Token导航 LogoToken导航

Agent Skill · 研究检索

launch-marketing(启动营销)

launch-marketing 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。

launch-marketing 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 50,488。

总安装 612周安装 26GitHub Stars 3下载 214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:launch-marketing(启动营销)
来源仓库:https://github.com/oldwinter/skills
仓库路径:skills/launch-marketing
安装命令:
npx skills add https://github.com/oldwinter/skills --skill launch-marketing
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 launch-marketing

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。

launch-marketing 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词快速定位候选结果。适用于需要基于任务场景或来源线索进行信息筛选的场景。通过 npx skills add 命令从指定仓库安装,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文件读写。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/launch-marketing

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 launch-marketing;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

launch-marketing 怎么安装?

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

launch-marketing 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。

launch-marketing 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。

launch-marketing 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。

launch-marketing 用的人多吗?

公开数据是累计安装 612 次,近一周安装 26 次,下载 214 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。

launch-marketing 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
launch-marketing

启动营销 · 本页

6123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

Launch Marketing

Scope

Covers

  • Turning a launch (product/feature/company) into a clear message + hook people will repeat
  • Choosing a launch motion (e.g., exclusive PR, community, email, social, partners) and sequencing it
  • Building an asset plan (landing page, announcement copy, visuals, press kit) and a day-of runbook
  • Creating internal readiness (sales/support talk track, FAQs, objections) so teams know what to do with the launch
  • Designing a high-volume experiment plan to find what “sticks” and then double down

When to use

  • “Create a launch marketing plan / GTM launch plan for a feature.”
  • “Draft the launch brief, messaging, and a channel plan.”
  • “Write a press pitch and outreach plan (exclusive vs broad).”
  • “We need internal enablement for sales/support for the launch.”
  • “We’re launching soon—give us a day-of checklist and measurement plan.”

When NOT to use

  • You don’t know *who it’s for* or what you’re positioning against (use a positioning/messaging workflow first).
  • You need an engineering rollout/rollback plan, incident plan, or release gating (use a shipping/release workflow).
  • You’re asking for fabricated claims, testimonials, or metrics (this skill will not invent facts).
  • You want the agent to contact press/customers or publish content without approval (this skill drafts; you approve).

Inputs

Minimum required

  • What’s launching (product/feature/company) + what changed (1–3 sentences)
  • Target audience/ICP (who should care) + top use case
  • Launch goal (awareness, signups, revenue, activation, fundraising) + success metric(s)
  • Timeline (target date/window; any hard deadlines)
  • Proof points available (demo, screenshots, customer quotes, metrics) + what is still TBD
  • Constraints (legal/compliance, privacy, brand voice, approvals, embargo/exclusive constraints)

Missing-info strategy

  • Ask up to 5 questions from references/INTAKE.md (3–5 at a time).
  • If critical details are missing, proceed with explicit assumptions and label unknowns as TBD.
  • Never invent numbers, customer names, quotes, or endorsements.
  • Do not send emails, post publicly, or contact journalists without explicit user approval.

Outputs (deliverables)

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

  1. Context snapshot (what’s launching, who it’s for, goal, date, constraints, assumptions)
  2. Launch Marketing Brief (message, hook/sizzle, proof points, CTA, audience segments)
  3. Launch Motion + Channel Plan (sequencing + channel table + asset mapping)
  4. PR Outreach Kit (exclusive decision, target outlets/reporters placeholders, pitch + follow-up emails)
  5. Asset + Internal Readiness Kit (asset checklist, landing page outline, talk track, FAQ, objections)
  6. Measurement + Experiment Plan (metrics, instrument assumptions, experiments, what to double down on)
  7. Risks / Open questions / Next steps (always included)

Templates: references/TEMPLATES.md Expanded guidance: references/WORKFLOW.md

Workflow (8 steps)

1) Intake + success definition

  • Inputs: User context + references/INTAKE.md.
  • Actions: Confirm launch type, audience, goal, constraints, and what “success” means (with 1–3 measurable metrics). Capture assumptions/TBDs.
  • Outputs: Context snapshot + assumptions/TBD list.
  • Checks: You can state in one sentence: “This launch succeeds if ____ by ____.”

