Token导航 LogoToken导航

Agent Skill · 开发

wave-coordinator(波协调员)

wave-coordinator 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

wave-coordinator 是开发类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为执行命令;许可证信息还不明确,第三方扫描已通过,按安装量在开发类的 21,746 个 Skill 里排第 20,764。

总安装 212周安装 9GitHub Stars 11下载 74核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:wave-coordinator(波协调员)
来源仓库:https://github.com/b-open-io/prompts
仓库路径:skills/wave-coordinator
安装命令:
npx skills add https://github.com/b-open-io/prompts --skill wave-coordinator
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/b-open-io/prompts --skill wave-coordinator

这个 Skill 是做什么的

开发类 Skill 面向写代码、改代码和排查问题,一般会读写仓库文件,部分还会执行构建或测试命令。

wave-coordinator 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息。适合在 Codex、Claude、Cursor、Gemini CLI 中围绕仓库状态和协作事项进行整理。通过 npx skills add 命令安装,需结合原始 README 核验具体用法。

安装前建议确认权限范围、维护状态,以及是否会触发联网或命令执行。注意该技能当前无原始 SKILL.md 内容可参考,实际功能以仓库实现为准。

来源仓库内路径:skills/wave-coordinator

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/b-open-io/prompts --skill wave-coordinator;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要执行命令,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

wave-coordinator 怎么安装?

在终端执行 npx skills add https://github.com/b-open-io/prompts --skill wave-coordinator。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

wave-coordinator 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

wave-coordinator 需要什么权限?

权限级别是执行命令。安装流程涉及命令执行,可能通过 npx skills add https://github.com/b-open-io/prompts --skill wave-coordinator 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

wave-coordinator 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

wave-coordinator 用的人多吗?

公开数据是累计安装 212 次,近一周安装 9 次,下载 74 次,GitHub 11 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

wave-coordinator 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要执行命令,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理开发类任务、又不想每次都手写提示词的人。

不太适合

  • 不能接受 Skill 在你机器上执行命令的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

开发类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
skill-vetter

技能审查员 · OpenClaw

8,779,018986操作浏览器MIT-0通过
ontology

本体论 · OpenClaw

6,636,960576只读MIT-0通过
entra-app-registration

内部应用程序注册 · Codex、Claude

6,631,872764接触敏感数据未明确通过
entra-app-registration

内部应用程序注册 · Codex、Claude

3,757,680201接触敏感数据未明确通过
nano-banana-pro

纳米香蕉专业版 · OpenClaw

3,526,898364接触敏感数据MIT-0有提醒
wave-coordinator

波协调员 · 本页

21211执行命令未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Wave Coordinator

Manage large-scale subagent dispatch through structured waves. Prevents context exhaustion, ensures output diversity, and avoids duplication across batches. Works alongside Skill(superpowers:dispatching-parallel-agents) — wave-coordinator handles batching and diversity, dispatching-parallel-agents handles the actual subagent spawning mechanics.

The Core Problem

Dispatching 10+ agents at once causes three failures:

  1. Context exhaustion — spawning agents is expensive; running out mid-batch leaves work incomplete
  2. Homogeneous output — identical prompts produce near-identical results, wasting compute
  3. Duplication — later waves repeat what earlier waves already produced

Wave coordination solves all three.

Wave Sizing Rule

Maximum 5 concurrent subagents per wave. If N > 5, divide into sequential waves:

N=12 → Wave 1 (5) → Wave 2 (5) → Wave 3 (2)
N=7  → Wave 1 (5) → Wave 2 (2)
N=5  → Wave 1 (5) — single wave, no split needed

Each wave completes fully before the next launches. Do not launch wave 2 until all wave 1 agents have returned results.

