cognitive-architectures
Patterns from SOAR, ACT-R, and LIDA for advanced agent cognitive cycles
npx skills add majiayu000/claude-skill-registry --skill brain-andreibesleaga-gabbe-10 --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.
# Cognitive Architectures for Agents ## Description This skill provides implementation patterns derived from classic and modern Cognitive Architectures (SOAR, ACT-R, LIDA) to structure agent reasoning, memory, and decision-making processes beyond simple prompt engineering. ## 1. SOAR (State, Operator, And Result) **Core Idea:** Intelligence is the ability to solve problems by navigating a "Problem Space" using "Operators." ### Implementation Pattern: Proposal-Evaluation Cycle Instead of a single "think" step, break agent reasoning into distinct phases: 1. **Elaboration**: Calculate all immediate inferences from current state. 2. **Proposal**: Generate candidate operators (actions/thoughts) for the current state. 3. **Evaluation**: Score candidate operators using preferences (heuristics). 4. **Selection**: Pick the best operator. 5. **Application**: Execute it to change the state. **Code Metaphor:** ```python def cognitive_cycle(state): # 1. Elaboration state = enrich_context(state) # 2. Proposal options = generate_candidates(state) # 3. Evaluation scored_options = evaluate_candidates(options, goal=state.goal) # 4. Selection best_op = select_winner(scored_options) # 5. Application n
- Description
- 1. SOAR (State, Operator, And Result)
- Implementation Pattern: Proposal-Evaluation Cycle
- 2. ACT-R (Adaptive Control of Thought-Rational)
- Implementation Pattern: Activation-Based Retrieval
- 3. LIDA (Learning Intelligent Distribution Agent)
- Implementation Pattern: The "Spotlight" of Consciousness
- References
What does the cognitive-architectures skill do?
Patterns from SOAR, ACT-R, and LIDA for advanced agent cognitive cycles
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill brain-andreibesleaga-gabbe-10 --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.