distribution-search
Guidance for finding probability distributions that satisfy specific statistical constraints such as KL divergence targets, entropy requirements, or moment conditions. This skill should be used when tasks involve constructing discrete or continuous probability distributions with specified divergence measures, entropy values, or other distributional properties through numerical optimization.
npx skills add majiayu000/claude-skill-registry --skill distribution-search-letta-ai-skills --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.
# Distribution Search ## Overview This skill provides systematic approaches for finding probability distributions that meet specific statistical constraints. Common tasks include constructing distributions with target KL divergence values (forward or backward), specified entropy, moment constraints, or combinations thereof. The approach emphasizes mathematical analysis before implementation, efficient parameterization, modular code structure, and rigorous verification. ## When to Use This Skill - Finding distributions with specific KL divergence values (forward or backward) - Constructing distributions with target entropy - Searching for distributions satisfying moment constraints - Optimization problems involving probability mass/density functions - Any task requiring numerical search over distribution parameters ## Methodology ### Phase 1: Mathematical Analysis Before Coding Before writing any code, thoroughly analyze the mathematical constraints: **1. Constraint Feasibility** - Determine if a solution exists given the constraints - Calculate bounds on achievable values (e.g., max entropy for given support) - Identify necessary conditions for solution existence **2. Degrees of Fr
- Overview
- When to Use This Skill
- Methodology
- Phase 1: Mathematical Analysis Before Coding
- Phase 2: Efficient Parameterization
- Phase 3: Optimization Strategy
- Phase 4: Code Organization
- Phase 5: Verification
- Common Pitfalls
- Pitfall 1: Full Array Creation for Large Vocabularies
- Pitfall 2: Inconsistent Formula Implementations
- Pitfall 3: Incorrect Masking in KL Divergence
- Pitfall 4: Insufficient Degrees of Freedom
- Pitfall 5: Syntax Errors from Truncated Writes
What does the distribution-search skill do?
Guidance for finding probability distributions that satisfy specific statistical constraints such as KL divergence targets, entropy requirements, or moment conditions. This skill should be used when tasks involve constructing discrete or continuous probability distributions with specified divergence measures, entropy values, or other distributional properties through numerical optimization.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill distribution-search-letta-ai-skills --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 majiayu000/claude-skill-registry, a repository with 534 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.