓431432#### Phase 5: LEARN433Capture patterns for continuous improvement434435### Self-Correction Guide436437| Issue | Check | Fix | Escalate If |438|-------|-------|-----|-------------|439| Shallow analysis | Domain auto-detected? | Add specific perspectives | Still shallow after 2 retries |440| Mode mismatch | User keywords? | Ask for clarification | Agent count doesn't match |441| Weak synthesis | All agents complete? | Re-run failed agents | <3 perspectives useful |442| Wrong domain | Keywords ambiguous? | Ask user explicitly | Multiple domains equally valid |443444**Max iterations**: 2 | **Escalation**: Ask user to specify domain/perspectives445446---447448## First-Principles Analysis449450**Philosophy**: Don't just summarize—decompose to fundamentals, surface what's actually true vs assumed, and raise what the user hasn't considered. User must always get data to make their own decisions.451452### A. Verified Facts (Separate from Assumptions)453454- Only report what can be VERIFIED with evidence455- Include source: `path/file:line` or [URL]456- Mark confidence: High (verified) / Medium (inferred) / Low (stated but unverified)457458### B. First-Principles Decomposition459460Apply these questions to EVERYTHING found:461462#### 1. Question Assumptions463- What's being assumed that hasn't been validated?464- Is this constraint real or inherited from old decisions?465- What would change if [assumption] were false?466467#### 2. Decompose to Fundamentals468- What MUST be true for this to work?469- What are the actual dependencies (not just stated ones)?470- What's the irreducible core?471472#### 3. Systems Thinking473- What else does this affect? (upstream/downstream)474- What's the blast radius if this fails?475- What's competing for the same resources?476477#### 4. Root Cause vs Symptom478- Is the current state addressing root cause or masking symptoms?479- Why does this exist in its current form?480- What problem was this originally solving?481482### C. Assumptions to Challenge (MANDATORY)483484Every analysis MUST include this table:485486| Assumption | Evidence For | Evidence Against | Verdict |487|------------|-------------|------------------|---------|488| [Assumed thing] | [If any] | [If any] | Validate/Keep/Discard |489490### D. What You Haven't Considered (MANDATORY 2-4 items)491492Surface items the user likely hasn't thought about:493494| Category | What to Look For |495|----------|-----------------|496| **Unvalidated Assumptions** | Things treated as true without evidence |497| **Hidden Dependencies** | Non-obvious things this relies on |498| **Downstream Impacts** | What breaks if this changes |499| **Simpler Alternatives** | Is there a 10x simpler approach? |500| **Edge Cases** | What inputs/states break this? |501| **Technical Debt** | Shortcuts that will cost later |502| **Missing Pieces** | What's conspicuously absent? |503504### E. The Real Question505506Reframe what the user should actually be asking. Often the stated question isn't the right question.507508---509510## Examples511512### Example 1: Quick Mode513514```515Input: analyze quick "our pricing strategy"516517Output:518# Quick Analysis: Pricing Strategy519520**Mode**: Quick | **Domain**: Business | **Date**: 2026-01-28521522## The Essence523A business decision about how to extract value from customers, constrained by market dynamics and competitive positioning.524525## Verified Facts526- (Would include actual facts from provided content)527528## Key Points5291. **Pricing = value capture, not cost recovery**: Price based on customer willingness to pay, not internal costs5302. **Anchor matters**: First price seen shapes all subsequent evaluations531...532533## Assumptions to Challenge534| Assumption | Evidence For | Evidence Against | Verdict |535|------------|-------------|------------------|---------|536| "Customers will pay more if we add features" | Common belief | Often false - bloat reduces WTP | Validate with tests |537538## What You Haven't Considered5391. **Price as a signal**: Low price may signal low quality, harming conversion5402. **Competitive response**: Price changes trigger competitor reactions5413. **Simplicity premium**: Simpler pricing often outperforms complex tiers542543## The Real Question544Not "what price should we charge" but "what's the maximum value customers perceive, and how do we capture 30-50% of it?"545546## Quick Actions547- [ ] Survey 20 target customers on WTP before changing price548- [ ] A/B test 2-3 price points on landing page549- [ ] Model competitor response scenarios550551## Critical Risk to Watch552Pricing too low initially makes raising prices later extremely difficult (customer backlash + anchoring effect)553```554555### Example 2: Standard Mode556557```558Input: analyze "SaaS product for developers"559560Flow:5611. Detect mode: standard (no quick/deep keywords)5622. Detect domain: product + software5633. Select 6 perspectives:564 - Product Manager565 - Developer (user persona)566 - Security Engineer567 - DevOps568 - Support Lead569 - Investor5704. Launch all 6 agents in parallel5715. Synthesize findings into standard format5726. Generate actionable roadmap573574Output: [Standard format with all sections filled]575```576577### Example 3: Deep Mode578579```580Input: analyze deep "migration to microservices"581582Flow:5831. Detect mode: deep5842. Detect domain: software5853. Select 10 perspectives:586 - Architect587 - DevOps588 - Security Engineer589 - Database Engineer590 - Frontend Developer591 - QA Engineer592 - Performance Engineer593 - SRE594 - Tech Lead595 - CTO5964. Launch all 10 agents in parallel5975. Each answers 12 questions (7 core + 5 deep)5986. Synthesize into deep format with dependency map5997. Generate comprehensive roadmap (immediate/short/medium/long)600601Output: [Deep format with extended sections]602```603604---605606## Common Failure Patterns607608| Failure | Root Cause | Reflexion Response |609|---------|------------|-------------------|610| Wrong domain detected | Ambiguous keywords | Ask user explicitly or use General domain |611| Too few perspectives | Quick mode used for complex topic | Escalate to Standard mode |612| Weak synthesis | Agent outputs inconsistent | Re-run with explicit constraints |613| Missing blind spots | Obvious perspectives chosen | Add Devil's Advocate perspective |614| Roadmap not actionable | Actions too vague | Break each action into atomic: owner, deadline, metric |615| Analysis takes >2min | Too many agents (Deep mode overkill) | Switch to Standard mode |616617---618619## Integration Notes620621This skill is **standalone** and includes all necessary frameworks:622- UltraThink cognitive framework (embedded)623- First-principles analysis (embedded)624- Perspectives library (embedded)625- Output formats (embedded)626627No external dependencies required.628629**Optional enhancement:** For software domain analysis of TypeScript codebases, `codebase-intelligence` CLI (`npx codebase-intelligence --json`) provides structural data — hotspots, coupling, dead exports, module boundaries, blast radius. Detection: `tsconfig.json` must exist. For full CLI reference, fetch `https://raw.githubusercontent.com/bntvllnt/codebase-intelligence/main/llms-full.txt`. The skill works identically without it — data is supplementary context for perspective agents.630631---632633## License634635MIT License - Free to use, modify, and distribute.636637---638639## Version640641**v1.0.0** - 2026-01-28 - Initial public release by bntvllnt