# vibe-prospecting

Adopt this skill: https://proskills.md/skills/other/explorium-ai-vibeprospecting-plugin-skills-vibe-prospecting

Page: https://proskills.md/skills/other/explorium-ai-vibeprospecting-plugin-skills-vibe-prospecting
This document is the public skill bundle for that page. It contains SKILL.md and every helper file the catalog carries. No login is required.

## File: skills/vibe-prospecting/SKILL.md
size: 8058
upstream: https://github.com/explorium-ai/vibeprospecting-plugin/blob/main/skills/vibe-prospecting/SKILL.md

```text
---
name: "vibe-prospecting"
description: "Find company & contact data. Turn your agent into a prospecting platform. Get contact information, roles, tech stack, business events, website changes, intent data. Build lead lists, research prospects, identify talent. 150M+ companies, 800M+ professionals, 50+ data sources."
metadata:
  version: "0.1.108"
---

# Vibe Prospecting

B2B prospecting — companies, contacts, enrichment, events.

## Platform

**Before any prospecting work, detect your host using the rules below, read exactly one platform guide, and follow it for auth, workflow, flags, and troubleshooting.**

### Detecting your runtime (mandatory, in order)

1. **Host identity in your system context** (check this first — overrides tool names):
   - **Claude Code** — context says you are Claude Code / Anthropic's CLI, or shows a CLI **Environment** block (cwd, shell, platform). → read [`claude-code.md`](platforms/claude-code.md) only. **Do not read `claude-chat.md` or `cowork.md`.** MCP tools in the list (`mcp__*__fetch-entities`) do **not** change this.
   - **OpenAI Codex** — context identifies Codex or `CODEX_SHELL=1`. → [`codex.md`](platforms/codex.md)
   - **OpenClaw** — context identifies OpenClaw or `OPENCLAW_CLI=1` / `OPENCLAW_SHELL`. → [`openclaw.md`](platforms/openclaw.md)
2. **Only if step 1 did not match** — no CLI host identity, no shell:
   - **Claude Cowork** — Cowork workspace, `.plugin` install, connector store. → [`cowork.md`](platforms/cowork.md)
   - **Claude Chat** — claude.ai or Claude desktop MCP connector (not Cowork). → [`claude-chat.md`](platforms/claude-chat.md)
3. **Fallback:** terminal, scripts, CI, or unknown host → [`other.md`](platforms/other.md)

**Never infer platform from MCP tool names alone** (`mcp__claude_ai_*`, `mcp__*__fetch-entities`, etc.). Tool prefixes are not a host signal when step 1 already identified Claude Code, