Intuitive OS Skill
Non-negotiables
- Intuition is a hypothesis or signal, never automatic truth.
- Capture the raw intuition before analytical contamination.
- Separate observation, interpretation, emotion, prediction, and decision.
- Convert meaningful forecasts into probabilities when resolvable.
- Preserve original predictions. Never rewrite history after outcomes.
- Score domains separately. Expertise does not transfer automatically.
- Seek disconfirming evidence and relevant base rates.
- Distinguish decision quality from outcome quality.
- Avoid pseudo-scientific body-language certainty and mind-reading.
- For safety-critical, medical, legal, financial, or high-stakes decisions, intuition may generate questions but should not replace appropriate evidence or expert review.
Modes
CAPTURE, SIGNAL, PREDICT, DECIDE, RED_TEAM, REVIEW, TRAIN, PROFILE.
Classification
For every important intuition, consider:
- expert pattern
- weak signal
- affect/emotion
- incentive recognition
- bias/stereotype
- noise/unknown
Multiple labels may coexist. Never force certainty.
Minimum prediction record
ID, timestamp, domain, proposition, probability, horizon/resolution date, observable signals, base rate if known, counter-evidence, decision/action, outcome, review.
Calibration
Prefer proper scoring such as Brier score for binary predictions. Also report calibration buckets (50-59, 60-69, etc.), sample size, and domain. Never imply statistical reliability from tiny samples.
Learning loop
Capture -> Explain signals -> Generate alternatives -> Estimate probability -> Decide -> Resolve -> Diagnose -> Update pattern library.
1---2name: intuitive-os3description: Train, test and calibrate intuition as a measurable skill, spanning raw intuition capture before analytical contamination, five-layer separation (observation, interpretation, affect, intuition, decision), intuition provenance (expert pattern, weak signal, emotion, incentive signal, bias, noise), falsifiable probabilistic forecasting with resolution criteria, base rates and Bayesian updating, decision journaling and premortems, red-teaming a hunch, Brier scoring and calibration buckets by domain, pattern-card and mental-model libraries, and a 90-day observe/calibrate/compress curriculum. Use for gut-feel checks, should-I-trust-this-instinct questions, forecasting and prediction logging, decision protocols and reviews, separating decision quality from outcome quality, spotting bias in your own judgment, weak-signal analysis, overconfidence and calibration audits, and intuition training plans. Trigger words: intuition, gut feeling, instinct, hunch, calibration, forecast, prediction, Brier, base rate, decision jo4---56# Intuitive OS Skill78## Non-negotiables91. Intuition is a hypothesis or signal, never automatic truth.102. Capture the raw intuition before analytical contamination.113. Separate observation, interpretation, emotion, prediction, and decision.124. Convert meaningful forecasts into probabilities when resolvable.135. Preserve original predictions. Never rewrite history after outcomes.146. Score domains separately. Expertise does not transfer automatically.157. Seek disconfirming evidence and relevant base rates.168. Distinguish decision quality from outcome quality.179. Avoid pseudo-scientific body-language certainty and mind-reading.1810. For safety-critical, medical, legal, financial, or high-stakes decisions, intuition may generate questions but should not replace appropriate evidence or expert review.1920## Modes21CAPTURE, SIGNAL, PREDICT, DECIDE, RED_TEAM, REVIEW, TRAIN, PROFILE.2223## Classification24For every important intuition, consider:25- expert pattern26- weak signal27- affect/emotion28- incentive recognition29- bias/stereotype30- noise/unknown3132Multiple labels may coexist. Never force certainty.3334## Minimum prediction record35ID, timestamp, domain, proposition, probability, horizon/resolution date, observable signals, base rate if known, counter-evidence, decision/action, outcome, review.3637## Calibration38Prefer proper scoring such as Brier score for binary predictions. Also report calibration buckets (50-59, 60-69, etc.), sample size, and domain. Never imply statistical reliability from tiny samples.3940## Learning loop41Capture -> Explain signals -> Generate alternatives -> Estimate probability -> Decide -> Resolve -> Diagnose -> Update pattern library.
agentik-os