← 返回 Skills 市场
agistack

Lead

作者 AGIstack · GitHub ↗ · v2.1.1 · MIT-0
cross-platform ✓ 安全检测通过
366
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install lead
功能描述
Qualify, prioritize, and advance sales prospects into the next best action. Built for founders, sales reps, and operators who need sharper lead judgment, fas...
使用说明 (SKILL.md)

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.

Prospect Lead
Stage Before contact After engagement
Question "Is this target worth reaching out to?" "Should I keep pursuing this person?"
Input Names, profiles, company data, signals Conversation history, replies, behavior
Output Priority tier + route Qualification 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
  2. Missing information

    • what must be clarified before investing more time
  3. Risks or friction

    • weak authority
    • weak urgency
    • weak problem clarity
    • weak timing
    • weak follow-through
  4. Next best action

    • pursue now
    • qualify further
    • nurture
    • deprioritize
  5. 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.

安全使用建议
This skill appears internally consistent and low-risk: it only processes user-provided lead information and does not ask for credentials or install software. Before installing, confirm the skill source or homepage if provenance matters (skill.json lists https://clawhub.ai but registry metadata shows none). When using the skill, avoid submitting sensitive personal data or confidential customer information unless you're comfortable sharing it with the agent, and remember the skill will generate follow-up text from whatever you provide. If you need tighter privacy or auditability, prefer skills from known publishers or request an auditable provenance/maintainer record.
功能分析
Type: OpenClaw Skill Name: lead Version: 2.1.1 The 'Lead' skill bundle is a purely instructional set of markdown and configuration files designed to guide an AI agent through sales lead qualification and prioritization. It contains no executable code, external dependencies, or instructions to access sensitive system data, and its logic is strictly confined to the stated purpose of business process automation (skill.md, skill.json).
能力评估
Purpose & Capability
Name, description, and declared capabilities (lead qualification, gap identification, action recommendation, follow-up drafting) match the SKILL.md instructions and example usage. The skill does not request unrelated credentials or binaries. Minor metadata inconsistency: registry metadata at the top lists no homepage while skill.json contains a homepage URL (https://clawhub.ai); this is an administrative discrepancy but does not affect functionality.
Instruction Scope
Runtime instructions are narrowly scoped to parsing user-provided lead information, scoring observable dimensions (fit, intent, urgency, authority), identifying gaps, recommending actions, and drafting concise follow-ups. The execution protocol explicitly instructs the agent to score only from visible evidence and not to guess, and does not direct the agent to read local files, system state, or external endpoints beyond user input.
Install Mechanism
No install specification and no code files are present (instruction-only). This is the lowest-risk model: nothing is downloaded or written to disk by the skill itself.
Credentials
The skill requires no environment variables, credentials, or config paths. All recommended inputs are user-provided lead data (names, role, messages, firmographics). There are no disproportionate secret or system access requests.
Persistence & Privilege
The skill is not marked always:true and does not request any persistent installation or modifications to other skills. It can be invoked by the agent (default behavior) but has no elevated privileges or background persistence.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install lead
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /lead 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v2.1.1
- Added a new README.md file. - Updated language in the Upstream Check to clarify when to use `/prospect` versus Lead, and note the requirement for engagement. - Added `/pipeline` reference under "Works Well With" for integration guidance. - No changes to core skill logic or functionality.
v2.1.0
**Version 2.1.0 Summary:** Introduces clearer guidance on when to use Lead vs Prospect, and adds upstream filtering. - Added a new "Lead vs Prospect" section to clarify stage-appropriate usage. - Introduced an "Upstream Check" to suggest using Prospect when only pre-engagement info is present. - Updated activation rules: use Lead skill only after there has been engagement. - Added interoperability note: recommends `@dpetcr/prospect` for pre-outreach targeting. - No changes to scoring or decision logic.
v2.0.0
**Lead 2.0.0 – Major update for clarity, precision, and decisive sales lead handling.** - Scope narrowed strictly to sales lead qualification (not music, medicine, journalism, or generic roles). - New decision framework: clear scoring and step-by-step protocol for fit, intent, urgency, and authority. - Explicit next-action recommendations (pursue, qualify, nurture, deprioritize) based on evidence; avoids guesswork. - Improved prompts and output guidelines for actionable, non-generic follow-up drafts. - Strong boundaries and use-case rules for when to apply the skill and when not to.
v1.0.0
Initial release with four-file structure
元数据
Slug lead
版本 2.1.1
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 4
常见问题

Lead 是什么?

Qualify, prioritize, and advance sales prospects into the next best action. Built for founders, sales reps, and operators who need sharper lead judgment, fas... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 366 次。

如何安装 Lead?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install lead」即可一键安装,无需额外配置。

Lead 是免费的吗?

是的,Lead 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Lead 支持哪些平台?

Lead 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Lead?

由 AGIstack(@agistack)开发并维护,当前版本 v2.1.1。

💬 留言讨论