PaperclipOrg
Claude Agent Skill · by Affaan M

Lead Intelligence

Install Lead Intelligence skill for Claude Code from affaan-m/everything-claude-code.

Works with Paperclip

How Lead Intelligence fits into a Paperclip company.

Lead Intelligence drops into any Paperclip agent that handles this kind of work. Assign it to a specialist inside a pre-configured PaperclipOrg company and the skill becomes available on every heartbeat — no prompt engineering, no tool wiring.

S
SaaS FactoryPaired

Pre-configured AI company — 18 agents, 18 skills, one-time purchase.

$27$59
Explore pack
Source file
SKILL.md321 lines
Expand
---name: lead-intelligencedescription: AI-native lead intelligence and outreach pipeline. Replaces Apollo, Clay, and ZoomInfo with agent-powered signal scoring, mutual ranking, warm path discovery, source-derived voice modeling, and channel-specific outreach across email, LinkedIn, and X. Use when the user wants to find, qualify, and reach high-value contacts.origin: ECC--- # Lead Intelligence Agent-powered lead intelligence pipeline that finds, scores, and reaches high-value contacts through social graph analysis and warm path discovery. ## When to Activate - User wants to find leads or prospects in a specific industry- Building an outreach list for partnerships, sales, or fundraising- Researching who to reach out to and the best path to reach them- User says "find leads", "outreach list", "who should I reach out to", "warm intros"- Needs to score or rank a list of contacts by relevance- Wants to map mutual connections to find warm introduction paths ## Tool Requirements ### Required- **Exa MCP** — Deep web search for people, companies, and signals (`web_search_exa`)- **X API** — Follower/following graph, mutual analysis, recent activity (`X_BEARER_TOKEN`, plus write-context credentials such as `X_CONSUMER_KEY`, `X_CONSUMER_SECRET`, `X_ACCESS_TOKEN`, `X_ACCESS_TOKEN_SECRET`) ### Optional (enhance results)- **LinkedIn** — Direct API if available, otherwise browser control for search, profile inspection, and drafting- **Apollo/Clay API** — For enrichment cross-reference if user has access- **GitHub MCP** — For developer-centric lead qualification- **Apple Mail / Mail.app** — Draft cold or warm email without sending automatically- **Browser control** — For LinkedIn and X when API coverage is missing or constrained ## Pipeline Overview ```┌─────────────┐     ┌──────────────┐     ┌─────────────────┐     ┌──────────────┐     ┌─────────────────┐│ 1. Signal   │────>│ 2. Mutual    │────>│ 3. Warm Path    │────>│ 4. Enrich    │────>│ 5. Outreach     ││    Scoring  │     │    Ranking   │     │    Discovery    │     │              │     │    Draft        │└─────────────┘     └──────────────┘     └─────────────────┘     └──────────────┘     └─────────────────┘``` ## Voice Before Outreach 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. ## Stage 1: Signal Scoring 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 | ### Signal Search Approach ```python# Step 1: Define target parameterstarget_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 peoplefor 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 voicesx_search = search_recent_tweets(    query="prediction markets OR AI tooling OR developer tools",    max_results=100)# Extract and score unique authors``` ## Stage 2: Mutual Ranking For each scored target, analyze the user's social graph to find the warmest path. ### Ranking Model 1. Pull user's X following list and LinkedIn connections2. For each high-signal target, check for shared connections3. Apply the `social-graph-ranker` model to score bridge value4. Rank mutuals by: | 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: ```textUse 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: ```textB(m) = Σ_{t ∈ T} w(t) · λ^(d(m,t) - 1)R(m) = B_ext(m) · (1 + β · engagement(m))``` Interpretation:- Tier 1: high `R(m)` and direct bridge paths -> warm intro asks- Tier 2: medium `R(m)` and one-hop bridge paths -> conditional intro asks- Tier 3: no viable bridge -> direct cold outreach using the same lead record ### Output Format ``` 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)    ...