Parallel Agent Dispatch
Use when two or more work items are genuinely independent and can be investigated concurrently without shared mutable state or sequential dependencies.
Install
npx skills add sandbaseai/workbuddy-skill --skill parallel-agent-dispatchgit clone --depth 1 https://github.com/sandbaseai/workbuddy-skill.git /tmp/workbuddy-skill
mkdir -p ~/.claude/skills
cp -r /tmp/workbuddy-skill/skills/parallel-agent-dispatch ~/.claude/skills/parallel-agent-dispatchPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Parallel Agent Dispatch Use this Skill when multiple work items can progress concurrently. Parallelism is a coordination decision, not a default optimization: dispatch only when each item can be understood and worked on without another item's mutable state, exclusive resource, or unresolved prerequisite. ## 1. Prove independence Inventory the work items, files, subsystems, dependencies, expected outputs, external resources, and ownership. Group failures or tasks by domain. Dispatch in parallel only when all are true: - the tasks have no sequential dependency or shared mutable write target; - one task's outcome will not change another's diagnosis or acceptance criteria; - each task has a bounded scope and a clear completion signal; - the required credentials, quotas, environments, and rate limits can be isolated; - results can be integrated and verified together afterward. Keep related failures in one investigation. Use sequential work when the system state must be understood as a whole, the same files or resources are edited, or one hypothesis depends on another's result. Do not split merely to create more Agents. ## 2. Prepare isolated assignments Give every Agent a self-contained brief containing: 1. one problem domain, exact paths or resource scope, and the observed symptom; 2. the goal and red-capable or otherwise checkable completion criterion; 3. relevant evidence, repository vocabulary, constraints, and known dependencies;
Details
- Skill name
parallel-agent-dispatch- Repository
- sandbaseai/workbuddy-skill
- Path
skills/parallel-agent-dispatch/SKILL.md- License
- MIT
- Repo updated
- 8 September 2026
FAQ
What does the Parallel Agent Dispatch skill do?
Use when two or more work items are genuinely independent and can be investigated concurrently without shared mutable state or sequential dependencies.
How do I install the Parallel Agent Dispatch skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add sandbaseai/workbuddy-skill --skill parallel-agent-dispatch. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Parallel Agent Dispatch popular?
It lives in sandbaseai/workbuddy-skill, which has 9 GitHub stars and 3 forks.
Related skills
Access Control Security Best Practices
9sandbaseai/workbuddy-skill
Design, review, implement, and verify least-privilege access controls across users, services, tenants, resources, and administrative workflows.
Accessibility Review
9sandbaseai/workbuddy-skill
Use when reviewing a web interface or interaction for semantic, keyboard, focus, screen-reader, ARIA, and contrast accessibility risks.
Acquire Codebase Knowledge
9sandbaseai/workbuddy-skill
Use when the user asks to map, document, or onboard into an existing codebase and needs evidence-backed architecture, structure, conventions, integrations, testing, and concerns documentation.
Prd
9sandbaseai/workbuddy-skill
Use when turning a product or AI feature idea into a measurable Product Requirements Document with user stories, technical specifications, acceptance criteria, evaluation, risks, and rollout phases.
Multi Agent Orchestration
9sandbaseai/workbuddy-skill
Use when coordinating genuinely independent Agent workstreams with task decomposition, dependency graphs, ownership, handoff contracts, approvals, recovery, and synthesis.
Prompt Injection Defense
9sandbaseai/workbuddy-skill
Use when threat-modeling or hardening an AI agent, RAG system, assistant, or tool workflow against direct, indirect, stored, cross-agent, or multimodal prompt injection.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.