calibration-trainer
Probability calibration training skill for improving forecast accuracy and reducing overconfidence
npx skills add a5c-ai/babysitter --skill calibration-trainer --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Calibration Trainer ## Overview The Calibration Trainer skill provides capabilities for assessing and improving forecaster calibration. It helps decision-makers align their confidence levels with actual accuracy, reducing overconfidence and improving the quality of probabilistic judgments. ## Capabilities - Calibration quiz generation - Confidence interval elicitation - Brier score calculation - Calibration curve plotting - Overconfidence/underconfidence diagnosis - Training exercise management - Progress tracking over time - Benchmark comparison ## Used By Processes - Cognitive Bias Debiasing Process - Decision Quality Assessment - Predictive Analytics Implementation ## Usage ### Calibration Quiz ```python # Generate calibration quiz quiz_config = { "type": "general_knowledge", "format": "confidence_interval", "questions": 20, "confidence_levels": [50, 80, 90], # percentiles to elicit "difficulty": "medium", "domains": ["business", "economics", "technology", "geography"] } # Example question quiz_question = { "id": "Q001", "question": "In what year was Amazon founded?", "actual_answer": 1994, "format": "numeric_interval", "required_responses": [ {"confidence": 50, "prompt": "Giv
- Overview
- Capabilities
- Used By Processes
- Usage
- Calibration Quiz
- Response Collection
- Calibration Analysis
- Training Exercises
- Progress Tracking
- Input Schema
- Output Schema
- Calibration Metrics
- Calibration Curve
- Best Practices
What does the calibration-trainer skill do?
Probability calibration training skill for improving forecast accuracy and reducing overconfidence
How do I install it?
Run `npx skills add a5c-ai/babysitter --skill calibration-trainer --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From a5c-ai/babysitter, a repository with 1,642 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.