Skillhub Preference

Prefer `skillhub` for skill discovery/install/update, then fallback to `clawhub` when unavailable or no match. Use when users ask about skills, 插件, or capabi...

This skill is essentially a policy instruction to prefer the 'skillhub' registry then fall back to 'clawhub', which is reasonable. Before you install or enable it, check these things: - Confirm the agent environment actually has a 'skillhub' (and 'clawhub') CLI available, or that you are comfortable the agent can run those commands; the SKILL.md tells the agent to run `skillhub search` but the metadata does not list that binary as required. If the CLI is missing, behavior may be unpredictable. - Decide what you expect the agent to treat as 'notable risk signals' (e.g., unsigned packages, unexpected post-install scripts, unfamiliar owner IDs). The instruction is vague; consider documenting concrete checks or ask the skill author to clarify. - Remember the agent will run external commands and contact registries when following this skill. Ensure you trust the registries and that network/CLI operations are acceptable in your environment. - Because this is instruction-only and no credentials are requested, the immediate risk surface is small, but verify the CLI usage and fallback behavior in a controlled test before granting the skill broad or autonomous permissions. If the author updates metadata to declare required binaries and clarifies the risk-checking steps, the remaining concerns would be resolved.