prospeo-full-export
Skill1 starsChanged 2 months agoMITView on GitHub
Use when exporting an entire Prospeo people search to CSV, including searches over the 25K result limit that need state-by-state splitting. Also use when someone built filters in Prospeo's UI and wants every matching contact out via the API.
- Reads credentials
- Installs packages
We split this skill into the rules it gives an agent
12 rules. About 0 are common, 7 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 18
Before exporting more than 500 contacts, run Prospeo on a 50-contact sample, then invoke /icp-prompt-builder to tune a qualification prompt …
- Distinctive: line 22
Safe skip: only if your Prospeo filter is already extremely tight (e.g., 5 exact titles + 1 industry + narrow headcount) AND you've run the …
- Distinctive: line 57
Security note: Never paste your API key directly into a script file.
- Distinctive: line 91
Create a TypeScript script
- Distinctive: line 92
Run it to paginate through all results
- Very specific: line 110
Run the search once to check total_count
- Distinctive: line 111
If > 20,000, switch to state-by-state mode
- Distinctive: line 140
Before running, Claude will estimate the credit cost:
- Very specific: line 184
Check that your location format is correct (must include #US, #GB, etc.)
- Very specific: line 186
Remove the person_contact_details filter to see all results (not just those with verified emails)
- Very specific: line 199
No other dependencies needed — the script uses only built-in Node.js modules.
- Distinctive: line 209
Or wait: if Prospeo returned <500 contacts for your filter, your ICP may be too narrow.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
Prospeo Full Search Export
Extract your entire Prospeo people search to a CSV file. Build your search in Prospeo's UI, then let Claude pull every single result via the API — even if the search has more than 25,000 results.
Required step: Qualify with /icp-prompt-builder (do not skip)
Before exporting more than 500 contacts, run Prospeo on a 50-contact sample, then invoke /icp-prompt-builder to tune a qualification prompt in 3-5 rounds of 10 (with your approval each round). Apply the tuned prompt to the full export to filter out bad fits.
Why required: email enrichment downstream costs $0.05-$0.15 per person. A 25K export that's 40% wrong-fit wastes $500-$1,500 on email-finding that goes nowhere. The ICP prompt builder takes 10-15 min and saves that cost 40-70% of the time.
Safe skip: only if your Prospeo filter is already extremely tight (e.g., 5 exact titles + 1 industry + narrow headcount) AND you've run the same filter successfully before. Even then, run /icp-prompt-builder on 10 samples as a sanity check — it's nearly free to confirm.
What This Does
- You build a search in Prospeo's web UI (filters for title, location, industry, company size, etc.)
- You tell Claude what filters you used
- Claude translates those filters into Prospeo API calls
- Claude paginates through every page of results and exports to CSV
- For large US searches (25K+), Claude automatically splits by state to get everything
Setup (First Time Only)
Step 1: Create a Prospeo Account
- Go to prospeo.io and sign up
- Choose a plan that includes the Search Person API (most paid plans do)
- Each API request that returns results costs 1 credit and returns 25 contacts
Step 2: Get Your API Key
- Log into Prospeo
- Go to Settings > API (or visit prospeo.io/app/settings/api)
- Copy your API key
Step 3: Set Your API Key
Set it as an environment variable so Claude can use it:
# Add to your shell profile (~/.zshrc or ~/.bashrc)
export PROSPEO_API_KEY="your_api_key_here"Then restart your terminal or run source ~/.zshrc.
Security note: Never paste your API key directly into a script file. Always use environment variables.
How to Use
Step 1: Build Your Search in Prospeo's UI
Go to prospeo.io/app/search and use the filters to build your search. The UI lets you filter by:
- Job title (e.g., "CEO", "VP Sales", "Head of Marketing")
- Location (e.g., "United States", "California", "New York")
- Company industry (e.g., "Information Technology", "Healthcare")
- Company headcount (e.g., 11-500 employees)
- Company technology (e.g., "Salesforce", "HubSpot")
- Revenue range
- Contact details (has verified email, has phone number)
Note the total result count shown in the UI — you'll need this to estimate credits.
Step 2: Tell Claude Your Filters
Just describe what you filtered for. Examples:
"I searched for CEOs and CTOs at companies with 11-500 employees in the US, in the Information Technology industry, with verified emails."
"I'm looking for VP of Sales and Head of Sales at SaaS companies in California with 50-200 employees."
"I need all Marketing Directors in the US at companies using HubSpot, 20-1000 headcount."
Step 3: Claude Runs the Export
Claude will:
- Confirm the filters and estimated credit cost
- Create a TypeScript script
- Run it to paginate through all results
- Export everything to a CSV file in your current directory
Filter Reference
Moved to references/api-reference.md — filter values and request/response details.
API Details
Moved to references/api-reference.md — filter values and request/response details.
The 25K Limit: State-by-State Splitting
Prospeo caps any single search at 25,000 results (1,000 pages x 25 per page). If your US-wide search has more than 25K results, the script automatically splits it into 50 separate state-level searches.
How it works:
- Run the search once to check
total_count - If > 20,000, switch to state-by-state mode
- Replace
"United States #US"with each state (e.g.,"California, United States #US") - Paginate through each state's results
- Deduplicate across states (by LinkedIn URL)
This means you can extract hundreds of thousands of results from a single search definition.
