frontend-impl-playbook

Stack-aware frontend implementation playbook for autopilot impl-agents. When a task touches *.tsx/*.jsx/*.css files, dispatchers prepend this playbook to the agent's brief so the first draft already meets the design-quality floor (reuse existing primitives, design tokens only, four states by default, accessibility baseline, mobile-first). Read this skill manually before implementing UI changes if your autopilot version does not auto-attach it yet.

atls — Atlassian CLI Dispatcher

<!-- installed-by: atls 0.2.5 -->

board-scanner

Board scanning and dispatch procedure for GitHub Projects v2. Scans the project board for mgr:* statuses and dispatches work to the executor hat via priority table. Auto-injected into coordinator prompts.

haiku-pilot

Haiku-first execution playbook: through deliberate prompt structure, sub-agent delegation, and quantitative escalation gates, get Haiku 4.5 to produce near-Opus quality on most tasks. Escalate to Sonnet/Opus only when gates trigger. Triggers: "haiku", "Haiku", "Haiku mode", "haiku-pilot". Do NOT use for: cost-only token optimization, file-count cognitive heuristic, agent dispatch table, CLAUDE.md / rules audit, harness health check. This SKILL is a runtime router + escalation gate, not a decision tree or directory.

Developing o8 (the self-hosting bootstrap)

o8 is a fleet-orchestration product we build BY orchestrating a fleet. The catch: o8's own dispatch pipeline isn't fully hardened, and the meta-bugs that break dispatch can't be reliably fixed by the fleet — they're the thing that's broken. So there's a bootstrap.

adr-consultation

Multi-agent consultation for architecture decisions. Dispatches 3 specialized reviewers in parallel (contrarian, user advocate, meta-process) to challenge a plan or ADR before implementation begins, producing a synthesis with a PROCEED or BLOCKED verdict. Use for "consult on this ADR", "challenge this design", "review before implementing", "should we proceed", or any Medium+ architecture decision. Do NOT use for trivial changes, simple bug fixes, or decisions already in implementation.

/dispatch — Multi-Model Dispatcher

Sends a task or prompt to another AI model for execution and retrieves the result. This skill **only provides the dispatch capability** — which model to pick, whether to fan out to multiple models, is decided by you (or the current Claude) based on the task at hand. No built-in model preference.

Energyatit

Connect AI agents to energy infrastructure. Dispatch, attest carbon, read meters.

hex-release

Guides interactive Hex package release for AgentJido repos. Supports automated (GitHub Actions workflow_dispatch) and manual release flows. Uses git_ops for version bumping and changelog generation. Triggers on: release, hex publish, bump version, new release, publish package.

ai-advise

Proactive governance advisor — checks standards, decisions, and quality trends during development. Always advisory, NEVER blocks. Three modes: `advise` (post-edit), `gate` (pre-dispatch), `drift` (on-demand decision audit). Trigger for 'governance check', 'advise on this change', 'check for drift', 'is this aligned with active decisions', 'shift-left advisory'. Not for blocking gates — use /ai-verify. Not for narrative code review — use /ai-review.

research-experiment

Coordinate autonomous research experiments across multiple coding agents using isolated git worktrees. Use when a user wants the main agent to define a goal, constraints, acceptance criteria, and experiment boundaries, then dispatch Codex/Claude/Gemini or other agents to independently search for solutions without touching production code.

Implement Universal — Single-Context Workshop Implementation Loop

This is the harness-agnostic twin of `/implement`. It is functionally identical, but instead of dispatching subagents via Claude Code's `Task` tool, it instructs **you** to adopt two distinct roles in sequence:

antigravity-swarm

Deploys autonomous sub-agents to perform tasks in the Antigravity IDE. Supports both manual dispatch and dynamic "Auto-Hiring" of agent teams.

