agentleFS
Sign inStart free
KbWenKbWen/agent-virtual-office/.agents/skills/dispatching-parallel-agents/SKILL.md

dispatching-parallel-agents

Skill65 starsChanged 3 months agoMITView on GitHub

Evaluate when to dispatch parallel agents; use a 4-step pattern to split, coordinate, and integrate results.

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 176 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every sub-task MUST have a clear Definition of Done.

    line 33

“Common” is measured: kept by at least 6 in 10 of the 176 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Dispatching Parallel Agents

Overview

Parallel agents are suitable for handling splittable tasks with low coupling. The goal is to shorten total lead time, not to increase coordination overhead.

When to Use

  • Tasks can be decomposed into independent sub-problems (e.g., documentation, testing, separate modules).
  • Dependencies between sub-tasks are low; clear interfaces can be defined.
  • Deadlines are tight, and lead time needs compression.

When NOT to Use

  • Problems are highly coupled and require frequent synchronization.
  • Requirements are still unclear; the cost of decomposition outweighs the benefits.
  • Unable to define unified acceptance criteria.

Four-Step Pattern

  1. Decompose: Split into mutually exclusive, independently verifiable sub-tasks.
  2. Dispatch: Specify each agent's scope, inputs/outputs, constraints, and deadline.
  3. Sync: Perform brief synchronizations at fixed checkpoints to handle conflicts and dependencies.
  4. Merge: Integrate outputs using a unified set of acceptance criteria and run regression tests.

Best Practices

  • Every sub-task MUST have a clear Definition of Done.
  • Collaborate primarily via interface contracts to avoid modifying each other's blocks.
  • Perform a global check before final integration.

Common Mistakes

  • Forcefully splitting non-splittable tasks, leading to rework.
  • Lacking sync checkpoints, resulting in integration explosion at the end.
  • Sub-tasks passing individually but failing global acceptance.

Download now (ZIP)

  • Other versions188 projects use a version of this.

    Word for word · 1

    1. KbWen/agentic-os★ 224100% same

    Edited · 0

    None found.

    Wrote their own version · 187

    1. obra/superpowers★ 305ksame name
    2. jnMetaCode/superpowers-zh★ 8.4ksame name
    3. openai/plugins★ 7.4ksame name
    4. farm-fe/farm★ 5.6ksame name
    5. GanyuanRan/Aegis★ 1.4ksame name
    6. pcvelz/superpowers★ 1.3ksame name
    7. coco-research/coco★ 797same name
    8. derHaken/SuperAntigravity★ 439same name
    9. koaning/wigglystuff★ 437same name
    10. Ibrahim-3d/conductor-orchestrator-superpowers★ 381same name

    177 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use chinese-code-review, chinese-commit-conventions and 10 more.

    Other files people use alongside this one.

    Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
    • GEd520Skill

      chinese-code-review

      中文 review 沟通参考——话术模板、分级标注（必须修复/建议修改/仅供参考）、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用，不要根据上下文自动触发。

      Also in 7 projects that use this

    • GEd520Skill

      chinese-commit-conventions

      中文 commit 与 changelog 配置参考——Conventional Commits 中文适配、commitlint/husky/commitizen 中文模板、conventional-changelog 中文配置。仅在用户显式 /chinese-commit-conventions 时调用，不要根据上下文自动触发。

      Also in 7 projects that use this

    • obraSkill

      diagnosing-superpowers

      Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.

      Also in 12 projects that use this

    • 10CGSkill

      workflow-runner

      十步循环轻量编排器，协调 Phase Skills 执行，支持灵活组合。

      Also in 8 projects that use this

    • kntismSkill

      condition-based-waiting

      Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests from timing guesses

      Also in 3 projects that use this

    • kntismSkill

      defense-in-depth

      Use when invalid data causes failures deep in execution, requiring validation at multiple system layers - validates at every layer data passes through to make bugs structurally impossible

      Also in 3 projects that use this

    • +2 more from GEd520
  • In this repository16 other files it gives its agents.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free