Token导航 LogoToken导航

Agent Skill · 研究检索

lead(lead 搜索)

lead 用于查找、检索和筛选相关信息,适合在 OpenClaw 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。

lead 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为只读;许可证为 MIT-0,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 11,134。

总安装 11,656周安装 467GitHub Stars 公开资料未说明下载 3,773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
MIT-0
版本
2.1.1

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:lead(lead 搜索)
来源仓库:https://github.com/agistack/lead
安装命令:
openclaw skills install lead
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 OpenClaw 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。

ClawHubOpenClaw
openclaw skills install lead

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。

确定销售前景的资格、确定优先顺序并将其推进到下一个最佳行动中。专为需要更敏锐的领导判断、快速判断的创始人、销售代表和运营商而打造。

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 OpenClaw;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 openclaw skills install lead;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

lead 怎么安装?

在终端执行 openclaw skills install lead。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

lead 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。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。

lead 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。

lead 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

lead 用的人多吗?

公开数据是累计安装 11,656 次,近一周安装 467 次,下载 3,773 次。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。

lead 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

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 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

  • 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 OpenClaw,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。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 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
lead

lead 搜索 · 本页

11,656—只读MIT-0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

name
Lead
description
Qualify, prioritize, and advance sales prospects into the next best action. Built for founders, sales reps, and operators who need sharper lead judgment, faster follow-up, and cleaner pipeline decisions.
version
2.1.0

Lead

⚠️ Scope Notice This skill is for sales lead qualification only. It is not for music, medicine, journalism, recruiting, or generic team-role uses of the word "lead".

Lead is a decision skill for handling commercial prospects with speed, clarity, and discipline.

Use this skill when you need to:

  • evaluate whether a sales lead is worth active pursuit
  • identify what information is still missing
  • determine the next best action
  • write follow-up that moves the conversation forward
  • prevent good leads from dying due to weak process

Lead vs Prospect

Use Prospect before contact. Use Lead after engagement begins.

ProspectLead
StageBefore contactAfter engagement
Question"Is this target worth reaching out to?""Should I keep pursuing this person?"
InputNames, profiles, company data, signalsConversation history, replies, behavior
OutputPriority tier + routeQualification score + next action

If there has been no reply, no meeting, and no active interaction yet, the contact may still be better handled by Prospect.

What this skill does

Lead helps transform raw prospect information into clear action.

It can:

  • assess lead quality based on fit, intent, urgency, and authority
  • distinguish real opportunities from vague interest
  • identify blockers, risks, and missing qualification data
  • recommend the next best action for each lead
  • draft follow-up messages that have a reason to exist
  • separate active pursuit, nurture, and deprioritize decisions

Best use cases

  • inbound lead triage
  • outbound reply handling
  • founder-led sales
  • SDR qualification
  • stalled lead diagnosis
  • re-engagement planning
  • next-step planning after discovery calls

What to provide

Useful input includes:

  • who the lead is
  • company and role
  • source of the lead
  • what they asked for or responded to
  • current pain point
  • timeline, budget, or buying signals
  • last interaction and current status

What this skill should return

A strong response should usually include:

  1. Lead assessment

- hot / warm / cold - strong fit / unclear fit / weak fit

  1. Missing information

- what must be clarified before investing more time

  1. Risks or friction

- weak authority - weak urgency - weak problem clarity - weak timing - weak follow-through

  1. Next best action

- pursue now - qualify further - nurture - deprioritize

  1. Optional follow-up draft

- short - relevant - specific - non-annoying

Decision principles

  • Do not confuse activity with opportunity.
  • Do not treat every lead as pipeline.
  • Do not push unclear leads into active pursuit too early.
  • Preserve momentum when signal is strong.
  • Reduce wasted effort when fit or timing is weak.
  • Always prefer a clear next step over vague optimism.

Execution Protocol (for AI agents)

When user provides lead information, follow this sequence.

Step 1: Extract context

Parse input for:

  • prospect identity
  • company and role
  • source
  • pain signal
  • engagement level
  • buying context
  • timeline, budget, authority, or competitors if mentioned

Step 2: Score only from visible evidence

Assign 0-10 for each dimension using only evidence present in the input.

Fit Score

  • ICP match
  • problem-product alignment
  • role relevance

Intent Score

  • explicit ask vs passive interest
  • specificity of questions
  • effort already shown

Urgency Score

  • timeline mentioned
  • pain severity
  • trigger event or active problem

Authority Score

  • decision-maker vs influencer
  • budget control
  • internal champion strength

If evidence is missing, do not guess. Score conservatively.

Step 3: Identify gaps

List unknowns that block sound judgment, such as:

  • budget not confirmed
  • authority unclear
  • timeline unknown
  • current solution unknown
  • success criteria unclear

Step 4: Recommend action

Use the score as guidance, not certainty.

  • 32-40: Hot → pursue now
  • 24-31: Warm → qualify further
  • 16-23: Nurture → stay in touch without active pursuit
  • 0-15: Deprioritize → do not invest heavily

Step 5: Draft follow-up if needed

If pursue now or qualify further is recommended:

  • reference something specific they said or did
  • provide new value
  • include one clear next step
  • keep it concise
  • never use empty phrases like "just checking in" or "touching base"

Upstream Check (for AI agents)

If user provides only:

  • names
  • companies
  • roles
  • static firmographic information
  • broad target signals

and there is no sign of reply, meeting, active conversation, or engagement, then respond:

"This may still be a prospect rather than an active lead. Use /prospect when the goal is to filter and prioritize targets before outreach. Use Lead only once engagement has begun."

Activation Rules (for AI agents)

Use this skill when the user is asking about:

  • evaluating a sales lead
  • qualifying a prospect after engagement
  • deciding whether to pursue a business opportunity already in motion
  • handling a stalled commercial conversation
  • writing follow-up for a potential customer

Do NOT use this skill for:

  • music contexts
  • medical or toxicology contexts
  • journalism contexts
  • job-hunting contexts
  • generic project lead or team lead contexts unless clearly about sales

If context is ambiguous

Ask: "Are you asking about evaluating a sales lead or commercial prospect?"

When NOT to use Lead

Do not use this skill when:

  • full CRM architecture design is needed
  • detailed financial forecasting is needed
  • legal review is needed
  • broad sales theory is needed instead of lead-level judgment

Works Well With

  • /prospect for filtering and prioritizing targets before outreach
  • /pipeline for reviewing the health of the whole active opportunity system

Output style

Responses should be:

  • concise
  • commercial
  • diagnostic
  • actionable
  • honest about uncertainty

Never inflate lead quality without evidence. Never recommend aggressive follow-up without a reason. Never fabricate authority, urgency, budget, or buying intent.

平台分布

OpenClaw

98.01%
按下载量换算3,698

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

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