Io.Github.Autonomous Testing/Wopee Mcp

AI testing agents for web apps — dispatch test runs, crawls, fetch artifacts and status.

swarm-iosm

Orchestrate complex development with AUTOMATIC parallel subagent execution, continuous dispatch scheduling, dependency analysis, file conflict detection, and IOSM quality gates. Analyzes task dependencies, builds critical path, launches parallel background workers with lock management, monitors progress, auto-spawns from discoveries. Use for multi-file features, parallel implementation streams, automated task decomposition, brownfield refactoring, or when user mentions "parallel agents", "orchestrate", "swarm", "continuous dispatch", "automatic scheduling", "PRD", "quality gates", "decompose work", "Mixed/brownfield".

Ai Ops

AI operations management: 12 specialized agents, task dispatch, and team coordination.

android-concurrency

Standards for Coroutines, Flow, and Threading. Use when writing suspend functions, choosing coroutine scopes, switching between StateFlow and SharedFlow, injecting Dispatchers for testability, or debugging threading issues in Android. (triggers: **/*ViewModel.kt, **/*UseCase.kt, **/*Repository.kt, suspend, viewModelScope, lifecycleScope, Flow, coroutine, Dispatcher, DispatcherProvider, GlobalScope)

convoy

The definitive guide for working with gastown's convoy system -- batch work tracking, event-driven feeding, stage-launch workflow, and dispatch safety guards. Use when writing convoy code, debugging convoy behavior, adding convoy features, testing convoy changes, or answering questions about how convoys work. Triggers on convoy, convoy manager, convoy feeding, dispatch, stranded convoy, feedFirstReady, feedNextReadyIssue, IsSlingableType, isIssueBlocked, CheckConvoysForIssue, gt convoy, gt sling, stage, launch, staged, wave.

governed-operator

Full governance constitution for multi-agent or solo governed workflows. Load for any work that touches shared state, requires independent review, spans multiple seats, or involves planning, architecture, code changes, reviews, dispatches, status reports, or canonical records. Not needed for quick factual questions or trivial one-off answers.

Open Dynamic Workflow (odw)

odw is the **orchestration layer**. You write a small JavaScript workflow that calls `agent(prompt, opts)` nodes; odw schedules them (parallel / pipeline / budget / worktree / resume) and dispatches each node to **PandaCode**, which runs the actual AI (`codex`, `claude`, or `bamboo`) and owns accoun

updater

Check Claude Code changelog for lintable changes and implement cclint updates — version gap detection, domain classification, parallel agent dispatch

Dispatcher

You are the dispatcher. You run in the main Claude Code session for a Taniwha project. Your job is mechanical: invoke the orchestrator, execute what it tells you, repeat. You do not decide what should happen next — that is the orchestrator's job, and it lives in a fresh subagent context every time

roster-orchestrator

Bootstraps roster workspaces. On chat session start, surfaces pending HITL items as a single banner. On a scheduled fire, verifies the schedule is registered, resolves the agent's merged env, dispatches the named agent via the host tool's native subagent primitive, writes a run log + state.md entry, and exits. Reads roster/<function>/schedules.yaml plus pending items at both roster/<function>/pending/ (error class) and <function>/<agent>/pending/ (lesson class). Subscription-billed primitives only — never invokes claude -p, claude --prompt, claude api, or the Anthropic SDK.

agentify

Bootstraps a dispatchable Claude sub-agent skill for every coding agent CLI installed on this machine (codex, aider, cursor, etc.). Use when the user wants to delegate tasks to locally-installed agent CLIs or expand the plugin's agent fleet.

lissom-impl

Dispatch to lissom-implementer agent to execute plan steps and verify completion.

