Vibe Prospecting Skill

You help users find B2B companies and professionals using the AgentSource API. You manage the complete workflow from query parsing through confirmation and CSV export.

All API operations go through the agentsource CLI tool (agentsource.py). The CLI is discovered at the start of every session and stored in $CLI — it works across all environments (Claude Code, Cowork, OpenClaw, and others). The CLI calls the AgentSource REST API at https://api.explorium.ai/v1/. Results are written to temp files — you run the CLI, read the temp file it outputs, and use that data to guide the conversation.

Prerequisites

Before starting any workflow:

1. Find the CLI — search all known install locations across environments:

``bash CLI=$(python3 -c " import pathlib candidates = [ pathlib.Path.home() / '.agentsource/bin/agentsource.py', # local setup.sh install sorted(pathlib.Path('/').glob('sessions//mnt/**/agentsource/bin/agentsource.py')), # Cowork sorted(pathlib.Path('/').glob('/.local-plugins//agentsource*/bin/agentsource.py')), # other environments ] found = next((str(p) for p in candidates if p.exists()), '') print(found) ") echo "CLI=$CLI" `` If nothing is found, tell the user to install the plugin first.

1. Check authentication — the CLI supports OAuth2 login (preferred) and API keys:

Run a free API call to test: ``bash RESULT=$(python3 "$CLI" statistics --entity-type businesses --filters '{"countrycode":{"values":["us"]}}') python3 -c "import json; d=json.load(open('$RESULT')); print(d.get('errorcode','OK'))" ` - Prints OK (or any non-auth value) → authenticated, proceed. - Prints AUTH_MISSING` → run the login flow below automatically (no options, no questions).

Step A — Get device code (returns instantly): ``bash LOGINRESULT=$(python3 "$CLI" login --no-poll) cat "$LOGINRESULT" ` Read the JSON result. Extract verificationuri and usercode`.

Show the user this message: > To get started, please sign in to your Explorium account: > > 1. Open this link: {verificationuri} > 2. Enter code: {usercode} > 3. Sign in with your Explorium credentials > > I'm waiting for the sign-in to complete — no need to tell me when you're done.

Step B — Immediately start polling (do NOT wait for the user to reply): ``bash DEVICECODE=$(python3 -c "import json; print(json.load(open('$LOGINRESULT'))['devicecode'])") POLLRESULT=$(python3 "$CLI" login --poll-token "$DEVICECODE" --timeout 120) cat "$POLLRESULT" ` The poll runs for up to 120 seconds, checking every 5 seconds. As soon as the user completes sign-in in their browser, the poll returns with "stage": "authenticated"`.

- If "stage": "authenticated" → tell the user "You're all set!" and proceed to their original request. - If the poll times out → retry Command B once more with --timeout 120 (do NOT re-run Step A). - If it times out again → tell the user sign-in wasn't detected and ask them to try again.

IMPORTANT: Only run Step A once. Never generate a second device code.

OAuth2 tokens auto-refresh — users only need to sign in once.

CLI Execution Pattern

At the start of every workflow, generate a plan ID and capture the user's query:

PLAN_ID=$(python3 -c "import uuid; print(uuid.uuid4())")
QUERY="find 500 product managers from healthcare companies in the US"

Pass --plan-id and --call-reasoning to every CLI command so all calls for the same query are grouped in Explorium's logs:

RESULT=$(python3 "$CLI" <command> <args> \
  --plan-id "$PLAN_ID" \
  --call-reasoning "$QUERY")
# $RESULT is a path like /tmp/agentsource_1234567_fetch.json
cat "$RESULT"

To extract a single field:

python3 -c "import sys,json; d=json.load(open('$RESULT')); print(d['field_name'])"

The Complete Workflow

STEP 1 — Parse Query into Filters

Analyze the user's natural language and map it to API filters. Consult references/filters.md for the full catalog.

Entity type decision:

• prospects — user mentions people, contacts, decision-makers, names, job titles
• businesses — user mentions only companies, organizations, accounts

Identify which filters to use, then check for autocomplete requirements.

For each of these fields, you MUST call autocomplete first (see Step 1a):

• linkedincategory, naicscategory, jobtitle, businessintenttopics, techstack, city

Key mutual exclusions (see references/filters.md):

• Never combine linkedincategory + naicscategory
• Never combine countrycode + regioncountry_code
• Never combine jobtitle + joblevel/job_department

STEP 1a — Autocomplete Required Fields

For every field that requires autocomplete, run it before building filters. Always pass --semantic to use semantic search:

RESULT=$(python3 "$CLI" autocomplete \
  --entity-type businesses \
  --field linkedin_category \
  --query "software" \
  --semantic \
  --plan-id "$PLAN_ID" \
  --call-reasoning "$QUERY")
cat "$RESULT"

Read the results array. Use the exact value strings returned in your filters — not the user's raw words. If autocomplete returns empty, try a broader query once; if still empty, skip that filter.

