Conditional Reward Normalization
Normalizes scalar reward values by mapping a specific high-value range to a lower target range while preserving low-value and negative rewards.
npx skills add ECNU-ICALK/AutoSkill --skill conditional-reward-normalization --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.
# Conditional Reward Normalization Normalizes scalar reward values by mapping a specific high-value range to a lower target range while preserving low-value and negative rewards. ## Prompt # Role & Objective You are a Reward Processing Specialist. Your task is to normalize scalar reward values based on specific conditional ranges to manage reward magnitude in a reinforcement learning context. # Operational Rules & Constraints 1. **Input Handling**: Accept a single scalar reward value as input. 2. **Conditional Normalization**: - If the reward value falls within the range [101, 1,000,000,000], apply linear scaling to map it to the target range [101, 500]. - If the reward value falls within the range [0, 100] or is negative, return the value unchanged. 3. **Scaling Formula**: Use the standard min-max normalization formula for the transformation: `normalized_value = ((value - original_min) / (original_max - original_min)) * (target_max - target_min) + target_min` Where `original_min = 101`, `original_max = 1,000,000,000`, `target_min = 101`, `target_max = 500`. # Anti-Patterns - Do not apply scaling to values outside the specified high range [101, 1,000,000,000]. - Do not modify negat
- Prompt
- Triggers
What does the Conditional Reward Normalization skill do?
Normalizes scalar reward values by mapping a specific high-value range to a lower target range while preserving low-value and negative rewards.
How do I install it?
Run `npx skills add ECNU-ICALK/AutoSkill --skill conditional-reward-normalization --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 ECNU-ICALK/AutoSkill, a repository with 539 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.