fullenrich-content-engagers
Skill298 starsChanged 6 months agoMITView on GitHub
Use when the user says "enrich people who engaged with this post", "qualify post engagers with FullEnrich", "scrape and enrich LinkedIn post {URL}", "engagers from this post into a CSV", "enrich this CSV of leads", "FullEnrich content engagers", or any variant indicating they want to convert a list of leads — either LinkedIn post likers/commenters scraped via Unipile, or a bring-your-own CSV — into ICP-qualified, enriched leads via FullEnrich v2 bulk enrichment with webhook callback delivery.
- Reads credentials
In this repository37 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- answer-linkedin-commentsSkill
- build-routineSkill
- campaign-dashboardSkill
- campaign-strategySkill
- claap-weekly-recapSkill
- cross-platform-schedulerSkill
- debuggerSkill
- enrich-with-signalsSkill
- find-lookalikesSkill
- fullenrich-event-attendeesSkill
- fullenrich-network-activationSkill
- fullenrich-plg-reverse-lookupSkill
- icp-importSkill
- import-leadsSkill
- integrate-with-yalcSkill
- launch-linkedin-campaignSkill
- lemlist-campaign-from-icpSkill
- list-adaptersSkill
- lost-deal-revival-agentSkill
- notion-reviewSkill
- personalize-messageSkill
- predictleads-dashboardSkill
- predictleads-lookalikesSkill
- predictleads-signalsSkill
- prospect-discovery-pipelineSkill
- provider-builderSkill
- qualify-leadsSkill
- research-prospectSkill
- run-competitive-intelSkill
- run-doctorSkill
- scrape-post-engagersSkill
- send-cold-emailSkill
- setupSkill
- show-routineSkill
- track-campaignsSkill
- yalc-orientationSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 2 are distinctive, and 4 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.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 27
Does not write outreach copy.
- Distinctive: line 28
Does not push to a CRM.
- Distinctive: line 35
Always shows current balance: before doing anything.
- Very specific: line 42
ALWAYS run with --dry-run first to surface the engager count, ICP-pass count, and estimated cost.
- Very specific: line 44
WAIT for explicit user confirmation before re-running without --dry-run.
- Very specific: line 45
Only pass --yes to the script when the user has approved the spend in this conversation.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
FullEnrich Content Engagers
One command turns a list of leads into a CSV of ICP-qualified prospects with verified work emails and phones. Two input modes:
- URL mode — scrape engagers from a LinkedIn post via Unipile
- CSV mode — bring your own list (any source: Sales Navigator export, PhantomBuster, Evaboot, manual paste, etc.)
Both modes converge on the same ICP filter + FullEnrich enrichment pipeline.
When This Skill Applies
- "enrich people who engaged with this post {URL}"
- "qualify post engagers with FullEnrich"
- "scrape and enrich LinkedIn post {URL}"
- "engagers from {URL} into a CSV"
- "enrich this CSV of leads with FullEnrich"
- "qualify and enrich leads.csv"
What This Skill Does NOT Do
- Does not write outreach copy. Pair with
personalize-messageafter. - Does not push to a CRM.
- Does not spend credits without explicit user approval. See "Credit safety contract" below.
Credit safety contract (MANDATORY)
This skill spends FullEnrich credits, which cost real money. Safeguards:
- Always shows current balance before doing anything.
- Always shows estimated cost of the run.
--max-credits Nceiling (default 500) — auto-trims the contact list to fit.- Hard-approval prompt — blocks on stdin until the user types
yes. If stdin is not a TTY, the script aborts unless--yesis passed. --dry-runmode — scrapes engagers + applies ICP without spending a credit.
When Claude invokes this skill on a user's behalf:
- ALWAYS run with
--dry-runfirst to surface the engager count, ICP-pass count, and estimated cost. - Quote the EXACT estimated credit cost back to the user.
- WAIT for explicit user confirmation before re-running without
--dry-run. - Only pass
--yesto the script when the user has approved the spend in this conversation. - Exception: respect locally modified scripts — the user took ownership.
Prerequisites
URL mode requires all four:
FULLENRICH_API_KEY= # https://app.fullenrich.com/app/api
UNIPILE_API_KEY= # https://dashboard.unipile.com
UNIPILE_DSN= # e.g. https://api18.unipile.com:14891
UNIPILE_ACCOUNT_ID= # the LinkedIn account ID under UnipileCSV mode requires only:
FULLENRICH_API_KEY=Optional (both modes):
FULLENRICH_WEBHOOK_URL= # public URL for FullEnrich callbacks; otherwise webhook.site fallbackWorkflow
- Resolve input source
- URL mode: resolve
social_idvia Unipileget-post, thenlist-post-comments+list-post-reactions. - CSV mode: parse
--csvfile, map columns (case-insensitive header aliases forfirst_name,last_name,linkedin_url,title,company, etc.).
- URL mode: resolve
- Dedupe — keyed on
linkedin_urlwhen present, otherwisefirst_name|last_name|company. Rows missing first_name AND (linkedin_url OR company) are dropped. - Apply ICP filter — load
config/icp.json(job-title regex, seniority allow-list, geo, company-size), score each contact 0–100, drop everything below the threshold. - Estimate cost + confirm — show the cost preview, block on stdin for
yes. - Enrich — chunk into ≤100 contacts per FullEnrich bulk request with
enrich_fields: ["contact.work_emails", "contact.phones"]. - Receive callbacks — webhook payloads land within ~30s per batch.
- Write outputs —
qualified-engagers.csv(passed ICP + enriched) andqualified-engagers-disqualified.csv(failed ICP, kept for inspection).
CLI Reference
# URL mode
node scripts/run.mjs <linkedin-post-url-or-post-id> [flags]
# CSV mode
node scripts/run.mjs --csv path/to/leads.csv [flags]
Flags (shared):
[--out path.csv] # default qualified-engagers.csv
[--icp config/icp.json] # ICP rules file
[--threshold 50] # ICP minimum score (0-100)
[--max <N>] # URL mode: page cap. CSV mode: hard row cap. (default 500)
[--max-credits <N>] # hard credit ceiling (default 500)
[--dry-run] # filter + cost preview, no spending
[--yes | -y] # skip the interactive approval promptCSV column conventions
The parser accepts the most common header naming conventions case-insensitively. For each contact field, the first matching header wins:
| Internal field | Accepted CSV headers |
first_name | first_name, firstname, first name, given_name (or split from name / full_name) |
last_name | last_name, lastname, last name, surname, family_name (or split from name / full_name) |
linkedin_url | linkedin_url, linkedin, profile_url, linkedin profile, linkedin_profile_url |
title | title, job_title, headline, position, current_position |
company_name | company, company_name, current_company, organization, employer |
domain | domain, company_domain, website |
See examples/sample-leads.csv for a minimal working CSV.
Reference
- Shared API client:
./scripts/lib/fullenrich-client.mjs - Shared webhook receiver:
./scripts/lib/fullenrich-webhook.mjs - Shared CSV writer:
./scripts/lib/csv.mjs - ICP config:
config/icp.json(editable per use case) - FullEnrich v2 docs:
https://docs.fullenrich.com/llms.txt
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.

