From dispatch
This skill should be used when the user invokes "/dispatch:sonnet <task>", asks to "run this with sonnet", "use sonnet for this", "dispatch to sonnet", or wants the balanced default model for standard dev tasks. Dispatches the given task to a Sonnet model subagent and returns the result.
How this skill is triggered — by the user, by Claude, or both
Slash command
/dispatch:sonnetThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Dispatch the task in `$ARGUMENTS` to a Sonnet model subagent.
Dispatch the task in $ARGUMENTS to a Sonnet model subagent.
Sonnet is the balanced default tier — good reasoning, moderate cost. Use it for standard dev tasks: code edits, bug fixes, test generation, codebase exploration, explanations, moderate analysis.
$ARGUMENTS is empty, ask the user: "What task should I dispatch to Sonnet?"Agent({
model: "sonnet",
description: "<one-line summary of the task>",
prompt: "<the full task from $ARGUMENTS>"
})
If the task is very simple (single lookup, format conversion, yes/no), suggest
/dispatch:haiku — it's faster and cheaper. If the task requires deep architectural
reasoning or root-cause debugging of a non-obvious issue, suggest /dispatch:opus.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub jobrien127/plugin-marketplace --plugin dispatch