What problem does it solve? AI agents often skip established workflows and improvise answers, ignoring reusable skills that already encode the correct procedure. This meta-skill forces the agent to check for and invoke relevant skills before responding, asking clarifying questions, or taking any action. ## Core Features & Use Cases - Mandatory skill-first rule: Requires invoking any potentially applicable skill (even at 1% relevance) before any response, with a decision flowchart and red-flag rationalization table. - Skill lifecycle management: Documents the OpenClaw skill_workshop tool actions (list, inspect, create, update, revise, apply, reject, quarantine) and the pending-proposal model for new skills. - Platform adaptation mapping: Translates generic skill actions (read a file, spawn a subagent, schedule an event) into concrete OpenClaw tools such as read, exec, sessions_spawn, and cron. - Use Case: A user asks the agent to fix a bug. Instead of diving into the code, the agent first checks the skill registry, finds a systematic-debugging skill, invokes it, and follows its procedure. ## Quick Start Ask the agent to list available workspace skills and invoke the relevant one before starting your task.