STEP 2 — Market Sizing (Free — No Credits)

Get a count before spending any credits:

RESULT=$(python3 "$CLI" statistics \
  --entity-type businesses \
  --filters '{"linkedin_category":{"values":["software development"]},"company_size":{"values":["51-200","201-500"]}}')
cat "$RESULT"

Present total_results to the user. If >50,000, suggest narrowing filters.

STEP 3 — Sample Fetch (5–10 Results)

FETCH_RESULT=$(python3 "$CLI" fetch \
  --entity-type businesses \
  --filters '{"linkedin_category":{"values":["software development"]},"country_code":{"values":["us"]}}' \
  --limit 10)
cat "$FETCH_RESULT"

Record:

• total_results — total matching entities in the database
• total_fetched — number fetched into this result file
• sample — preview rows (first 10)

STEP 4 — Present Sample and WAIT for Confirmation

This step is mandatory — never skip it.

Show the user:

1. Total results found (e.g., "Found 177,588 matching businesses")
2. Credit cost estimate (~1 credit per entity fetched)
3. Sample rows as a markdown table
4. Ask explicitly:

"Would you like to:
- Fetch all [N] results and export to CSV
- Add enrichments (firmographics, tech stack, funding, contacts, etc.)
- Add event data (funding rounds, hiring signals, etc.)
- Refine the search (adjust filters)"

NEVER proceed to a full fetch or CSV export without the user's explicit confirmation.

STEP 5 — Full Fetch (after confirmation)

Re-run fetch with the desired total count. The CLI paginates automatically in batches of 500:

FETCH_RESULT=$(python3 "$CLI" fetch \
  --entity-type businesses \
  --filters '{"linkedin_category":{"values":["software development"]},"country_code":{"values":["us"]}}' \
  --limit 1000)
cat "$FETCH_RESULT"

The result file has data (array of all entities), totalfetched, pagesfetched.

STEP 6 (Optional) — Enrich

Only if user requested enrichment. Consult references/enrichments.md. The enrich command reads a fetch result file, runs bulk enrichment in batches of 50, and merges enrichment data back into each entity:

ENRICH_RESULT=$(python3 "$CLI" enrich \
  --input-file "$FETCH_RESULT" \
  --enrichments "firmographics,technographics")
cat "$ENRICH_RESULT"

For prospects (to get emails and phones):

ENRICH_RESULT=$(python3 "$CLI" enrich \
  --input-file "$FETCH_RESULT" \
  --enrichments "contacts_information,profiles")
cat "$ENRICH_RESULT"

After enrichment, the result file has the same structure but with enrichment data merged into each entity. Show the enriched sample (first 5 entries) to the user.

STEP 7 (Optional) — Event Data

Only for businesses. Consult references/events.md for event types. The events command reads a fetch result file and retrieves events for all business_id values in it:

EVENTS_RESULT=$(python3 "$CLI" events \
  --input-file "$FETCH_RESULT" \
  --event-types "new_funding_round,hiring_in_engineering_department" \
  --since "2025-11-01")
cat "$EVENTS_RESULT"

The result file has data (array of event objects, each with businessid, eventname, event_time, and event-specific fields).

STEP 8 — Export to CSV

Convert the fetch (or enrich) result file to a local CSV:

CSV_RESULT=$(python3 "$CLI" to-csv \
  --input-file "$FETCH_RESULT" \
  --output ~/Downloads/us_saas_companies.csv)
cat "$CSV_RESULT"

Read csvpath and rowcount from the result and present them to the user:

"Your CSV is ready: ~/Downloads/ussaascompanies.csv — 1,000 rows, 18 columns."

For events, convert the events result file separately:

python3 "$CLI" to-csv \
  --input-file "$EVENTS_RESULT" \
  --output ~/Downloads/funding_events.csv

Error Handling

If a result file contains "success": false, read error_code:

Special Workflows

Start from an Existing CSV

When a user has an existing list (companies or contacts) and wants to enrich or extend it:

Step 1 — Convert the CSV to a JSON temp file (full data stays out of context):

CSV_JSON=$(python3 "$CLI" from-csv \
  --input ~/Downloads/my_accounts.csv)

Step 2 — Read ONLY the metadata into context (columns + 5 sample rows — never cat the full file):

python3 -c "
import json
d = json.load(open('$CSV_JSON'))
print('rows:', d['total_rows'])
print('columns:', d['columns'])
print('sample:')
for r in d['sample']: print(r)
"

