Statistical Mechanics

Use this skill when the user says 'diffusion model math', 'score matching', 'DDPM', 'Langevin dynamics', 'reverse SDE', 'probability flow ODE', 'Boltzmann distribution', 'energy-based model', 'classifier-free guidance', 'flow matching', 'noise schedule'. Explains the statistical-mechanics view of generative modeling (Boltzmann distributions, Langevin dynamics, forward/reverse diffusion SDEs, score functions) and implements a correct DDPM training and sampling loop. Do NOT use for: using pretrained image generators (ai/genai-vision), information-theoretic losses (fundamental-truths/information-

45 stars 6 forksData & Analytics

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add j4flmao/agent-skills --skill statistical-mechanics
Manual install
git clone --depth 1 https://github.com/j4flmao/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/fundamental-truths/statistical-mechanics ~/.claude/skills/statistical-mechanics

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Statistical Mechanics & Diffusion Models

## Purpose
Diffusion and score-based models borrow directly from statistical physics: data is gradually corrupted by Gaussian noise (a forward diffusion process), and a network learns the score ∇ₓ log pₜ(x) needed to run the process backwards. Softmax temperature, energy-based models, and Langevin sampling share the same Boltzmann foundations. This skill gives the exact equations, how they map to code, and the practical knobs (schedules, parameterization, guidance, samplers).

## Agent Protocol

### Trigger
"diffusion math", "DDPM", "DDIM", "score matching", "score function", "Langevin", "reverse SDE", "probability flow ODE", "noise schedule", "classifier-free guidance", "flow matching", "energy-based model", "Boltzmann".

### Input Context
- Goal: understanding, implementing from scratch, or debugging training/sampling.
- Data type and resolution; compute budget.
- Existing code (if debugging): parameterization (ε, x₀, v), schedule, sampler.

### Output Artifact
Derivation summary with the governing equations and a minimal correct implementation or a diagnosis.

### Response Format
```
Forward: q(x_t|x_0) = N(√ᾱ_t x_0, (1−ᾱ_t) I)  schedule={linear|cosine}, T={n}
Parameterization: {ε|x0|v}-prediction  Loss: {MSE on target}
Sampler: {ancestral DDPM|DDIM|DPM-Solver|ODE}  steps={n}
Guidance: CFG w={value} (p_uncond={x} in training)
Diagnosis: {issue -> fix}
```

### Completion Criteria
Read the full skill on GitHub

Details

Skill name
statistical-mechanics
Path
skills/fundamental-truths/statistical-mechanics/SKILL.md
License
MIT
Repo updated
17 November 2026

FAQ

What does the Statistical Mechanics skill do?

Use this skill when the user says 'diffusion model math', 'score matching', 'DDPM', 'Langevin dynamics', 'reverse SDE', 'probability flow ODE', 'Boltzmann distribution', 'energy-based model', 'classifier-free guidance', 'flow matching', 'noise schedule'. Explains the statistical-mechanics view of generative modeling (Boltzmann distributions, Langevin dynamics, forward/reverse diffusion SDEs, score functions) and implements a correct DDPM training and sampling loop. Do NOT use for: using pretrained image generators (ai/genai-vision), information-theoretic losses (fundamental-truths/information-

How do I install the Statistical Mechanics skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add j4flmao/agent-skills --skill statistical-mechanics. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Statistical Mechanics popular?

It lives in j4flmao/agent-skills, which has 45 GitHub stars and 6 forks.

Related skills

Agent Observability

45

j4flmao/agent-skills

Use when the user asks about agent observability, tracing agent reasoning, debugging an agent loop, OpenTelemetry GenAI spans for LLM calls, LLM cost tracking per agent, agent audit logs or hallucination/eval monitoring in production. Produces instrumentation config, trace schema, dashboards, alerts and cost attribution. Not for generic service tracing without LLMs (use devops-opentelemetry).

DevOps & Cloud

AI Agent Architectures

45

j4flmao/agent-skills

Use when the user asks to build an AI agent, design an agent that calls tools and keeps memory, write an agent system prompt or pick an agent framework (Claude Agent SDK, OpenAI Agents SDK, LangGraph). Produces an architecture brief covering loop, tools, memory, guardrails and evals, routing depth to child skills. Not for workflow patterns (use ai-agentic-workflows).

AI, LLMs & Agents

AI Agent Core Loop

45

j4flmao/agent-skills

Use when the user asks about the agent loop, ReAct vs plan-and-solve, re-planning, Reflexion, an agent stuck in a loop, max iterations or termination conditions. Produces a loop spec or patch with state, success predicate, caps and no-progress detection. Not for overall agent design (use ai-agent-architectures) or tool schemas (use tool-calling-principles).

AI, LLMs & Agents

Tableau Next Implementation Advisor

24

forcedotcom/partner-ecosystem-agentic-kit

Use for Tableau Next scratch enablement, Data 360 dependencies, semantic models, workspaces, visualizations, dashboards, deployment ordering, and integration decisions. Owns Tableau Next implementation and integration decisions relevant to partner solutions.

Data & Analytics

Information Theory

45

j4flmao/agent-skills

Use this skill when the user says 'entropy', 'cross-entropy loss', 'KL divergence', 'perplexity', 'bits per byte', 'mutual information', 'compression is prediction', 'manifold hypothesis', 'intrinsic dimension', 'ELBO'. Explains the information-theoretic quantities behind ML training and evaluation and applies them: interpreting losses and perplexity, KL in distillation/RLHF/VAEs, calibration, and measuring intrinsic dimension of embeddings. Do NOT use for: diffusion/score-based generative math (fundamental-truths/statistical-mechanics), classical statistics and hypothesis tests (data-science/

Data & Analytics

Letterboxd Watchlist

33

dvcrn/openclaw-skills-marketplace

Scrape a public Letterboxd user's watchlist into a CSV/JSONL list of titles and film URLs without logging in. Use when a user asks to export, scrape, or mirror a Letterboxd watchlist, or to build watch-next queues.

Data & Analytics17

Browse the most popular Claude skills, all data & analytics skills, or write your own with the skills generator.