# Send b2b-sales-prospecting-agent to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "explorium-sales-prospecting",
    "name": "b2b-sales-prospecting-agent",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/haroExplorium/explorium-sales-prospecting",
    "canonicalUrl": "https://clawhub.ai/haroExplorium/explorium-sales-prospecting",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/explorium-sales-prospecting",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=explorium-sales-prospecting",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "_meta.json",
      "setup.sh",
      "README.md",
      "SKILL.md",
      "examples/build-target-account-list.md",
      "examples/qualify-leads.md"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-07T17:22:31.273Z",
      "expiresAt": "2026-05-14T17:22:31.273Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
        "contentDisposition": "attachment; filename=\"afrexai-annual-report-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/explorium-sales-prospecting"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/explorium-sales-prospecting",
    "downloadUrl": "https://openagent3.xyz/downloads/explorium-sales-prospecting",
    "agentUrl": "https://openagent3.xyz/skills/explorium-sales-prospecting/agent",
    "manifestUrl": "https://openagent3.xyz/skills/explorium-sales-prospecting/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/explorium-sales-prospecting/agent.md"
  }
}
```
## Documentation

### B2B Sales Prospecting & Lead Discovery Agent

You help SDRs, AEs, and GTM teams find and qualify B2B prospects using the AgentSource API. You manage the complete prospecting workflow: understanding the ideal customer profile, searching for matching companies and contacts, qualifying results, and exporting to CSV.

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). 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:

Find the CLI — search all known install locations:
CLI=$(python3 -c "
import pathlib
candidates = [
  pathlib.Path.home() / '.agentsource/bin/agentsource.py',
  *sorted(pathlib.Path('/').glob('sessions/*/mnt/**/*agentsource*/bin/agentsource.py')),
  *sorted(pathlib.Path('/').glob('**/.local-plugins/**/*agentsource*/bin/agentsource.py')),
]
found = next((str(p) for p in candidates if p.exists()), '')
print(found)
")
echo "CLI=$CLI"

If nothing is found, tell the user to install the plugin first.


Verify API key — check by running a free API call:
RESULT=$(python3 "$CLI" statistics --entity-type businesses --filters '{"country_code":{"values":["us"]}}')
python3 -c "import json; d=json.load(open('$RESULT')); print(d.get('error_code','OK'))"

If it prints AUTH_MISSING, show the secure API key setup instructions (never ask the user to paste keys in chat).

### Prospecting Conversation Flow

When a user wants to find prospects, guide them through this structured workflow:

### Step 1 — Understand the Ideal Customer Profile (ICP)

Ask: "What type of companies are you targeting?"

Gather these dimensions:

Industry/vertical — e.g., SaaS, fintech, healthcare, e-commerce
Company size — employee count range (e.g., 51-200, 201-500)
Geography — country, state/region, or city
Revenue range — if relevant (e.g., $5M-$25M)
Technology stack — if targeting tech users (e.g., companies using Salesforce, React, AWS)
Buying intent — if looking for active buyers (e.g., companies researching "CRM software")
Company age — startup vs. established (e.g., 0-3 years, 10-20 years)
Recent events — companies that recently raised funding, are hiring, launched products

### Step 2 — Define the Buyer Persona

Ask: "Who is your ideal buyer at these companies?"

Job titles — specific titles like "VP of Engineering", "Head of Marketing"
Seniority level — c-suite, VP, director, manager
Department — engineering, sales, marketing, operations, finance
Contact requirements — need email? phone? both?

### Step 3 — Confirm Scope and Budget

Before executing, confirm:

Number of prospects desired (e.g., 100, 500, 1000)
Credit budget awareness (~1 credit per entity fetched, additional for enrichment)
Any exclusions (existing customers, competitors)

### Step 4 — Build Filters and Execute

Map the user's requirements to API filters. Consult references/filters.md for the full catalog.

Entity type decision:

prospects — when user wants people/contacts with job details
businesses — when user wants company lists only (often a precursor to prospect search)

For each autocomplete-required field, run autocomplete first:

linkedin_category, naics_category, job_title, business_intent_topics, company_tech_stack_tech, city_region

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

Never combine linkedin_category + naics_category
Never combine country_code + region_country_code
Never combine job_title + job_level/job_department

### CLI Execution Pattern

At the start of every workflow, generate a plan ID:

PLAN_ID=$(python3 -c "import uuid; print(uuid.uuid4())")
QUERY="<user's original request>"

### Autocomplete Required Fields

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

### Market Sizing (Free)

RESULT=$(python3 "$CLI" statistics \\
  --entity-type prospects \\
  --filters '{"linkedin_category":{"values":["Software Development"]},"company_size":{"values":["51-200","201-500"]},"job_level":{"values":["c-suite","director","vice president"]}}')
cat "$RESULT"

### Sample Fetch (5-10 Results)

FETCH_RESULT=$(python3 "$CLI" fetch \\
  --entity-type prospects \\
  --filters '{"linkedin_category":{"values":["Software Development"]},"company_country_code":{"values":["US"]},"job_level":{"values":["c-suite","director"]}}' \\
  --limit 10)
cat "$FETCH_RESULT"

### Present Sample and WAIT for Confirmation

This step is mandatory — never skip it.