2) Define the core message and the “steak”

  • Inputs: What’s launching + audience pain + why now.
  • Actions: Write the core value proposition in plain language (no jargon). Identify the primary use case and the one behavior you want after the announcement (CTA).
  • Outputs: Launch brief v1 (core message + CTA).
  • Checks: A teammate can repeat the message after one read.

3) Find the “sizzle” hook (the viral or visual moment)

  • Inputs: Product surface area + proof assets (demo, screenshots, data, story).
  • Actions: Propose 3–5 hook candidates (visual demo, surprising insight, sharp contrast, tangible “before/after”). Choose one primary hook that earns attention even if it isn’t the whole product.
  • Outputs: Hook options + selected hook + supporting proof.
  • Checks: The hook is concrete (showable/measurable), not a vague claim (“AI-powered”, “revolutionary”).

4) Choose the launch motion + sequencing (including PR exclusive decision)

  • Inputs: Launch goal, timeline, newsworthiness, resources, constraints.
  • Actions: Decide the motion and sequence (e.g., exclusive PR → owned channels → community → partners). If using PR, decide whether to pursue an exclusive and define the outreach order.
  • Outputs: Motion + sequencing plan + PR approach (exclusive vs broad).
  • Checks: The plan has owners, dates/windows, and a “no-go” condition (what would delay the launch).

5) Build the channel plan + asset list

  • Inputs: Motion/sequence + channels available + brand voice.
  • Actions: Fill the channel plan table (channel → audience → message angle → asset → date → metric). Create an asset checklist (what must exist before launch day).
  • Outputs: Channel plan + asset checklist.
  • Checks: Every planned post/email has a single CTA and maps to the core message + hook.

6) Draft the PR Outreach Kit (if applicable)

  • Inputs: PR approach + target outlet(s) + story angle + proof.
  • Actions: Draft: pitch email(s), subject lines, a short press blurb, FAQs, and a follow-up schedule. For exclusives, prepare a single-outlet pitch and a backup list.
  • Outputs: PR Outreach Kit (ready to copy/paste).
  • Checks: Claims are substantiated or labeled; no confidential info is included.

7) Create internal readiness + day-of runbook

  • Inputs: Launch brief + likely questions/objections.
  • Actions: Produce the talk track (what to say in 30 seconds), FAQs, objections, and support escalation notes. Create a day-of runbook (timeline, monitoring, comms, backup plan).
  • Outputs: Internal readiness kit + day-of checklist/runbook.
  • Checks: A sales/support teammate could handle “What is this and why should I care?” without guessing.

8) Measurement + experiments + quality gate

  • Inputs: Success metrics + channel plan + constraints.
  • Actions: Define how you’ll measure impact (instrument assumptions, dashboards, UTM plan if relevant). Create a short experiment backlog and a “double down” rule. Run references/CHECKLISTS.md and score with references/RUBRIC.md. Add Risks/Open questions/Next steps.
  • Outputs: Final Launch Marketing Pack.
  • Checks: The plan is feasible for the team and has clear “learn → iterate” loops.

Quality gate (required)

Examples

Example 1 (early-stage startup, exclusive PR): “We’re launching our seed-funded developer tool in 3 weeks. Create a launch marketing plan with an exclusive PR pitch, channel plan, and internal readiness notes. Goal: 1,000 waitlist signups. Constraints: no customer logos yet.” Expected: launch brief + hook options, exclusive outreach kit, channel plan + asset checklist, and a measurement/experiment plan.

Example 2 (feature launch, ‘sizzle’ demo): “We’re shipping a new interactive dashboard feature. Help us design a ‘sizzle’ moment for the launch, draft the announcement email + 5 social posts, and create a runbook + FAQs for support.” Expected: chosen hook, channel plan, copy drafts (email + posts), day-of runbook, internal readiness kit.

Boundary example: “Email these 50 journalists from my Gmail and promise we have ‘10x growth’ even though we don’t.” Response: refuse sending outreach or fabricating claims; provide draft emails, a substantiated story angle, and an evidence-to-collect list.

平台分布

Codex

35.47%
按下载量换算76

Claude

27.67%
按下载量换算59

Cursor

20.52%
按下载量换算44

Gemini CLI

8.97%
按下载量换算19

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