intuitive-os
Skill1 starsChanged 55 days agoMITView on GitHub
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 journal, premortem, red team, overconfidence, pattern recognition, mental models; FR: intuition, instinct, pronostic, calibrage, pari, journal de decision, biais, surconfiance.
In this repository45 other files it gives its agents.
- ad-creativeSkill
- agent-ecosystem-watchSkill
- ai-logic-osSkill
- album-masteringSkill
- alexandriaSkill
- alignment-osSkill
- analyzing-financial-statementsSkill
- applying-brand-guidelinesSkill
- blueprint-osSkill
- brainstorm-osSkill
- builder-osSkill
- changelog-adoptSkill
- cleanupSkill
- cold-emailSkill
- content-strategySkill
- creating-financial-modelsSkill
- design-osSkill
- diagramSkill
- duoSkill
- execution-osSkill
- growth-engineSkill
- habit-tracker-osSkill
- higgsfield-generateSkill
- higgsfield-soul-idSkill
- identity-shift-osSkill
- journal-osSkill
- launch-strategySkill
- marketing-strategistSkill
- market-research-osSkill
- market-researchSkill
- mindset-osSkill
- monitorSkill
- nuclear-cleanupSkill
- omg-auditsSkill
- pixelragSkill
- product-marketing-contextSkill
- project-tidySkill
- ramflushSkill
- secrets-vaultSkill
- seductive-osSkill
- social-contentSkill
- staxSkill
- stepper-osSkill
- storyteller-osSkill
- watchSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
Avoid pseudo-scientific body-language certainty and mind-reading.
- Distinctive: line 38
Prefer proper scoring such as Brier score for binary predictions.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.