By tylergibbs1
Skills for orchestrating multi-agent coding work: fan out subagents to implement, then ship to a PR and run a review-and-fix workflow. Every agent pulls fresh docs via Context7.
Orchestrate a multi-agent implementation: decompose a task, fan out subagents to implement each piece in parallel, and brief each one with the context it needs plus a mandate to pull fresh docs via Context7. Use when the user wants to "use subagents", "fan out", "parallelize implementation", "orchestrate agents", spin up workers, or build a feature that splits into independent workstreams. Covers Claude Code subagents, Claude Code dynamic workflows, and Codex subagents.
Push the current changes to a pull request, then launch a dynamic workflow that reviews the PR diff, adversarially verifies each finding, and fixes the confirmed ones — pushing the fixes back to the PR. Use when the user wants to "push to a PR and review", "open a PR then review and fix findings", "ship and review", or run a multi-agent review-and-fix pass over a branch. Pairs with orchestrating-subagents (which implements the change first).
A collection of Agent Skills for orchestrating multi-agent coding work — fanning out subagents to implement a change, then shipping it to a PR and running a review-and-fix workflow over the diff.
Both skills require every agent that touches an external library to pull current docs via Context7 before writing code, so implementations and fixes track real APIs instead of stale training data.
Turns the calling agent into an orchestrator: it scouts the repo, freezes shared contracts, decomposes the task into independent subtasks, and dispatches one subagent per subtask in parallel — each with a self-contained brief and the Context7 mandate. Covers Claude Code subagents, Claude Code dynamic workflows, and Codex subagents.
Use when:
Pushes the current changes to a pull request, then launches a dynamic workflow that reviews the PR diff across dimensions, adversarially verifies each finding to drop false positives, and fixes the confirmed ones in isolated worktrees before pushing the fixes back to the PR.
Use when:
The two pair up: orchestrating-subagents implements the change, then
shipping-pr-reviews ships and reviews it.
With the skills.sh installer (pick the skills and the agents to install them on):
npx skills@latest add tylergibbs1/dispatch
Or install as a Claude Code plugin (the repo ships a
.claude-plugin/plugin.json):
/plugin marketplace add tylergibbs1/dispatch
/plugin install dispatch
Both skills are invoke-only (disable-model-invocation: true) — they spawn
fleets of subagents / dynamic workflows, so you trigger them deliberately rather
than have the agent auto-fire them.
Invoke them as slash commands (or by name):
/orchestrating-subagents build the API, the UI, and the migration for feature X
/shipping-pr-reviews push this branch to a PR, then review and fix the findings
Each skill contains:
SKILL.md — instructions for the agent (loaded when triggered)references/ — supporting docs loaded on demand (templates, dispatch mechanisms)metadata.json — version and referencesSee CONTRIBUTING.md for how to add a new skill and the frontmatter rules enforced by CI.
MIT
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub tylergibbs1/dispatchCodeWarden watches over your code quality: Ultracite enforcement, React 19/Next.js App Router patterns, security auditing, Vercel deployment, React performance best practices, design guidelines, and automated workflows for modern TypeScript/React applications
Semantic context packer - combines import resolution with semantic search
CodeWarden watches over your code quality: Ultracite enforcement, React 19/Next.js App Router patterns, security auditing, Vercel deployment, React performance best practices, design guidelines, and automated workflows for modern TypeScript/React applications
Semantic context packer - combines import resolution with semantic search
Agent-to-agent communication system using file-attached warnings for cross-session context sharing and collaboration.
Matt Pocock's agent skills for real engineering — grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Design fluency for frontend development. 1 skill with 23 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.
Harness-native ECC plugin for engineering teams - 67 agents, 279 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.