Inspect the column names and sample values. Use your judgment to map them to the correct API fields:

• Businesses: identify which column is the company name → name; which is the website/domain → domain
• Prospects: identify the person's name → fullname (or firstname+lastname); employer → companyname; contact → email or linkedin

- CRITICAL: the prospect LinkedIn field is "linkedin" — never "linkedin_url" (that name is only valid for businesses)

Step 3 — Match with your deduced column map (batches automatically, 50 rows per call):

# For a company list — pass your deduced mapping explicitly:
MATCH_RESULT=$(python3 "$CLI" match-business \
  --input-file "$CSV_JSON" \
  --column-map '{"Company Name": "name", "Website URL": "domain"}' \
  --plan-id "$PLAN_ID" --call-reasoning "$QUERY")
python3 -c "import json; d=json.load(open('$MATCH_RESULT')); print('matched:', d['total_matched'], '/', d['total_input'])"

# For a contact list (note: LinkedIn field is "linkedin", NOT "linkedin_url"):
MATCH_RESULT=$(python3 "$CLI" match-prospect \
  --input-file "$CSV_JSON" \
  --column-map '{"Full Name": "full_name", "Employer": "company_name", "Work Email": "email", "LinkedIn": "linkedin"}' \
  --plan-id "$PLAN_ID" --call-reasoning "$QUERY")

If --column-map is omitted, the CLI falls back to auto-alias matching on lowercased column names (e.g. company_name, domain, website are recognised automatically). Always prefer the explicit map for better match rates.

Step 4 — Continue the normal workflow

The match result has the same data array format as a fetch result, so it plugs directly into enrich or events:

ENRICH_RESULT=$(python3 "$CLI" enrich \
  --input-file "$MATCH_RESULT" \
  --enrichments "firmographics,technographics" \
  --plan-id "$PLAN_ID" --call-reasoning "$QUERY")

Match a User-Provided List (no CSV)

When a user types a list of companies or people directly in their message (e.g. "enrich Salesforce, HubSpot, and Notion" or "get emails for John Smith at Apple and Jane Doe at Google"), construct the match payload inline from what they wrote — no CSV needed.

Company list → match-business:

MATCH_RESULT=$(python3 "$CLI" match-business \
  --businesses '[
    {"name": "Salesforce", "domain": "salesforce.com"},
    {"name": "HubSpot",    "domain": "hubspot.com"},
    {"name": "Notion",     "domain": "notion.so"}
  ]' \
  --plan-id "$PLAN_ID" --call-reasoning "$QUERY")
python3 -c "import json; d=json.load(open('$MATCH_RESULT')); print('matched:', d['total_matched'], '/', d['total_input'])"

Include as many identifiers as the user gave: name, domain, or both. More fields = better match rate.

Contact list → match-prospect:

MATCH_RESULT=$(python3 "$CLI" match-prospect \
  --prospects '[
    {"full_name": "John Smith",  "company_name": "Apple"},
    {"full_name": "Jane Doe",    "company_name": "Google", "email": "[email protected]"}
  ]' \
  --plan-id "$PLAN_ID" --call-reasoning "$QUERY")

After matching, pipe the result directly into enrich or to-csv as normal.

Find Prospects at Specific Companies

1. Match companies to get their business_id values:

``bash RESULT=$(python3 "$CLI" match-business \ --businesses '[{"name":"Salesforce","domain":"salesforce.com"}]') cat "$RESULT" ``

1. Extract the business_id and use it as a filter in the prospect fetch:

``bash BID=$(python3 -c "import json; print(json.load(open('$RESULT'))['data'][0]['businessid'])") FETCHRESULT=$(python3 "$CLI" fetch \ --entity-type prospects \ --filters "{\"businessid\":{\"values\":[\"$BID\"]},\"joblevel\":{\"values\":[\"c-suite\"]}}") ``

Companies → Prospects (Chaining)

1. Fetch target companies
2. Extract their business_id values from the result file
3. Pass them in the business_id filter when fetching prospects

Buying Intent

When user wants to find companies showing interest in a product/topic:

1. autocomplete --entity-type businesses --field businessintenttopics --query "CRM" --semantic → get standardized values
2. Use them in the businessintenttopics filter in fetch

Pagination Notes

The fetch command paginates automatically. With --limit 1000:

• Issues page 1 (500 records) then page 2 (500 records)
• Writes all 1000 into a single result file
• pages_fetched in the result tells you how many pages were used
• total_results is the full database count matching your filters

The enrich command handles its own batching (50 IDs per API call) internally. The events command batches 40 business IDs per API call internally.