agentleFS
Sign inStart free
CodeAlive-AICodeAlive-AI/ceo-ai-os/skills/sales-prospecting/SKILL.md

sales-prospecting

Skill9 starsChanged 6 months agoMITView on GitHub

Build targeted prospect lists with verified contacts matching your ICP. Use when asked to find leads, build a prospect list, or identify target accounts. For signal-based prospect discovery, see signal-scanner. For enriching a single known lead, see lead-enrichment. For writing outreach, see cold-email.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before helping, check MEMORY.md for: current ICP definition, target segments, existing pipeline.

    line 9
  2. Distinctive:

    Always verify emails before outreach

    line 82
  3. Distinctive:

    Start with 10-20 prospects, refine ICP, then scale

    line 84

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

[YOUR_PRODUCT] Context

Before helping, check MEMORY.md for: current ICP definition, target segments, existing pipeline. Output in Russian (company names and titles in original). For chat platforms: numbered list of prospects with key info.

Sales Prospecting

Build targeted prospect lists with verified contact information.

Workflow

Step 1: Find Target Companies (Fiber NL Search)

orth run fiber /v1/natural-language-search/companies -d '{"query": "DESCRIBE YOUR ICP IN NATURAL LANGUAGE"}'

Examples:

  • "B2B SaaS companies with 100-500 engineers using microservices architecture"
  • "Series A startups in developer tools space San Francisco"
  • "Enterprise companies with large Python codebases"

Step 2: Find Decision Makers (Fiber People Search)

orth run fiber /v1/people-search -d '{"searchParams": {"job_titles": ["VP Engineering", "Head of Engineering", "CTO"], "company_names": ["Company1", "Company2", "Company3"]}}'

Step 3: Get Emails for a Domain (Hunter)

orth run hunter /v2/domain-search -q domain=target-company.com

Returns all known emails at that domain with roles and confidence.

Step 4: Find Specific Email (Hunter)

orth run hunter /v2/email-finder -q domain=target.com -q first_name=FIRST -q last_name=LAST

Step 5: Verify Email (Fiber)

orth run fiber /v1/validate-email/single -d '{"email": "lead@company.com"}'

Step 6: Company Context for Personalization (Brand.dev)

orth run brand-dev /v1/brand/retrieve -q domain=target.com

Output Format

For each prospect:

1. **[Name]** — [Title] @ [Company] ([size] employees)
   Email: [email] ([verified/unverified])
   LinkedIn: [url]
   Why target: [brief reason based on ICP match]

End with summary:

Total: [N] prospects at [M] companies
Next step: review list, then use cold-email skill for outreach

Tips

  • Fiber NL search is powerful — describe ICP in plain English
  • Always verify emails before outreach
  • Get company context (Step 6) for personalized cold emails
  • Start with 10-20 prospects, refine ICP, then scale

Related Skills

  • pipeline-manager — add found prospects to pipeline with scoring
  • signal-scanner — automated prospect discovery via buying signals
  • lead-enrichment — deep enrichment of a single lead
  • find-email-by-name — quick email lookup
  • cold-email — write outreach emails for prospects
  • outreach-sender — send and track outreach
  • founder-sales — full sales strategy and workflow
  • sales-qualification — qualify prospects before outreach

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free