Menü
AI 原生线索情报和外联流水线。用智能体驱动的信号评分、互惠排名、热路径发现、来源语音建模和跨渠道外联（电子邮件、LinkedIn 和 X）替代 Apollo、Clay 和 ZoomInfo。当用户想要查找、评估和触达高价值联系人时使用。
| name | lead-intelligence |
| description | AI 原生线索情报和外联流水线。用智能体驱动的信号评分、互惠排名、热路径发现、来源语音建模和跨渠道外联（电子邮件、LinkedIn 和 X）替代 Apollo、Clay 和 ZoomInfo。当用户想要查找、评估和触达高价值联系人时使用。 |
| origin | ECC |
Agent-powered lead intelligence pipeline that finds, scores, and reaches high-value contacts through social graph analysis and warm path discovery.
web_search_exa)X_BEARER_TOKEN, plus write-context credentials such as X_CONSUMER_KEY, X_CONSUMER_SECRET, X_ACCESS_TOKEN, X_ACCESS_TOKEN_SECRET)┌─────────────┐ ┌──────────────┐ ┌─────────────────┐ ┌──────────────┐ ┌─────────────────┐
│ 1. Signal │────>│ 2. Mutual │────>│ 3. Warm Path │────>│ 4. Enrich │────>│ 5. Outreach │
│ Scoring │ │ Ranking │ │ Discovery │ │ │ │ Draft │
└─────────────┘ └──────────────┘ └─────────────────┘ └──────────────┘ └─────────────────┘
Do not draft outbound from generic sales copy.
Run brand-voice first whenever the user's voice matters. Reuse its VOICE PROFILE instead of re-deriving style ad hoc inside this skill.
If live X access is available, pull recent original posts before drafting. If not, use supplied examples or the best repo/site material available.
Search for high-signal people in target verticals. Assign a weight to each based on:
| Signal | Weight | Source |
|---|---|---|
| Role/title alignment | 30% | Exa, LinkedIn |
| Industry match | 25% | Exa company search |
| Recent activity on topic | 20% | X API search, Exa |
| Follower count / influence | 10% | X API |
| Location proximity | 10% | Exa, LinkedIn |
| Engagement with your content | 5% | X API interactions |
# Step 1: Define target parameters
target_verticals = ["prediction markets", "AI tooling", "developer tools"]
target_roles = ["founder", "CEO", "CTO", "VP Engineering", "investor", "partner"]
target_locations = ["San Francisco", "New York", "London", "remote"]
# Step 2: Exa deep search for people
for vertical in target_verticals:
results = web_search_exa(
query=f"{vertical} {role} founder CEO",
category="company",
numResults=20
)
# Score each result
# Step 3: X API search for active voices
x_search = search_recent_tweets(
query="prediction markets OR AI tooling OR developer tools",
max_results=100
)
# Extract and score unique authors
For each scored target, analyze the user's social graph to find the warmest path.
social-graph-ranker model to score bridge value| Factor | Weight |
|---|---|
| Number of connections to targets | 40% — highest weight, most connections = highest rank |
| Mutual's current role/company | 20% — decision maker vs individual contributor |
| Mutual's location | 15% — same city = easier intro |
| Industry alignment | 15% — same vertical = natural intro |
| Mutual's X handle / LinkedIn | 10% — identifiability for outreach |
Canonical rule:
Use social-graph-ranker when the user wants the graph math itself,
the bridge ranking as a standalone report, or explicit decay-model tuning.
Inside this skill, use the same weighted bridge model:
B(m) = Σ_{t ∈ T} w(t) · λ^(d(m,t) - 1)
R(m) = B_ext(m) · (1 + β · engagement(m))
Interpretation:
R(m) and direct bridge paths -> warm intro asksR(m) and one-hop bridge paths -> conditional intro asks
If the user explicitly wants the ranking engine broken out, the math visualized, or the network scored outside the full lead workflow, run `social-graph-ranker` as a standalone pass first and feed the result back into this pipeline.
