ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

multi-task

Orchestrate parallel execution of batch tasks by splitting work into independent units and dispatching them to multiple subagents simultaneously. Use this skill whenever the user has multiple similar independent tasks — such as processing a batch of files (PDFs, DOCX, images, CSVs), developing multiple pages or components, generating multiple reports, or any scenario involving 'each', 'every', 'all', 'batch', or a list of similar items. Also trigger when the user provides a numbered list of tasks, references a folder of files to process, or describes repetitive work across multiple inputs. Even if the user doesn't explicitly say 'parallel' or 'batch', if the work naturally decomposes into 3+ independent units of similar type, use this skill to maximize throughput.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/brightween/multi-task
Or

Multi-Task: Parallel Batch Orchestration

Overview

When users present tasks that decompose into multiple independent work units, serial execution wastes time. This skill guides you to identify batch opportunities, construct self-contained prompts for each unit, and dispatch them as parallel subagents via the Task tool — completing in minutes what would otherwise take much longer sequentially.

The core insight: a single message can contain multiple Task tool calls, and they all execute concurrently. Your job is to make each subagent's prompt fully self-contained (they cannot see this conversation) and to coordinate the results.

When to Use This Skill

Strong signals:

  • User says "process all files in X folder"
  • User provides a list: "do A, B, C, D for each of these..."
  • User mentions "batch", "bulk", "every", "each", "all N files"
  • A folder contains multiple files needing the same operation
  • User wants multiple pages/components/reports generated

Also consider using when:

  • User describes repetitive work that you'd otherwise do in a loop
  • The task involves 3+ independent units of similar type
  • Processing time per unit is non-trivial (reading/transforming documents, generating code, etc.)

Do NOT use when:

  • Tasks have strict sequential dependencies (output of task N feeds into task N+1)
  • There are fewer than 3 work units (overhead isn't worth it)
  • The task is a single complex operation that can't be decomposed
  • User explicitly asks for serial processing

The 6-Step Workflow

Step 1: ANALYZE — Understand the Work

Before dispatching anything, enumerate what needs to be done:

  1. List all work units — files to process, pages to build, items to transform
  2. Identify the operation — what happens to each unit (extract, convert, summarize, generate, etc.)
  3. Check for shared context — do all units need the same template, config, or reference data? If so, read it once now and include it in every subagent prompt.
  4. Detect dependencies — are any units dependent on others? If yes, read references/advanced-patterns.md for dependency handling strategies. If all units are independent (the common case), proceed directly.
  5. Count the units — this determines your dispatch strategy:
    • 3-10 units: single wave, all parallel
    • 11-50 units: dispatch in waves of 8-10
    • 50+ units: run 2-3 pilot tasks first to validate your prompt, then dispatch the rest in waves

Present your analysis to the user:

Found N work units: [brief list]
Operation: [what will happen to each]
Shared context: [any common dependencies]
Dependencies: [none / description]
Strategy: [single wave / M waves of ~K / pilot + waves]

Wait for user confirmation before dispatching, especially for large batches.

Step 2: PLAN — Decompose into Task Units

For each work unit, define:

Metadata

Stars4190
Views0
Updated2026-04-18
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-brightween-multi-task": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.