By WeZZard
Delegate tasks to external agent CLIs through one router and one brief contract — probed facts before use, write isolation through worktrees, a multi-model audit panel, and concurrent image generation with failure memory.
Audit completed or in-progress work with a panel of external models — the same self-contained audit brief to Codex and Kimi in parallel for their diverse biases, file-backed reports, and a compiled digest of agreements and disagreements. Use after completing significant work, before declaring a nontrivial task done, or whenever the user asks for an audit or a second opinion.
Generate images by dispatching one brief concurrently to every usable image-capable external agent, presenting all results as options with artifact paths, and remembering login and quota failures so a failed agent is never dispatched to again until its record clears. Use whenever the user asks for image generation.
Dispatch a task to external agent CLIs through the dispatch external-agent router — compose a self-contained task brief, probe all agent facts in one matrix call, and receive the outputs verbatim as evidence. The audit and image-generation skills build on this one; use it directly only when the user directs an external-agent task outside those types.
Dispatch delegates tasks to external agent CLIs — Codex, Kimi, Antigravity, Cursor, Grok — through one router and one brief contract. Facts are probed in one call before use, agents are pinned by the dispatching skill, repository writes are isolated in git worktrees, and outputs return verbatim as evidence. Claude Code only.
dispatch:external-agent router subagent with the brief.Dispatch pairs with the attune plugin: attune's experiment and verification skills widen through dispatch's panel when it is installed, and degrade gracefully to self-run variants when it is not. Either plugin works alone.
/plugin marketplace add wezzard/skills
/plugin install dispatch@wezzard-skills
The skills are dispatch:use-external-agents, dispatch:audit, and
dispatch:image-generation; the router runs as the
dispatch:external-agent subagent. External agent CLIs are probed, never
assumed — scripts/external-agents.sh matrix is the one fact call.
MIT — see LICENSE.
Uses power tools
Uses Bash, Write, or Edit tools
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub wezzard/skills --plugin dispatchWeZZard's Claude Code skills collection
Tools for auditing and improving Claude Code skill definitions
Capture and apply human-ruled knowledge the model cannot internalize — user preferences and output-style rulings, settled by oracle: research the world, ask the human, experiment on the unknown.
Distilled by WeZZard in China, Assembled from WWDC.
Ultra-compressed communication mode. Cuts 65% of output tokens (measured) while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Unified capability management center for Skills, Agents, and Commands.