Critical Intuition

---
name: critical-intuition
description: Stress-test, critique, and challenge existing ideas through pattern recognition, bias detection, Bayesian reasoning, blind-spot exposure, and red-flag identification. Use when the user asks to stress-test a plan, challenge assumptions, find flaws, identify risks in an idea, expose hidden biases, audit a proposal for blind spots, or "poke holes in this". NOT for generating new ideas or solutions (use creative-problem-solving), NOT for structured risk registers or mitigation plans (use risk-management), NOT for brainstorming or divergent thinking (use creative-problem-solving).
---

# Critical Intuition & Sixth Sense

Stress-test existing ideas and detect hidden patterns. Backward-looking, convergent analysis — complements creative-problem-solving (forward-looking, divergent generation).

## When to Use / Not Use

**Use when:**
- Reading between the lines on proposals, communications, or situations
- Identifying what is missing, hidden, or unstated
- Critically evaluating arguments, evidence, or reasoning
- Detecting early warning signs or red flags
- Synthesizing complex information under uncertainty
- "Something feels off" but you cannot articulate why

**Do NOT use when:**
- Generating new creative solutions -> use `creative-problem-solving`
- Brainstorming or strategic reframing -> use `creative-problem-solving`
- Building structured risk registers -> use `risk-management`
- Making final decisions between options -> use `prioritization`

## Decision Tree

```
What kind of analysis do you need?
├── "What am I missing?" or "What could go wrong?"
│   └── Gap analysis + red flag detection (§Step 2, §Step 6)
├── "Read between the lines" on a document
│   └── Multi-level reading (§Step 1: surface, subtext, meta)
├── "Is this argument/evidence sound?"
│   └── Critical reasoning (§Step 3: argument structure, fallacies, evidence)
├── "How likely is this?" or "What should I believe?"
│   └── Probabilistic assessment (§Step 4: Bayesian, multiple hypotheses)
├── "Something feels off but I can't say why"
│   └── Intuitive synthesis (§Step 5: gestalt, micro-signals)
├── "What should I watch for going forward?"
│   └── Early warning detection (§Step 6: leading indicators, tipping points)
└── Need to GENERATE new ideas, not evaluate existing ones?
    └── Use creative-problem-solving instead
```

## Seven-Step Analysis Process

### Step 1: Multi-Level Reading

| Level | What to Examine | Question |
|-------|----------------|----------|
| Surface | What is explicitly stated | "What are the obvious facts?" |
| Subtext | What is implied but not stated | "What assumptions are embedded? What's conspicuously absent?" |
| Meta | Why it's communicated this way | "What are the incentives? What power dynamics are at play?" |

For techniques, read `references/pattern-recognition.md`.

### Step 2: Signal Detection

- **Pattern recognition**: What patterns emerge? Signal vs. noise? Meta-patterns?
- **Anomaly detection**: What doesn't fit? Discontinuities? Unusually present or absent?
- **Micro-signals**: Timing variations, emphasis patterns, language hedging, topic avoidance
- **Gap analysis**: What information is missing that would normally be present?

For subtle signal detection, read `references/sixth-sense.md`.

### Step 3: Critical Reasoning

- **Argument structure**: Identify premises and conclusions, evaluate logical validity, detect hidden assumptions
- **Fallacy detection**: Formal fallacies, informal fallacies, statistical fallacies, motivated reasoning
- **Evidence evaluation**: Source credibility, data quality, sample representativeness, confounding factors

For frameworks, read `references/critical-thinking.md`.

### Step 4: Probabilistic Assessment

- **Bayesian thinking**: Prior probability → evidence strength → updated probability → residual uncertainty
- **Multiple hypotheses**: Generate alternatives, assess relative likelihood, identify discriminating evidence
- **Confidence calibration**: How confident should you be? What would change your mind?

