Agent skill · vasilyu1983
foundations-ai-planning-search
Applies planning and search theory (A*, CSP, MCTS, STRIPS/PDDL, HTN) to agent design. Use when an LLM agent hallucinates action sequences or needs precondition/effect validity.
What it needs
About 9k tokens when loaded.
What this skill does
AI Planning And Search Foundations 10 applied AI planning and search primitives for turning a problem into states, actions, constraints, heuristics, and plans. Use this when the hard part is problem formulation or explicit search over alternatives, not language fluency. Contents Quick Reference When to Apply Primitive Index Formal Supporting Theory Anti-Patterns Misuse Boundaries Decision Checklist Composition Recipes Workflow ASCII Flow Navigation Fact-Checking --- Quick Reference Primitive Problem It Solves Key Parameters ----------- ------------------ ---------------- Problem Formulation Vague tasks cannot be searched or verified State, actions, transition model, goal test, path cost Uninformed Search Need complete baseline without domain heuristic Branching factor b; depth d; frontier policy Heuristic Search Large state spaces need directed exploration Heuristic h(n); admissibility; consistency Local Search State is large but path is irrelevant Neighborhood; objective; restart/schedule Constraint Satisfaction Need assignments satisfying hard constraints Variables, domains, constraints, MRV/LCV, arc consistency Adversarial Search Opponent actions affect outcomes Utility, depth, alpha-beta bounds, rollout policy Classical Planning Need valid action sequence from symbolic preconditions/effects STRIPS/PDDL, progression/regression, plan graph Hierarchical Planning Tasks decompose into reusable subplans Methods, subtasks, ordering constraints Contingent / Belief-State Planning Partial observability or nondeterministic actions Belief state, sensing actions, policy vs sequence Planner-Agent Integration LLM agent needs explicit plan validity and search boundaries Planner tool, state abstraction, verifier, replanning trigger --- When to Apply Apply this skill when: The task can be stated as states, actions, transitions, goals, and costs. You need A, uniform-cost search, beam search, backtracking, alpha-beta, MCTS, STRIPS/PDDL, HTN, or CSP reasoning. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills vasilyu1983/foundations-ai-planning-search