AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Critical Intuition

skill-viktorbezdek-skillstack-critical-intuition · by viktorbezdek

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 (…

No reviews yet
0 installs
29 views
0.0% view→install

Install

$ agentstack add skill-viktorbezdek-skillstack-critical-intuition

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-viktorbezdek-skillstack-critical-intuition)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Critical Intuition? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

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

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.