# Pddl Skills

> Automated Planning utilities for loading PDDL domains and problems, generating plans using classical planners, validating plans, and saving plan outputs. Supports standard PDDL parsing, plan synthesis, and correctness verification.

- Skill: `bishal-pdmsft/pddl-skills-4` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx get-skill add bishal-pdmsft/pddl-skills-4`
- Raw SKILL.md: https://api.skillmd.com/api/skills/bishal-pdmsft/pddl-skills-4/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- License: Proprietary. LICENSE.txt has complete terms
- Author: bishal-pdMSFT (https://skillmd.com/u/bishal-pdmsft)
- Updated: 2026-11-15
- Page: https://skillmd.com/skills/bishal-pdmsft/pddl-skills-4

---


# Setup and Workflow

Before invoking any skill in this bundle, read and follow the instructions in
[`ENVIRONMENT_SETUP.md`](./ENVIRONMENT_SETUP.md). It covers the planner
backend's shared-lease prerequisites that every planning call depends on.

# Requirements for Outputs

## General Guidelines

### PDDL Files
- Domain files must follow PDDL standard syntax.
- Problem files must reference the correct domain.
- Plans must be sequential classical plans.

### Planner Behavior
- Planning must terminate within timeout.
- If no plan exists, return an empty plan or explicit failure flag.
- Validation must confirm goal satisfaction.

---

# PDDL Skills

## 1. Load Domain and Problem

### `load-problem(domain_path, problem_path)`

Loads a PDDL domain and problem file into a unified planning problem object.
Uses `unified_planning.io.PDDLReader`. Raises on parse failure.

## 2. Plan Generation

### `generate-plan(problem_object)`

Generates a sequential plan for a problem via
`unified_planning.shortcuts.OneshotPlanner` with default planner `pyperplan`.
Returns `None` if no plan exists.

## 3. Plan Saving

### `save-plan(plan_object, output_path)`

Writes a plan to disk in standard PDDL plan format via
`unified_planning.io.PDDLWriter`.

## 4. Plan Validation

### `validate(problem_object, plan_object)`

Returns True iff the plan satisfies the problem's goal, using
`unified_planning.shortcuts.SequentialPlanValidator`.

# Example Workflow
```python
problem = load_problem("domain.pddl", "task01.pddl")
plan = generate_plan(problem)
if not validate(problem, plan):
    raise ValueError("Generated plan is invalid")
save_plan(plan, "task01.plan")
```

# Notes

- This skill set enables reproducible planning pipelines.
- Designed for PDDL benchmarks and automated plan synthesis tasks.
- Ensures oracle solutions are fully verifiable.