### Step 5: Intuitive Synthesis

- **Gestalt perception**: Combine disparate cues, see the whole picture, emergent understanding
- **Cross-domain connections**: Analogical reasoning, structural similarities, principle transfer
- **Tacit knowledge**: Pattern matching without explicit rules — gut feeling as compressed expertise

For synthesis techniques, read `references/synthesis-frameworks.md`.

### Step 6: Early Warning Detection

- **Leading indicators**: Upstream signals, stress accumulation, resilience degradation, variance increases
- **Trajectory sensing**: Momentum assessment, inflection point detection, tipping point proximity
- **Red flag clusters**: Multiple small concerns, coincidence accumulation, pattern breaks

For details, read `references/sixth-sense.md`.

### Step 7: Judgment Formation

- **Information integration**: Combine quantitative and qualitative, triangulate sources, weight by reliability
- **Decision under uncertainty**: Expected value, scenario analysis, robust options
- **Metacognitive check**: How confident am I? What biases might affect me? What am I missing?

## Analysis Depth by Stakes

| Stakes Level | Steps | Techniques |
|---|---|---|
| Low (minor, reversible) | Steps 1-2 + red flag scan | Surface + subtext reading, quick pattern check |
| Medium (significant, partially reversible) | Full 7-step process | All techniques, probabilistic assessment |
| High (irreversible, major consequences) | Full process + extended patterns | Multiple hypothesis testing, explicit metacognitive checks, counter-argument generation |

## Anti-Patterns

| Anti-Pattern | Problem | Solution |
|---|---|---|
| Over-reading: finding signals that aren't there | Every proposal looks suspicious; alarming conclusions from ambiguous data | Calibrate confidence; distinguish high-confidence findings from speculation; require corroborating evidence |
| Analysis paralysis: too many hypotheses | 10 possible interpretations but no recommendation | Force probabilistic ranking; assign relative likelihoods; identify discriminating evidence that would resolve ambiguity |
| Confirmation bias in direction | "Gut feeling" biases analysis toward confirming initial suspicion | Explicit metacognitive check: "What would change my mind?" Generate strongest counter-argument |
| Asking for validation not analysis | "Confirm this is a good plan" biases toward agreement | Ask "What am I missing?" or "What could go wrong?" instead |
| No artifact to analyze | "What do you think about acquisitions generally?" is theory, not analysis | Share the actual document, proposal, or situation details; subtext reading requires actual text |
| Paraphrasing instead of sharing originals | Paraphrasing already filters out the signals the skill would detect | Paste the full document; let the skill read between the actual lines |
| Skipping metacognitive check | Analysis blind to its own biases and gaps | Always complete Step 7: "What biases might affect me? What am I missing?" |
| Creative-problem-solving overlap | Trying to generate solutions with a critique skill | Generate with creative-problem-solving, then evaluate here; they are complementary opposites |

## Validation Checklist

Before finalizing judgment:
- [ ] Read at multiple levels (surface, subtext, meta)?
- [ ] Detected patterns and anomalies?
- [ ] Evaluated reasoning and evidence rigorously?
- [ ] Checked for cognitive biases?
- [ ] Synthesized multiple signals intuitively?
- [ ] Calibrated confidence appropriately?
- [ ] Acknowledged what you don't know?
- [ ] Judgment is actionable and well-grounded?

## Integration

- creative-problem-solving — Generative counterpart: create ideas there, evaluate here
- risk-management — Structured risk frameworks that this skill's pattern detection feeds into
- systems-thinking — Deeper feedback loop analysis for what this skill identifies
- prioritization — Ranking the risks and opportunities this skill surfaces
- outcome-orientation — Define measurable criteria for monitoring early warning indicators

## References

- `references/pattern-recognition.md` — Advanced pattern detection, signal vs. noise, anomaly detection
- `references/critical-thinking.md` — Argument analysis, logical structure, fallacy detection
- `references/sixth-sense.md` — Micro-signals, subtle energy shifts, early warning systems
- `references/synthesis-frameworks.md` — Multi-source synthesis, decision under uncertainty
- `references/extended-patterns.md` — Advanced techniques, red/green flag catalogs, output templates