MUTUAL RANKING REPORT
=====================
#1 @mutual_handle (Score: 92)
Name: Jane Smith
Role: Partner @ Acme Ventures
Location: San Francisco
Connections to targets: 7
Connected to: @target1, @target2, @target3, @target4, @target5, @target6, @target7
Best intro path: Jane invested in Target1's company
#2 @mutual_handle2 (Score: 85)
...
For each target, find the shortest introduction chain:
You ──[follows]──> Mutual A ──[invested in]──> Target Company
You ──[follows]──> Mutual B ──[co-founded with]──> Target Person
You ──[met at]──> Event ──[also attended]──> Target Person
For each qualified lead, pull:
Generate personalized outreach for each lead. The draft should match the source-derived voice profile and the target channel.
Pick one primary channel in this order:
Use multi-channel only when there is a strong reason and the cadence will not feel spammy.
Goal:
Avoid:
Goal:
Avoid:
For each target, produce:
If browser control is available:
If desktop automation is available:
Do not send messages automatically without explicit user approval.
Users should set these environment variables:
# Required
export X_BEARER_TOKEN="..."
export X_ACCESS_TOKEN="..."
export X_ACCESS_TOKEN_SECRET="..."
export X_CONSUMER_KEY="..."
export X_CONSUMER_SECRET="..."
export EXA_API_KEY="..."
# Optional
export LINKEDIN_COOKIE="..." # For browser-use LinkedIn access
export APOLLO_API_KEY="..." # For Apollo enrichment
This skill includes specialized agents in the agents/ subdirectory:
User: find me the top 20 people in prediction markets I should reach out to
Agent workflow:
1. signal-scorer searches Exa and X for prediction market leaders
2. mutual-mapper checks user's X graph for shared connections
3. enrichment-agent pulls company data and recent activity
4. outreach-drafter generates personalized messages for top ranked leads
Output: Ranked list with warm paths, voice profile summary, and channel-specific outreach drafts or drafts-in-app
brand-voice for canonical voice captureconnections-optimizer for review-first network pruning and expansion before outreach从零开始或通过转换 PowerPoint 文件创建精美的、动画丰富的 HTML 演示文稿。当用户想要构建演示文稿、将 PPT/PPTX 转换为网页或为演讲/路演创建幻灯片时使用。帮助非设计师通过视觉探索而非抽象选择发现他们的审美。
可视化技能、规则和智能体定义是否被真正遵循 — 自动生成 3 个提示严格度级别的场景，运行智能体，分类行为序列，并报告合规率及完整工具调用时间线
使用 tinystruct Java 框架进行开发的专家指南。在 tinystruct 代码库或任何基于 tinystruct 构建的项目上工作时使用 — 包括创建 Application 类、@Action 映射路由、单元测试、ActionRegistry、HTTP/CLI 双模式处理、内置 HTTP 服务器、事件系统、JSON 与 Builder/Builders、使用 AbstractData 的数据库持久化、POJO 生成、Server-Sent Events (SSE)、文件上传和出站 HTTP 网络。
查看、理解、操作视频和音频。查看 — 从本地文件、URL、RTSP/直播流或实时录制桌面进行摄取；返回实时上下文和可播放的流链接。理解 — 提取帧、构建视觉/语义/时间索引，以及带时间戳和自动片段的搜索时刻。操作 — 转码和归一化（编解码器、fps、分辨率、宽高比）、执行时间线编辑（字幕、文本/图像叠加、品牌、音频叠加、配音、翻译）、生成媒体资产（图像、音频、视频），以及为直播流或桌面捕获中的事件创建实时警报。
Remotion 的最佳实践 —— 在 React 中创建视频。涵盖 3D、动画、音频、字幕、图表、转场等 29 条领域特定规则。
翻译签证申请文件（图片）为英文并创建包含原文和译文的双语 PDF