Decomposes complex user requests into executable subtasks, identifies required capabilities, searches for existing skills at skills.sh, and creates new skills when no solution exists. This skill should be used when the user submits a complex multi-step request, wants to automate workflows, or needs help breaking down large tasks into manageable pieces.

Decomposes complex user requests into executable subtasks, identifies required capabilities, searches for existing skills at skills.sh, and creates new skills when no solution exists. This skill should be used when the user submits a complex multi-step request, wants to automate workflows, or needs help breaking down large tasks into manageable pieces.

This skill is internally consistent and does what it says: decompose tasks, map capabilities, and search/create skills. The main practical risk is that following its instructions requires using the Skills CLI (npx) to fetch/install third‑party skills or to initialize new skills — those actions will download and execute external code. Before installing or letting an agent run npx installs: (1) review the code of any skill you plan to install, (2) avoid granting secrets (API keys, tokens) unless you trust the target skill, (3) run installations in an isolated environment or sandbox, and (4) consider restricting the agent's ability to run arbitrary CLI/network commands if you need stronger confinement.

Type: OpenClaw Skill Name: super-skills Version: 1.0.0 The skill's primary function is to decompose user requests and manage other OpenClaw skills (search, install, create). All instructions in SKILL.md, including the use of `npx skills find`, `npx skills add`, and `npx skills init`, are directly aligned with this stated purpose. There is no evidence of intentional harmful behavior such as data exfiltration, unauthorized execution, or persistence mechanisms. The skill explicitly notes that 'Skill creation requires user confirmation before proceeding', which is a mitigating factor for the `npx skills init` command.