agentleFS
timscheueraitimscheuerai/gtm-architecture-template/.agents/skills/lead-sourcing/SKILL.md

lead-sourcing

Skill2 starsChanged 2 months agoMITView on GitHub

Translate an ICP into comparable account and contact searches, build a bounded first batch and preserve provider filters and provenance.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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 company/private/ when populated.

    line 8
  2. Distinctive:

    Write a filter ledger before sourcing:

    line 10
  3. Distinctive:

    Use the user's validated search as an anchor.

    line 19
  4. Very specific:

    Start with ten known accounts or a supplied CSV.

    line 21

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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 the first account batch

Read company/private/ when populated; use the ICP and persona only as labeled examples. Follow the runtime contract for OXYGEN discovery.

Write a filter ledger before sourcing:

CriterionBusiness meaningProvider field/operatorVerified semanticsPost-filter
GeographyHQ, operating market or person's locationDiscover current schemaDo not equate theseFlag unknowns
SizeActual employees or provider estimate/bucketDiscover current schemaRecord measurement basisAudit boundaries
BuyerRemit plus title variantsInclude/exclude titlesInclude local-language variantsPersona scoring
ExclusionsCustomers, active deals, competitorsExact identity where possibleSeparate match from substring suspicionHold ambiguity

Use the user's validated search as an anchor. Mirror its meaning across connected providers; unsupported filters become explicit post-filters. Do not assume Apollo, Sales Navigator and Blitz use identical headcounts, taxonomies or title matching.

Start with ten known accounts or a supplied CSV. Preserve source ID, domain, source, signal type, original timestamp and batch ID. Inspect missing keys and parse quoted CSV properly. Reuse normalise_sources; use oxygen-dedupe for identity conflicts.

For provider calls, discover exact schemas/enums, preview the narrow scope and price, then execute only the requested capped probe. Capture pagination cursors and completion status; partial pages are not the whole TAM. Scope people searches to company-qualified accounts.

Return saved filters, batch size, unique accounts, exclusions, unknowns and source coverage. A source match is a candidate; research and independent company/persona gates decide fit.

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.