Camacho Mcp

Persistent tmux terminal for AI agents — real-time spectating, SSH host-group dispatch.

orbit-orchestrate

Prepares and supervises an Orbit backlog. Deduplicates and pilots tasks (task-pilot), assigns crews, promotes ready work, dispatches with `orbit run ship` and `orbit run auto` drains, diagnoses failed or stuck `jrun-*` runs, and routes CI/QA sweep findings into repair tasks. Use for delivery operations across tasks, jobs, activities and workflow runs. Use orbit for one assigned task and orbit-setup for machine configuration or scheduler installation.

campaign-conductor

Run a project as an orchestrated campaign: Claude as conductor (Fable 5.1, or Opus 5 when Fable is unavailable) dispatching a mixed fleet of workers, Claude Opus 5 agents for UI/UX and design judgment, Claude Sonnet 5 agents for surveys and search, OpenAI Codex CLI workers for implementation and everything else. Use whenever the user says "start a campaign", "campaign mode", "orchestrate this", "use the fleet", "mix of agents", "send out workers", "codex workers", or asks Claude to run a multi-task project by delegating to parallel agents rather than implementing directly. Also use when resuming work in a repo whose CLAUDE.md points at a campaign-hq folder.

Accessibility Review - WCAG Conformance Audit

Advisory-only accessibility audit. Dispatches a `QA - Web A11y Reviewer` agent to evaluate web content against WCAG 2.2 Level AA, prioritize issues by real-world user impact, and recommend fixes. No changes are made.

teambuilder-apply-dispatch-loop

Dispatch pending tasks from an OpenSpec change's tasks.md to the right Teambuilder persona in fresh subagents. Use from `/opsx:apply` (or `openspec-apply-change`) when Teambuilder personas are present in `.claude/agents/`.

kernelgen-flagos

Unified GPU kernel operator generation skill. Automatically detects the target repository type (FlagGems, vLLM, or general Python/Triton) and dispatches to the appropriate specialized sub-skill. Also includes a feedback submission sub-skill for bug reports. Use this skill when the user wants to generate a GPU kernel operator, create a Triton kernel, or says things like "generate an operator", "create a kernel for X", or "/kernelgen-flagos". This single skill replaces the need to install kernelgen-general, kernelgen-for-flaggems, kernelgen-for-vllm, and kernelgen-submit-feedback separately.

file-conversion

Use this skill when the user asks to convert a file from one format to another (e.g. csv to xlsx, xlsx to json, pdf text to csv) and you're not sure which library handles that specific pair, or whether it's supported in this environment at all. Dispatches to the right library per format pair and explicitly lists conversions that are NOT supported here so you don't attempt one that will silently fail or produce a wrong result.

A Claude Skill collection designed for task automation, document parsing, and intelligent dispatch. such as utilities for webpage-to-Markdown conversion, API doc parsing, and structured JSON extraction—optimized for LLM-driven workflows

mm — Dispatcher / Cheat Sheet

Короткие алиасы для длинных команд. Также — если юзер просто пишет `/mm`, выводи список.

HumanOps

MCP server for AI agents to dispatch real-world tasks to verified human operators

fulcra-agent-atc

Model & cap routing (ATC) for a subscription fleet: declare your accounts once, then a capability-ranked router (`coord-engine route --needs …`) picks the cheapest model that can do the job across every subscription, a cross-account cap ledger keeps traffic inside its windows, and outcome logging demotes a model that keeps failing a task class. Standalone on one account; scales to a coord team of resident dispatchers.

subtask

Parallel task orchestration CLI that dispatches work to AI workers (via Claude Code) in isolated git workspaces. Use when the user wants to draft, create, run, or manage tasks, delegate tasks to workers/subagents, or mentions subtask or Subtask.

ai-six-sigma-property-os

Design an AI Six Sigma Black Belt operating model for property service, maintenance dispatch, environmental testing, quote generation, CRM follow-up, and workflow quality dashboards. Use when the user needs a Property Agent OS, AI + Ontology + DMAIC management system, CTQ metrics, agent-team roles, work-order states, or MVP roadmap for operations quality.

Goosetown Orchestrator

Decompose, dispatch, synthesize. Don't build — make sure the right things get built, in the right order, with the right context. The user knows what needs to exist; you know how to coordinate building it. Keep the whole picture legible: who's doing what, why, and what's been learned so far.

dispatch

Shared multi-model CLI dispatch infrastructure for the adv plugin. Houses dispatch.sh, preflight.sh, run-phase.sh, scope.sh, and reviewer prompt templates used by the adv-review agent and adv-* commands.