RALSTP Consultant

Analyze problems using RALSTP (Recursive Agents and Landmarks Strategic-Tactical Planning). Based on PhD thesis by Dorian Buksz (RALSTP). Identifies agents,...

This skill appears to do what it says: conceptual analysis via LLM and an optional formal mode that parses PDDL files with the included script. Before using: (1) Only run the analyze.py on PDDL files you trust or run it in a sandbox — it will read any local files you point it at but does not perform network access or execute code from those files. (2) Expect the script to be heuristic and approximate (regex-based parsing); results may be incorrect on complex PDDL. (3) No credentials or external endpoints are requested, so installing it does not expose secrets. If you want extra safety, inspect the script (it's short) or run it in an isolated environment.

Type: OpenClaw Skill Name: ralstp-consultant Version: 1.0.1 The skill bundle provides a RALSTP consultant, designed to analyze problems using a specific planning methodology. The `SKILL.md` clearly outlines its purpose and usage, including an optional 'Formal Mode' that utilizes `scripts/analyze.py` for PDDL file analysis. The `analyze.py` script is a self-contained Python program that parses PDDL files, identifies agents, and calculates difficulty metrics. It does not perform any network requests, execute external commands, access sensitive files beyond its stated purpose, or use `eval`/`exec` on untrusted input. There is no evidence of data exfiltration, persistence mechanisms, or prompt injection attempts designed to subvert the agent's core functionality for malicious ends. The code and documentation align with the stated purpose of a planning analysis tool.