Token导航 LogoToken导航

Agent Skill · 研究检索

running-effective-meetings(召开有效的会议)

running-effective-meetings 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。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。

running-effective-meetings 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 49,936。

总安装 635周安装 27GitHub Stars 3下载 222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:running-effective-meetings(召开有效的会议)
来源仓库:https://github.com/oldwinter/skills
仓库路径:skills/running-effective-meetings
安装命令:
npx skills add https://github.com/oldwinter/skills --skill running-effective-meetings
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/oldwinter/skills --skill running-effective-meetings

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于查找、检索和筛选相关信息,支持关键词和任务场景定位。适合在 Codex、Claude 等宿主中快速获取候选结果。可结合来源仓库 README 核验具体用法和权限范围。安装前建议确认是否会触发联网或文件读写操作。

running-effective-meetings 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/running-effective-meetings

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/oldwinter/skills --skill running-effective-mee…;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

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

running-effective-meetings 怎么安装?

在终端执行 npx skills add https://github.com/oldwinter/skills --skill running-effective-meetings。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

running-effective-meetings 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。

running-effective-meetings 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

running-effective-meetings 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。

running-effective-meetings 用的人多吗?

公开数据是累计安装 635 次,近一周安装 27 次,下载 222 次,GitHub 3 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。

running-effective-meetings 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。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 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。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 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。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
running-effective-meetings

召开有效的会议 · 本页

6353只读未明确通过

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

Running Effective Meetings

Scope

Covers

  • Deciding whether a meeting is needed (vs async doc/message)
  • Choosing the right meeting format (operational / strategic / decision / workshop)
  • Preparing a pre-read and “priming” to avoid context-less discussions
  • Facilitating discussion, capturing decisions, and ensuring follow-through
  • Improving recurring meeting hygiene (split/kill/shorten meetings)

When to use

  • “Create an agenda and facilitation plan for a decision meeting.”
  • “We need a weekly operational cadence — design the meeting format and templates.”
  • “This meeting keeps going in circles — redesign it so we decide and assign actions.”
  • “Turn this messy invite into a clear meeting brief + pre-read + follow-up.”

When NOT to use

  • The goal is purely status updates (use async updates instead).
  • There is no discussion to be had (you already have the decision and only need to broadcast it).
  • The “decision owner” is not attending and cannot delegate decision rights.
  • The topic is a sensitive HR/legal/medical issue requiring specialist handling.
  • You actually need a multi-day workshop (e.g., a full design sprint) rather than a single meeting.

Inputs

Minimum required

  • Meeting objective (what changes after the meeting)
  • Meeting type (or “recommend”): operational / strategic discussion / decision / workshop
  • Attendees (and the decision owner, if any)
  • Time box + date/time constraints (and remote/hybrid details)
  • Context links or a 5–10 bullet background summary

Missing-info strategy

  • Ask up to 5 questions from references/INTAKE.md.
  • If answers aren’t available, proceed with explicit assumptions and label unknowns.

Outputs (deliverables)

Produce a Meeting Pack in Markdown (in-chat; or as files if requested), in this order:

  1. Meeting brief (goal, type, decision(s), roles, pre-work)
  2. Pre-read (context, options, open questions; “discover” happens async)
  3. Agenda (timed, discussion-first)
  4. Facilitation script (priming, prompts, how to handle stalls)
  5. Notes template + Decision log + Action items table
  6. Follow-up message (decisions, owners, deadlines, who-else-needs-to-know)
  7. Risks / Open questions / Next steps (always included)

Templates: references/TEMPLATES.md

Workflow (7 steps)

1) Decide if a meeting is needed and pick the format

  • Inputs: Request + context + constraints.
  • Actions: Clarify objective; decide whether the live meeting is for discussion only; pick meeting type (operational vs strategic vs decision vs workshop).
  • Outputs: Meeting type recommendation + meeting objective + draft brief header.
  • Checks: You can answer: “What will be different after this meeting?”

2) Define the discussion scope (what is in-room vs async)

  • Inputs: Objective; stakeholders; open questions.
  • Actions: Separate Discover / Discuss / Decide:

- Discover (context/data/options) → async pre-read - Discuss (trade-offs, objections, clarifications) → live meeting - Decide (final call + recording) → after discussion, captured explicitly

  • Outputs: Pre-read outline + list of discussion questions + decision statement(s).
  • Checks: At least 60% of the live time is reserved for discussion, not reading.

3) Prime participants (pre-work + pre-read)

  • Inputs: Pre-read outline; attendee list.
  • Actions: Create a priming section (goal, conversation category, decision rights); assign pre-work; send pre-read 24–48h before when possible.
  • Outputs: Complete pre-read + pre-work assignments.
  • Checks: Every attendee can arrive “ready to discuss” without a live info dump.

4) Build a timed agenda that matches the format

  • Inputs: Meeting type; discussion questions; time box.
  • Actions: Timebox segments; limit to 1–3 topics; include explicit decision points; reserve time for closing alignment.
  • Outputs: Agenda with timing, prompts, and expected outputs per section.
  • Checks: Agenda maps each segment to a tangible output (decision, list, owner, next step).

5) Assign roles and write the facilitation script

  • Inputs: Agenda; participants.
  • Actions: Assign facilitator, decision owner, note-taker, timekeeper; write prompts and “if stuck” branches; set ground rules (parking lot, stack, time boxing).
  • Outputs: Facilitation script + roles list.
  • Checks: Roles are named; escalation path is clear if consensus fails.

6) Run the meeting and capture decisions/actions in real time

  • Inputs: Script; notes template.
  • Actions: Start with priming; facilitate discussion; capture decisions and action items as they happen; keep to time boxes.
  • Outputs: Filled notes + decision log entries + action items table.
  • Checks: No important decision is left implicit or “to be clarified later.”

7) Close, follow up, and improve meeting hygiene

  • Inputs: Captured notes/decisions/actions.
  • Actions: End with: (1) What did we decide? (2) Who does what by when? (3) Who else needs to know? Send follow-up within 24h; propose hygiene changes (split strategic vs operational, cancel/shorten recurring meetings).
  • Outputs: Follow-up message + updated trackers + hygiene recommendations + Risks/Open questions/Next steps.
  • Checks: Every action item has an owner and due date; stakeholders to inform are named.

Quality gate (required)

Examples

Example 1 (Operational cadence): “Design a weekly operational meeting for a product squad to track priority projects without drifting into strategy.” Expected: a structured meeting brief, recurring agenda template, status update pattern, and a hygiene rule to move strategy to a separate forum.

Example 2 (Decision meeting): “Create a decision meeting pack for choosing between two onboarding flows (A vs B) with PM/Design/Eng and a decision owner.” Expected: pre-read with options + evidence, timed agenda, facilitation prompts for trade-offs, and a decision record + action items.

Boundary example: “Schedule a meeting to ‘get alignment’ but there’s no decision, no owner, and no pre-read.” Response: ask for the decision/outcome; recommend async discovery first; refuse to produce a meeting pack until objective/owner is defined.

Reference files

平台分布

Codex

32.68%
按下载量换算73

Claude

31.54%
按下载量换算70

Cursor

19.55%
按下载量换算43

Gemini CLI

9.48%
按下载量换算21

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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