← 返回 Skills 市场
d4umak

HeyLead

作者 D4umak · GitHub ↗ · v0.9.13
cross-platform ⚠ suspicious
460
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install heylead
功能描述
HeyLead is an autonomous LinkedIn SDR that creates buyer personas, manages outreach campaigns, sends personalized messages, follows up, and tracks pipeline a...
使用说明 (SKILL.md)

HeyLead — Autonomous LinkedIn SDR

Your AI sales rep. One command to fill your pipeline.

HeyLead is an MCP-native autonomous LinkedIn SDR that gives your OpenClaw agent the ability to do LinkedIn outreach — find prospects, send personalized messages, follow up, and close deals.

What This Skill Does

This skill connects HeyLead as an MCP server in your OpenClaw agent, giving it 34 specialized LinkedIn outreach tools:

  • ICP Generation — RAG-powered buyer personas with pain points, fears, barriers, and LinkedIn search parameters
  • Campaign Management — Create, pause, resume, archive, and compare outreach campaigns
  • Personalized Outreach — Voice-matched connection invitations that sound like you, not a bot
  • Multi-Touch Sequences — Follow-up DMs, engagement warm-ups (comments, likes, endorsements)
  • Reply Handling — Sentiment classification, auto-responses, meeting scheduling
  • Analytics — Funnel reports, conversion rates, stale lead detection, engagement ROI
  • Autonomous Scheduling — 24/7 cloud scheduler for invitations, follow-ups, and reply checks

Setup

Prerequisites

  • uv installed (brew install uv on Mac, or curl -LsSf https://astral.sh/uv/install.sh | sh)

Configuration

Add to your openclaw.json:

{
  "mcp": {
    "servers": [
      {
        "name": "heylead",
        "command": "uvx",
        "args": ["heylead"]
      }
    ]
  }
}

First-Time Account Setup

After adding the MCP server, tell your OpenClaw agent:

"Set up my HeyLead profile"

You'll get a sign-in link — authenticate with Google, connect LinkedIn, copy your token, and paste it back. Takes ~1 minute, no API keys needed.

Usage Examples

"Find me CTOs at fintech startups in New York"
"Generate an ICP for AI SaaS founders"
"Create a campaign targeting VP of Sales at Series B startups"
"Send outreach to the campaign"
"Check my replies"
"How's my outreach doing?"
"Suggest next action"
"Enable the cloud scheduler"

Typical Workflow

1. setup_profile(backend_jwt="...")        → Connect LinkedIn
2. generate_icp(target="CTOs fintech")     → Create buyer personas
3. create_campaign(target="...", icp_id="...") → Find prospects
4. toggle_scheduler(enabled=True)          → Autopilot outreach
5. check_replies() / show_status()         → Monitor pipeline
6. close_outreach(outcome="won")           → Track conversions

Two Modes

  • Autopilot — AI handles outreach automatically within rate limits and working hours
  • Copilot — Review every message before it sends

All 34 Tools

Tool What it does
setup_profile Connect LinkedIn, analyze writing style, create voice signature
generate_icp Create Ideal Customer Profiles with buyer personas
create_campaign Find prospects and build an outreach campaign
generate_and_send Send personalized connection invitations
send_followup Follow-up DMs after connection accepted
reply_to_prospect Auto-reply based on sentiment analysis
engage_prospect Comment, react, follow, or endorse prospects
send_voice_memo Send voice notes on LinkedIn
check_replies Monitor inbox, classify sentiment, surface hot leads
show_status Campaign dashboard with stats and health
campaign_report Detailed analytics and funnel report
suggest_next_action AI-recommended next step
approve_outreach Approve/edit/skip copilot messages
show_conversation View full message thread with a prospect
edit_campaign Update name, mode, booking link, preferences
pause_campaign Pause outreach on a campaign
resume_campaign Resume a paused campaign
archive_campaign Mark campaign as completed
delete_campaign Permanently delete a campaign
skip_prospect Remove a bad-fit prospect
retry_failed Retry failed outreaches
emergency_stop Kill switch — pause all campaigns
export_campaign Export results as table/CSV/JSON
compare_campaigns Side-by-side campaign comparison
close_outreach Record won/lost/opted-out outcome
toggle_scheduler Enable/disable autonomous scheduler
scheduler_status View scheduler state and pending jobs
create_post Generate and publish LinkedIn posts
brand_strategy LinkedIn personal brand audit and strategy
import_prospects Import prospects from CSV
crm_sync Sync won deals to HubSpot CRM
show_strategy View strategy engine insights
manage_watchlist Manage signal keyword watchlists
show_signals View detected buying signals

Pricing

Plan Price Limits
Free $0 50 invitations/month, 1 campaign, 30 engagements/month
Pro $29/mo Unlimited campaigns, 5 LinkedIn accounts, cloud scheduler

