agentleFS
guerrilla2799guerrilla2799/sdr-copilot/skills/build-list/SKILL.md

build-list

Skill1 starsChanged 4 months agoMITView on GitHub

Build a scored, tiered target-account or contact list for outbound — from a trigger event, a vertical, or a lookalike. Use when the rep says "build me a list", "find companies that...", "who should I target for [play]", or needs accounts/contacts for a new sequence.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. chacosoldier/compabob★ 34same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository14 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Read ${CLAUDE_PLUGIN_ROOT}/references/icp.md, references/messaging.md, and references/guardrails.md if not already in context.

    line 12
  2. Very specific:

    Use Exa category:company searches shaped by the trigger.

    line 16
  3. Distinctive:

    Run 3-5 differently-angled queries so the list isn't one search's bias.

    line 21
  4. Distinctive:

    Check each surviving account against HubSpot:

    line 29
  5. Distinctive:

    If HubSpot unavailable, mark the whole list "⚠️ NOT yet deduped against CRM — do this before importing to Outreach"

    line 33
  6. Distinctive:

    Email addresses: do NOT guess. Options, in order: (1) existing HubSpot record, (2) Clay enrichment — but ONLY with a credit check first, …

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Build List

Turn a targeting idea into a scored, CRM-safe list ready for Outreach import. Input: a criterion ("companies that just made a relevant new hire", "companies matching our ICP on [platform]", "accounts on the legacy incumbent up for renewal") — or a play number from the messaging reference.

Before you build

Read ${CLAUDE_PLUGIN_ROOT}/references/icp.md, references/messaging.md, and references/guardrails.md if not already in context. Confirm with the rep: how many accounts (default 15, hard cap 25 per run) and which play/hook this list feeds.

Step 1 — Source candidates (Exa)

Use Exa category:company searches shaped by the trigger. Describe the ideal company, not keywords. Examples:

  • Hook #2 (your primary play): "[a company matching your Hook #2 trigger — describe the ideal company, not keywords], 100-2500 employees"
  • Hook #3 (new-hire trigger): search for the relevant recent job postings and "started new role" signals from the ICP reference
  • Hook #1/#5 (displacement): "company hiring for experience with the legacy incumbent or a competing tool" (see messaging.md for approved names)

Run 3-5 differently-angled queries so the list isn't one search's bias. Collect ~2x the target count as raw candidates.

Step 2 — Score and cut

Score each candidate on the 10-point rubric (evidence required — no points for vibes). Cut everything under 5. Sort: 8-10 = Tier A, 5-7 = Tier B (qualify before sequencing).

Step 3 — CRM safety pass (guardrail #1)

Check each surviving account against HubSpot:

  • Existing customer (lifecycle stage / closed-won) → remove, list separately as "excluded — customer"
  • Open deal / active demo → remove, list separately as "excluded — active pipeline"
  • Cold history → keep, note it
  • If HubSpot unavailable, mark the whole list "⚠️ NOT yet deduped against CRM — do this before importing to Outreach"

Step 4 — Find the people

For each Tier A account, one Exa category:people search for the Champion and Practitioner (per the buying committee in the ICP reference; singular form: "[Champion title] at [company]"). Two contacts per account max.

Email addresses: do NOT guess. Options, in order: (1) existing HubSpot record, (2) Clay enrichment — but ONLY with a credit check first, ≤25 rows, and the rep's explicit go-ahead (guardrail #2), (3) leave blank for manual lookup.

Output format

# Target List: [name] · [date] · feeds Hook #[N]

## Tier A — sequence now (X accounts)
| Company | Score | Key evidence | Contact 1 | Contact 2 | CRM |
|---|---|---|---|---|---|

## Tier B — qualify first (X accounts)
[same table]

## Excluded — active pipeline (do not touch)
[company → reason]

Also write the Tier A table as a CSV file (list-[name]-[date].csv) with columns matching an Outreach import: Company, Domain, First Name, Last Name, Title, LinkedIn URL, Email, ICP Score, Trigger Evidence.

End with next steps: "Import the CSV to Outreach, or say draft a sequence for this list to build the touches first."

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.