``` ## Stage 3: Warm Path Discovery For each target, find the shortest introduction chain: ```You ──[follows]──> Mutual A ──[invested in]──> Target CompanyYou ──[follows]──> Mutual B ──[co-founded with]──> Target PersonYou ──[met at]──> Event ──[also attended]──> Target Person``` ### Path Types (ordered by warmth)1. **Direct mutual** — You both follow/know the same person2. **Portfolio connection** — Mutual invested in or advises target's company3. **Co-worker/alumni** — Mutual worked at same company or attended same school4. **Event overlap** — Both attended same conference/program5. **Content engagement** — Target engaged with mutual's content or vice versa ## Stage 4: Enrichment For each qualified lead, pull: - Full name, current title, company- Company size, funding stage, recent news- Recent X posts (last 30 days) — topics, tone, interests- Mutual interests with user (shared follows, similar content)- Recent company events (product launch, funding round, hiring) ### Enrichment Sources- Exa: company data, news, blog posts- X API: recent tweets, bio, followers- GitHub: open source contributions (for developer-centric leads)- LinkedIn (via browser-use): full profile, experience, education ## Stage 5: Outreach Draft Generate personalized outreach for each lead. The draft should match the source-derived voice profile and the target channel. ### Channel Rules #### Email - Use for the highest-value cold outreach, warm intros, investor outreach, and partnership asks- Default to drafting in Apple Mail / Mail.app when local desktop control is available- Create drafts first, do not send automatically unless the user explicitly asks- Subject line should be plain and specific, not clever #### LinkedIn - Use when the target is active there, when mutual graph context is stronger on LinkedIn, or when email confidence is low- Prefer API access if available- Otherwise use browser control to inspect profiles, recent activity, and draft the message- Keep it shorter than email and avoid fake professional warmth #### X - Use for high-context operator, builder, or investor outreach where public posting behavior matters- Prefer API access for search, timeline, and engagement analysis- Fall back to browser control when needed- DMs and public replies should be much tighter than email and should reference something real from the target's timeline #### Channel Selection Heuristic Pick one primary channel in this order: 1. warm intro by email2. direct email3. LinkedIn DM4. X DM or reply Use multi-channel only when there is a strong reason and the cadence will not feel spammy. ### Warm Intro Request (to mutual) Goal: - one clear ask- one concrete reason this intro makes sense- easy-to-forward blurb if needed Avoid: - overexplaining your company- social-proof stacking- sounding like a fundraiser template ### Direct Cold Outreach (to target) Goal: - open from something specific and recent- explain why the fit is real- make one low-friction ask Avoid: - generic admiration- feature dumping- broad asks like "would love to connect"- forced rhetorical questions ### Execution Pattern For each target, produce: 1. the recommended channel2. the reason that channel is best3. the message draft4. optional follow-up draft5. if email is the chosen channel and Apple Mail is available, create a draft instead of only returning text If browser control is available: - LinkedIn: inspect target profile, recent activity, and mutual context, then draft or prepare the message- X: inspect recent posts or replies, then draft DM or public reply language If desktop automation is available: - Apple Mail: create draft email with subject, body, and recipient Do not send messages automatically without explicit user approval. ### Anti-Patterns - generic templates with no personalization- long paragraphs explaining your whole company- multiple asks in one message- fake familiarity without specifics- bulk-sent messages with visible merge fields- identical copy reused for email, LinkedIn, and X- platform-shaped slop instead of the author's actual voice ## Configuration Users should set these environment variables: ```bash# Requiredexport X_BEARER_TOKEN="..."export X_ACCESS_TOKEN="..."export X_ACCESS_TOKEN_SECRET="..."export X_CONSUMER_KEY="..."export X_CONSUMER_SECRET="..."export EXA_API_KEY="..." # Optionalexport LINKEDIN_COOKIE="..." # For browser-use LinkedIn accessexport APOLLO_API_KEY="..."  # For Apollo enrichment``` ## Agents This skill includes specialized agents in the `agents/` subdirectory: - **signal-scorer** — Searches and ranks prospects by relevance signals- **mutual-mapper** — Maps social graph connections and finds warm paths- **enrichment-agent** — Pulls detailed profile and company data- **outreach-drafter** — Generates personalized messages ## Example Usage ```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 leaders2. mutual-mapper checks user's X graph for shared connections3. enrichment-agent pulls company data and recent activity4. 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``` ## Related Skills - `brand-voice` for canonical voice capture- `connections-optimizer` for review-first network pruning and expansion before outreach