Agent skill · operations · aiskillstore
parallel-agents
Dispatch multiple agents to work on independent problems concurrently. Use when facing 3+ independent failures or tasks.
Why this skill is useful
Provides a structured approach to dispatching multiple agents concurrently, enhancing task resolution efficiency with specific implementation patterns.
What it needs
About 3k tokens when loaded. Last updated 2026-08-07. 405 stars on the source repository.
What this skill does
Dispatching Parallel Agents Assign separate agents to independent problem domains simultaneously for faster resolution. When to Use 3+ test failures across different files/subsystems Multiple independent tasks that don't share state Investigations that won't interfere with each other Failures from unrelated root causes When NOT to Use Failures are interconnected Tasks share state or create conflicts Agents would modify the same files You lack context to properly scope tasks Implementation Steps 1. Group by Domain Organize failures/tasks into independent categories: 2. Define Focused Tasks Each agent receives: Field Description ----------- -------------------------------- Scope Specific files/tests to focus on Goal Clear success criteria Constraints What NOT to change Output Expected deliverable 3. Dispatch Concurrently IMPORTANT: Launch all tasks in a single message (no runinbackground). Multiple Task calls in the same message automatically run in parallel, and Claude waits for all to complete. Avoid runinbackground: true unless you need to do other work while waiting. Task IDs must be captured and used within the same response. 4. Integrate Results 1. Review all agent outputs (available after parallel completion) 2. Verify no conflicts between changes 3. Run full test suite 4. Merge changes Effective Agent Prompts Good prompt: Bad prompt: Prompt Template Common Pitfalls Mistake Problem Solution --------------- ------------------------- ---------------------- Vague scope Agent changes wrong files Specify exact paths Missing context Agent can't diagnose Include error messages No constraints Conflicting changes Define boundaries Unclear output Can't verify success Specify deliverables Benefits Reduces investigation time through parallelization Each agent maintains narrow focus Minimizes cross-agent interference Solves multiple problems concurrently Background Execution For long-running tasks where you need to continue working, use runinbackground: true. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aiskillstore/parallel-agents