US States (ordered by population for efficiency)
California, Texas, Florida, New York, Illinois, Pennsylvania,
Ohio, Georgia, North Carolina, Michigan, New Jersey, Virginia,
Washington, Arizona, Massachusetts, Tennessee, Indiana, Missouri,
Maryland, Wisconsin, Colorado, Minnesota, South Carolina, Alabama,
Louisiana, Kentucky, Oregon, Oklahoma, Connecticut, Utah, Iowa,
Nevada, Arkansas, Mississippi, Kansas, New Mexico, Nebraska,
Idaho, West Virginia, Hawaii, New Hampshire, Maine, Montana,
Rhode Island, Delaware, South Dakota, North Dakota, Alaska,
Vermont, WyomingScript Template
Moved to references/script-template.md — the complete export script to copy into your project.
Credit Cost Estimation
Before running, Claude will estimate the credit cost:
| Total Results | Pages | Credits | Approximate Cost (varies by plan) |
| 1,000 | 40 | 40 | ~$2 |
| 5,000 | 200 | 200 | ~$10 |
| 25,000 | 1,000 | 1,000 | ~$50 |
| 100,000 (state split) | ~4,000 | ~4,000 | ~$200 |
Claude will always tell you the estimated cost and ask for confirmation before running the full export.
Example Conversations
Simple search:
"Export all CEOs at 11-50 person companies in California in the SaaS industry with verified emails."
Large US-wide search:
"I need every VP of Sales and Head of Sales in the US at companies with 50-500 employees. The Prospeo UI shows 87,000 results."
With exclusions:
"Marketing Directors in the US, exclude staffing and recruiting industries, 20-200 headcount, must have verified email."
With technology filter:
"CTOs at companies using Shopify in the US, any company size."
Troubleshooting
"Set PROSPEO_API_KEY environment variable first"
Your API key isn't set. Run: export PROSPEO_API_KEY="your_key" in your terminal.
"API error: 401"
Your API key is invalid. Check it at prospeo.io/app/settings/api.
"API error: 402"
You're out of credits. Top up your Prospeo account.
"API error: 429"
Rate limited. The script handles this automatically with exponential backoff. If it persists, you're making too many concurrent requests — only run one export at a time.
Results seem low
- Check that your location format is correct (must include
#US,#GB, etc.) - Broaden your title filters — Prospeo does fuzzy matching by default
- Remove the
person_contact_detailsfilter to see all results (not just those with verified emails)
Duplicates across states
The script deduplicates by LinkedIn URL automatically. Some contacts may appear in multiple state searches if they've relocated — the dedup handles this.
Requirements
- Node.js 18+ (for native
fetchsupport) - TypeScript (
npm install -g tsxto run .ts files directly) - A Prospeo account with API credits
No other dependencies needed — the script uses only built-in Node.js modules.
What to do next
Run /icp-prompt-builder on a 50-contact sample (required step above). Apply the tuned prompt to your full export, then /list-quality-scorecard to grade.
Next: /campaign-copywriting → /smartlead-campaign-upload-public.
Or wait: if Prospeo returned <500 contacts for your filter, your ICP may be too narrow. Broaden titles (add synonyms) or industries before scaling.
Related skills
/icp-prompt-builder— required qualification pass before scaling/list-quality-scorecard— grade the filtered list/campaign-copywriting— write the emails/smartlead-campaign-upload-public— launch in DRAFT
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- growthenginenowoslawski/coldoutboundskills★ 75947% same
Wrote their own version · 0
None found.
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 repository58 other files it gives its agents.
- abm-measurementSkill
- abm-retargetingSkill
- abm-target-accountsSkill
- auto-research-publicSkill
- b2b-cold-email-copywritingSkill
- blitz-list-builderSkill
- buying-committee-mapperSkill
- campaign-copywritingSkill
- campaign-strategySkill
- champion-move-detectionSkill
- clay-playbooksSkill
- closed-won-replication-playSkill
- cold-email-kickoffSkill
- cold-email-starter-kitSkill
- cold-email-weekly-rhythmSkill
- competitor-engagersSkill
- deliverability-incident-responseSkill
- deliverability-test-publicSkill
- disco-likeSkill
- email-deliverability-auditSkill
- email-gateway-detectionSkill
- email-waterfallSkill
- experiment-designSkill
- google-maps-list-builderSkill
- icp-onboardingSkill
- icp-prompt-builderSkill
- lead-magnet-brainstormSkill
- list-builderSkill
- list-expanderSkill
- list-quality-scorecardSkill
- personalization-subagent-patternSkill
- playbook-ad-librarySkill
- playbook-ai-specificitySkill
- playbook-case-study-pageSkill
- playbook-company-name-cleaningSkill
- playbook-creative-ideasSkill
- playbook-first-name-cleaningSkill
- playbook-fundraisingSkill
- playbook-google-site-searchSkill
- playbook-hiring-surgeSkill
- playbook-job-posting-languageSkill
- playbook-linkedin-engagementSkill
- playbook-lookalikesSkill
- playbook-name-to-other-prospectsSkill
- playbook-new-in-roleSkill
- playbook-pricing-pageSkill
- playbook-social-link-findingSkill
- playbook-social-postsSkill
- playbook-tech-on-websiteSkill
- playbook-warm-introsSkill
- positive-reply-scoringSkill
- prospeo-search-apiSkill
- smartlead-apiSkill
- smartlead-campaign-upload-publicSkill
- smartlead-inbox-managerSkill
- smartlead-spintaxSkill
- spam-word-checkerSkill
- zapmail-domain-setup-publicSkill
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.