Context Budget Check

Before launching each wave, estimate context budget:

  1. Count tokens consumed so far (rough estimate: each spawned agent costs ~2-4k tokens in overhead)
  2. Reserve at minimum 20% of the context window for synthesis and final output
  3. If budget is tight, reduce the next wave size to 2-3 agents
  4. If budget is critically low, stop dispatching and synthesize from what you have

Hard rule: Never launch a wave if you estimate it will hit the context limit before completion. Stop early and synthesize. Incomplete partial output is better than a context overflow crash.

Directive Diversity

Each agent in a wave must receive unique creative direction. Do not send the same prompt to all agents in a wave.

How to generate diverse directives

Before dispatching, generate N distinct emphasis angles for N agents. Vary along at least one axis:

AxisExample variations
Toneformal / conversational / terse / expansive
Focusconciseness / error handling / edge cases / performance / examples
Perspectivebeginner / expert / skeptic / advocate
Structureprose / bullet list / table / code-first
Constraintmax 200 words / no jargon / no code / examples only

Example: Generating 5 skill variants

Agent 1: "Write the most concise version possible. No examples, pure principle."
Agent 2: "Lead with 3 concrete examples, then derive the rule."
Agent 3: "Focus entirely on error cases and what can go wrong."
Agent 4: "Write for someone encountering this concept for the first time."
Agent 5: "Assume expert audience. Skip fundamentals, go deep on edge cases."

Never assign the same emphasis to two agents in the same wave.

Deduplication Check

Before launching each wave after the first:

  1. Read the output produced by all prior waves
  2. Identify themes, approaches, or content already covered
  3. Add exclusion instructions to the new wave's directives: "Do NOT produce a version similar to [description of prior output]"
  4. If a prior wave already produced a high-quality result for a particular angle, skip that angle in subsequent waves

Wave Progress Tracking

Maintain a mental (or written) wave ledger before each dispatch:

Wave 1: [5 agents] — launched, awaiting results
Wave 2: [5 agents] — pending (blocked on wave 1)
Wave 3: [2 agents] — pending (blocked on wave 2)

Output so far: [list of completed items]
Remaining: [list of items not yet produced]

Update the ledger after each wave completes. This prevents re-dispatching work already done and helps identify what the final synthesis pass needs.

Integration with superpowers

Wave-coordinator handles what to dispatch and when. Skill(superpowers:dispatching-parallel-agents) handles how to spawn subagents. Use them together:

  1. Use this skill to plan wave sizes, generate diverse directives, and track progress
  2. Use Skill(superpowers:dispatching-parallel-agents) for the actual subagent spawning call syntax

If the superpowers plugin is not installed, use Claude Code's native Task tool for subagent spawning instead. Do not silently degrade — state which tool you are using.

Worked Example

Task: Generate 8 variations of a landing page headline.

Wave plan:

Wave 1 (5 agents):

  • Agent A: Urgency angle ("Limited time, immediate benefit")
  • Agent B: Social proof angle ("Join 10,000+ users who...")
  • Agent C: Problem-first angle ("Tired of X? Meet Y.")
  • Agent D: Benefit-first angle ("Do X in half the time.")
  • Agent E: Curiosity angle ("The surprising way to X")

Collect wave 1 output. Review for quality and coverage.

Wave 2 (3 agents — note: reduced from 5 because only 3 remain):

  • Check wave 1 output first
  • Agent F: Contrast angle not yet covered
  • Agent G: Minimalist / single-word-impact angle
  • Agent H: Question format not yet tried

Synthesize all 8 results. Rank by quality. Present top 3 with rationale.

Key Rules

  • 5 agents max per wave — no exceptions
  • Check context budget before each wave
  • Unique directive per agent — never duplicate prompts within a wave
  • Read prior output before launching the next wave
  • Stop and synthesize if budget runs low — do not push through to completion at the cost of a crash
  • Wave 2+ directives must explicitly exclude angles already covered in prior waves

平台分布

Codex

33.87%
按下载量换算25

Claude

32.16%
按下载量换算24

Cursor

17.32%
按下载量换算13

Gemini CLI

9.65%
按下载量换算7

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add https://github.com/b-open-io/prompts --skill wave-coordinator 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills