build-list
Skill34 starsChanged 23 days agoMITView on GitHub
Build a ranked, CRM-deduped outbound prospect list from an ICP description. Use for "/build-list", "find me leads matching X", "build a prospect list for Y", or when the user wants a scored outbound list. Orchestrates discovery + the lead-pipeline module + enrichment.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- guerrilla2799/sdr-copilottheir own version, first seen Oct 20, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- guerrilla2799/sdr-copilot★ 1same 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 repository21 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- add-agentSkill
- chart-tufteSkill
- councilSkill
- design-precheckSkill
- document-exportSkill
- handoverSkill
- index-memorySkill
- log-decisionSkill
- mcp-debugSkill
- meeting-prepSkill
- memory-debtSkill
- merge-contactsSkill
- morning-briefSkill
- post-callSkill
- reflectSkill
- setupSkill
- system-auditSkill
- tasksSkill
- visual-explainerSkill
- weekly-reviewSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 0 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 29
Discover candidates → raw CSV: Use the web-search MCP (e.g.
- Very specific: line 60
Never enrich skip rows. Write the enriched result back to reports/lead-pipeline/02-deduped.csv (or a 02b-enriched.csv).
- Very specific: line 77
Do not send anything. This builds a list.
- Very specific: line 81
If a stage's numbers look wrong (e.g.
≈ “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.
Files
Build List
Turn an ICP description into a ranked, deduped, CRM-aware outbound list using the
lead-pipeline module. You run the judgement/IO steps (discover, enrich); the
script runs the deterministic steps (clean, dedup, score). The cardinal rule:
Dedup against the CRM before enriching. Never spend enrichment effort or credits on accounts the user already knows. Known accounts become warm intros.
Preconditions
- A CRM to dedup against:
data/crm-merge/contacts.json. If it is missing, tell the user to run/merge-contactsfirst (dedup is the whole point); offer to proceed without it only if they insist, noting every lead will beproceed. - An ICP rubric at
modules/lead-pipeline/icp.json. If onlyicp.example.jsonexists, copy it and adjust it to the user's request before scoring.
Steps
- Read the ICP from the request. Pull out: industry/segment, geography, company-size band, and target buyer titles. Confirm anything ambiguous in one short question rather than guessing.
- Discover candidates → raw CSV. Use the web-search MCP (e.g. exa
web_search_exa/linkedin_search_exa) to find matching accounts. Write a CSV toreports/lead-pipeline/00-raw.csvwith whatever you found across these columns:company, domain, contact_name, contact_email, title, country(partial rows are fine; later stages fill gaps). If no search MCP is available, ask the user for a raw CSV and skip to step 3. - Clean (script):
python3 modules/lead-pipeline/pipeline.py clean \ --in reports/lead-pipeline/00-raw.csv \ --out reports/lead-pipeline/01-cleaned.csv --country <codes> - Dedup against the CRM (script):
Report the split: how manypython3 modules/lead-pipeline/pipeline.py dedup \ --in reports/lead-pipeline/01-cleaned.csv \ --crm data/crm-merge/contacts.json \ --out reports/lead-pipeline/02-deduped.csvproceed(cold),warm(known account, route viacrm_known_contact),skip(already known, drop from outbound). - Enrich the survivors only. For rows tagged
proceedorwarmthat lack a domain / email / decision-maker, enrich with whatever you have, in this order:- web search MCP for the company domain + LinkedIn (high hit-rate, cheap),
- an enrichment provider MCP (e.g. Clay) for verified emails, check remaining credits first, and only for rows still missing an email,
- public business registries for named decision-makers at small firms when
enrichment misses.
Never enrich
skiprows. Write the enriched result back toreports/lead-pipeline/02-deduped.csv(or a02b-enriched.csv).
- Score (script):
python3 modules/lead-pipeline/pipeline.py score \ --in reports/lead-pipeline/02-deduped.csv \ --icp modules/lead-pipeline/icp.json \ --out reports/lead-pipeline/03-scored.csv --top 50 - Hand back the ranked top-N (path
reports/lead-pipeline/04-top-*.csv), the disposition split, and the tier distribution. Call out thewarmaccounts explicitly: those are the highest-value, lowest-risk plays.
Guardrails
- Do not send anything. This builds a list; outreach is a separate, reviewed step
(see the
linkedin-outreachmodule). - Respect data-protection law and platform terms. Flag if the user's target list looks like scraped personal data being repurposed for cold mail.
- If a stage's numbers look wrong (e.g. zero
skip/warmwith a populated CRM), inspect the stage CSV before continuing. That is why each stage is a file. - Be honest about enrichment misses; report the hit-rate rather than fabricating emails.
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
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.

