active-inference
Apply Active Inference to minimize prediction error (Surprise).
npx skills add majiayu000/claude-skill-registry --skill brain-andreibesleaga-gabbe-7 --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.
# Active Inference Skill > "Action is the process of changing the world to match your prediction." ## 1. The Concept (Free Energy Principle) Standard agents are "Goal-Directed" (Maximize Reward). **Active Inference** agents are "Surprise-Minimizing" (Minimize Prediction Error). - **Goal:** Not just to "win", but to understand and control. - **Surprise:** The difference between *Expectation* and *Observation*. ## 2. The Feedback Loop 1. **Predict:** "If I run `go test`, it will output PASS." 2. **Act/Sense:** Run the command and read the output. 3. **Compare:** Calculate **Prediction Error**. - *Result:* "FAIL". -> **Surprise!** ## 3. Solving the Error You have two choices to minimize surprise: 1. **Perceptual Inference (Change Mind):** "My model was wrong. The code implies X, not Y." -> Update docs/mental model. 2. **Active Inference (Change World):** "The code is wrong. I will edit it to make the test pass." -> Writes code. ## 4. Epistemic Action (Curiosity) If Surprise is "Unknown" (Uncertainty is high), perform an **Epistemic Action** (Probe/Log) to gain information, rather than a pragmatic action to achieve a goal. ## 5. System Prompt Template ```markdown You are an Active Infe
- 1. The Concept (Free Energy Principle)
- 2. The Feedback Loop
- 3. Solving the Error
- 4. Epistemic Action (Curiosity)
- 5. System Prompt Template
- 6. Implementation (Pythonic Pseudo-code)
What does the active-inference skill do?
Apply Active Inference to minimize prediction error (Surprise).
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill brain-andreibesleaga-gabbe-7 --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.