Prompt Architect

Transform rough ideas into professional-grade LLM prompts. Analyzes text, images, links, and documents to craft optimized prompts using proven frameworks (Co...

This skill is instruction-only and internally consistent with its purpose of producing optimized prompts. Things to consider before installing/using: (1) The skill expects to analyze links, images, and documents — only provide content you are comfortable sharing (do not paste secrets or private credentials). (2) It mandates 5–10 clarifying questions each run, which may require extra user interaction and could lead you to share more context than you intended. (3) The instructions say to 'browse' links but do not define how (if your agent lacks web access the skill may fail or will ask you to paste content); check whether your agent supports browsing/multimodal inputs. (4) The skill only offers the final prompt in English or Arabic by design — if you need other languages, expect extra manual steps. Overall the skill appears coherent and low-risk, but avoid submitting sensitive documents or credentials into the clarifying-question flow.

Type: OpenClaw Skill Name: prompt-architect Version: 1.0.0 The OpenClaw AgentSkills bundle for 'prompt-architect' is benign. All files, including the `SKILL.md` instructions for the AI agent and the various reference markdown files, are entirely focused on the stated purpose of helping users craft optimized LLM prompts. There are no instructions for unauthorized data access, exfiltration, system command execution, persistence, or any form of prompt injection against the OpenClaw agent itself. The content consistently provides guidance and templates for *generating* prompts, not for performing malicious actions.