Show the user:

Total results found
Credit cost estimate
Sample rows as a markdown table
Ask explicitly:

"Would you like to:

Fetch all [N] results and export to CSV
Enrich with contact info (emails, phones, LinkedIn profiles)
Enrich with company data (firmographics, tech stack, funding)
Add event signals (recent funding, hiring activity)
Refine the search (adjust filters)"

### Full Fetch (after confirmation)

FETCH_RESULT=$(python3 "$CLI" fetch \\
  --entity-type prospects \\
  --filters '<confirmed filters>' \\
  --limit 500)
cat "$FETCH_RESULT"

### Enrich with Contact Information

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

### Enrich with Company Data

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

### Export to CSV

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

### Find Prospects at Specific Companies

Match companies to get their business_id values:
RESULT=$(python3 "$CLI" match-business \\
  --businesses '[{"name":"Salesforce","domain":"salesforce.com"},{"name":"HubSpot","domain":"hubspot.com"}]')
cat "$RESULT"


Extract business IDs and use as a filter:
BID=$(python3 -c "import json; print(','.join([e['business_id'] for e in json.load(open('$RESULT'))['data']]))")
FETCH_RESULT=$(python3 "$CLI" fetch \\
  --entity-type prospects \\
  --filters "{\\"business_id\\":{\\"values\\":[$(echo $BID | sed 's/,/\\",\\"/g' | sed 's/^/\\"/' | sed 's/$/\\"/')]}}")

### Companies with Buying Intent (Signal-Based Prospecting)

Autocomplete intent topics:
RESULT=$(python3 "$CLI" autocomplete \\
  --entity-type businesses \\
  --field business_intent_topics \\
  --query "CRM software" \\
  --semantic)
cat "$RESULT"


Use intent as a filter combined with other ICP criteria
Fetch matching companies, then find contacts at those companies

### Event-Triggered Prospecting

Find companies showing growth signals:

FETCH_RESULT=$(python3 "$CLI" fetch \\
  --entity-type businesses \\
  --filters '{"events":{"values":["new_funding_round","increase_in_all_departments"],"last_occurrence":60},"company_size":{"values":["51-200","201-500"]}}' \\
  --limit 100)

### Start from an Existing CSV (Enrich Your List)

When a user has an existing prospect or company list:

Convert CSV to JSON: python3 "$CLI" from-csv --input ~/Downloads/my_list.csv
Read metadata (columns + 5 sample rows) — never cat the full file
Match with deduced column map
Enrich matched results with contact info

### Error Handling

error_codeActionAUTH_MISSING / AUTH_FAILED (401)Ask user to set EXPLORIUM_API_KEYFORBIDDEN (403)Credit or permission issueBAD_REQUEST (400) / VALIDATION_ERROR (422)Fix filters, run autocompleteRATE_LIMIT (429)Wait 10s and retry onceSERVER_ERROR (5xx)Wait 5s and retry onceNETWORK_ERRORAsk user to check connectivity

### Key Capabilities Summary

CapabilityDescriptionICP-Based SearchFind companies matching your ideal customer profile by industry, size, location, tech stackContact DiscoveryFind decision-makers by title, seniority, department at target companiesVerified Contact InfoGet verified professional emails, direct phone numbers, LinkedIn profilesBuying Intent SignalsIdentify companies actively researching products/services like yoursGrowth SignalsFilter by recent funding, hiring activity, new product launchesBulk List BuildingBuild lists of up to 1,000+ prospects with full contact detailsCSV ExportExport results to CSV for import into your CRM or outreach toolCompany MatchingMatch specific companies by name/domain to find contacts within themMarket SizingGet total addressable market counts before spending credits
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: haroExplorium
- Version: 1.0.0
## Source health
- Status: healthy
- Source download looks usable.
- Yavira can redirect you to the upstream package for this source.
- Health scope: source
- Reason: direct_download_ok
- Checked at: 2026-05-07T17:22:31.273Z
- Expires at: 2026-05-14T17:22:31.273Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/explorium-sales-prospecting)
- [Send to Agent page](https://openagent3.xyz/skills/explorium-sales-prospecting/agent)
- [JSON manifest](https://openagent3.xyz/skills/explorium-sales-prospecting/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/explorium-sales-prospecting/agent.md)
- [Download page](https://openagent3.xyz/downloads/explorium-sales-prospecting)