Privacy

  • Contacts and messages stored in local SQLite database
  • AI calls routed through HeyLead backend (Gemini 2.0 Flash) or your own key
  • No messages or contacts stored on HeyLead servers

Links

License

MIT

安全使用建议
This skill does roughly what it says (autonomous LinkedIn outreach), but there are several inconsistencies you should resolve before installing: - Verify the upstream project: inspect the GitHub repo and the PyPI package source (the SKILL.md links exist, but 'source: unknown' in metadata is concerning). Make sure the heylead package you install is the same code the skill documents. - Clarify the installer command ('uv' vs 'uvx'): ask the author which binary you must install and where it comes from. Avoid running curl | sh on an unknown host without reviewing the install script contents. - Confirm data flows and storage: the skill claims local-only storage for contacts/messages but also says LLM calls can route through HeyLead backend. Ask whether messages or metadata are transmitted to HeyLead servers and whether any tokens are retained server-side. - Prefer using your own LLM key and verify how/where that key is stored. If possible, test in an isolated environment or sandbox account before connecting production LinkedIn/Google accounts. - Expect to paste OAuth tokens during setup; ensure you understand what the token scope is (read/write messages, connections, profile) and revoke it if you uninstall. If you cannot get clear answers to the above, treat the skill as higher-risk and avoid provisioning it with real accounts or sensitive credentials.
功能分析
Type: OpenClaw Skill Name: heylead Version: 0.9.13 The skill is classified as suspicious primarily due to the `curl -LsSf https://astral.sh/uv/install.sh | sh` instruction in `SKILL.md` for installing the `uv` prerequisite. While `uv` is a legitimate tool and this is a common installation method, it represents a supply chain vulnerability by executing a remote script, which could lead to arbitrary code execution if the source (`astral.sh`) were compromised. Additionally, the skill handles sensitive LinkedIn authentication tokens and personal data, routing AI call content to external backends (HeyLead or Gemini), which, despite privacy claims of local storage for contacts/messages, involves significant trust in the skill's unseen implementation.
能力评估
Purpose & Capability
The feature set (LinkedIn outreach, account linking, scheduling) reasonably explains needing a connector and account tokens. However, the SKILL.md asks you to install 'uv' but the MCP configuration and manifest use the command 'uvx' — that mismatch is unexplained and could cause confusion or point to missing install steps. Repository/homepage metadata is inconsistent (source 'unknown' vs links in SKILL.md and clawhub.json).
Instruction Scope
Instructions direct you to connect Google and LinkedIn accounts and to copy/paste tokens during setup (expected for this capability). But the skill also states AI calls are routed through the HeyLead backend (Gemini 2.0 Flash) unless you use your own key — that implies message content and contacts might be transmitted to an external backend despite the claim that 'No messages or contacts stored on HeyLead servers.' The SKILL.md does not clearly specify what data is sent to the backend versus stored locally.
Install Mechanism
This is instruction-only (no code files), so risk is lower. The SKILL.md recommends installing 'uv' using a remote installer (curl ... | sh), which is a higher-risk pattern than a curated package because it runs a remote script. The manifest suggests running 'uvx heylead' but SKILL.md only documents installing 'uv' — the install/run mismatch is unexplained.
Credentials
clawhub.json and the skill declare no required environment variables, but runtime setup clearly involves tokens (Google/LinkedIn) and optionally an LLM key. The lack of declared env vars is inconsistent with the instructions that ask you to paste a 'token' and optionally use 'your own key'. That omission makes it harder to audit what credentials will be in scope and where they will be stored or transmitted.
Persistence & Privilege
The skill is not forced-always and does not request elevated platform flags. It requires adding an MCP server entry to openclaw.json (user action) which grants it persistent availability, but that behavior is expected for an MCP-native integration and is not itself excessive.
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 heylead
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /heylead 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
v0.9.13
v0.9.13 release
v0.9.12
OpenClaw integration, updated tool count to 34
v0.9.11
HeyLead 0.9.11 Changelog - Added detailed SKILL.md documentation, including tool descriptions, setup instructions, workflow, modes, and privacy info - Outlined all 34 supported LinkedIn SDR tools with clear capabilities and sample usage - Provided pricing tiers and improved onboarding steps for OpenClaw integration - Clarified autonomous vs. copilot workflow and data privacy practices - Updated links for PyPI, GitHub, and issue tracking
元数据
Slug heylead
版本 0.9.13
许可证
累计安装 0
当前安装数 0
历史版本数 3
常见问题

HeyLead 是什么?

HeyLead is an autonomous LinkedIn SDR that creates buyer personas, manages outreach campaigns, sends personalized messages, follows up, and tracks pipeline a... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 460 次。

如何安装 HeyLead?

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

HeyLead 是免费的吗?

是的,HeyLead 完全免费(开源免费),可自由下载、安装和使用。

HeyLead 支持哪些平台?

HeyLead 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 HeyLead?

由 D4umak(@d4umak)开发并维护,当前版本 v0.9.13。

💬 留言讨论