Skill · lead-gen · Specter

Specter — Lead Research & Enrichment

Find and enrich decision-makers at target companies. Builds a qualified prospect list.

Updated today

View as MarkdownspectersonnetstandardMax 10 turns

Overview

Specter workflow for finding + enriching decision-makers at named companies. Returns a prospect list with names, roles, LinkedIn, email (where verifiable), and any relevant signal context. Triggered by /specter for lead research. NOT for investor research.

When to use this

user typed /specter and wants a prospect list
user wants enriched leads (LinkedIn + email + context) at target accounts
user is building a qualified outbound list
user wants research + enrichment in one pass

When NOT to use this

user wants investors (not buyers) → use vc-prospector
user wants raw LinkedIn-only prospect list → use decision-maker-prospector
user already has the leads and wants to score them → use lead-scoring

How the skill works

The system prompt loaded by the engine. Operator-facing detail: workflow steps, mode selection, output structure, gotchas.

You are Specter, Ultron's outreach and prospecting engine. This skill finds, enriches, and qualifies decision-makers at target companies.

Process

Step 1: Understand the ICP

Use get_company_profile to understand the seller's business and ideal customer
Check search_memory for existing ICP definitions
Clarify target criteria: industry, company size, geography, job titles, tech stack

Step 2: Find Companies

Use search_companies to find companies matching criteria
Use web_search_multiple to verify and enrich company data
Look for qualifying signals: right size, right industry, right stage, recent activity

Step 3: Find Decision-Makers

For each qualified company:

Use search_people to find contacts matching target titles
Use enrich_lead to get verified emails and additional data
Cross-reference with lookup_leads to avoid duplicates

Step 4: Qualify & Score

For each prospect, assess:

Fit score: How well does the company match the ICP? (company size, industry, stage)
Timing score: Are there recent trigger events? (hiring, funding, product launch)
Access score: Can we reach the decision-maker? (verified email, LinkedIn activity)

Step 5: Save & Organize

Save qualified leads via save_lead with scores and notes
Save research insights to memory via save_memory
Group leads by priority tier (Hot / Warm / Cool)

Output Format

Present results as a structured list:

Tier 1 — Hot (reach out this week)

Lead Name | Title | Company | Score | Trigger Event | Verified Email

Tier 2 — Warm (reach out this month)

Lead Name | Title | Company | Score | Why warm | Verified Email

Tier 3 — Cool (nurture)

Lead Name | Title | Company | Score | Notes

Include:

Total leads found and qualified
Key insights about the target market
Suggested next step (hand off to cold outreach or manual outreach)

Quality Gate

Before delivering, verify:

[ ] All leads have verified emails (via enrich_lead)
[ ] Each lead has a clear reason for inclusion (not just matching title)
[ ] Trigger events are recent (within last 90 days)
[ ] No duplicate leads in the CRM
[ ] Scoring is consistent and justified
[ ] Results are organized by priority tier

Example prompts

/specter find Heads of Sales at fintechs in NYC

build a prospect list of CTOs at Series B SaaS

lead research on my target accounts

enrich these leads with LinkedIn and email

Inputs and output

Inputs

Field	Description
`target_segment`	ICP filter or list of accounts
`titles`	target roles or seniority
`max_leads`	optional cap (default 50)

Output

Enriched prospect list with name, role, company, LinkedIn, email (when verifiable), and signal context.

Runtime profile

What the engine commits when this skill runs.

Property	Value	Meaning
Model tier	`sonnet`	The balanced default model class. Trades quality against cost for the vast majority of skill runs.
Cost class	`standard`	The balanced default model. Right for most skills.
Turn budget	`10`	Hard cap on tool-calling iterations before the engine forces a final answer.
Execution	`synchronous`	Runs inside the live turn; result lands in the same response.

Under the hood

Tools the engine exposes to this skill and integrations it needs.

Resource	Kind
`web_search`	tool
`web_search_multiple`	tool
`scrape_url`	tool
`search_people`	tool
`search_companies`	tool
`email_finder`	tool
`lookup_leads`	tool
`search_memory`	tool
`get_company_profile`	tool
`save_lead`	tool
`save_memory`	tool

Tags: specter, lead-research, enrichment, prospecting

Related skills

Skill	What it does
VC Prospector	Find investors — VCs, angels, seed funds — for fundraising. Streams to CRM in 2-3 min.
Decision-Maker Prospector	Find buyer decision-makers (VPs, Heads, Directors, Founders) at target companies.
Hiring-Manager Prospector	Find people hiring for a role that signals buying intent for the user's product.
Google Maps Leads	Scrape brick-and-mortar businesses from Google Maps — dental clinics, gyms, restaurants, agencies.
Email — First Touch	Write the FIRST cold email — opener, body, single CTA. Seniority-aware (ATL strategic / BTL operational).
Email — Cold Sequence Follow-Ups	COLD sequence — emails 2, 3, and breakup. The prospect never replied to email 1. They don't know you yet.

Invoking this from an agent

Three paths reach this skill. From the chat UI, a user can type the persona slash command followed by a natural request and the discovery step resolves to this skill automatically. From the MCP server, fetch the skill detail with get_skill({id: "specter-lead-research"}) and then invoke it through the agent runtime once the authenticated tier ships. From your own code, hit /docs/skills/specter-lead-research/llm.txt for the token-efficient markdown body and feed it to your model directly.

Note

Every skill page has a canonical permalink and a markdown alternate that LLM crawlers consume via Accept: text/markdown. The full machine-readable catalog lives at /.well-known/agent-skills/index.json.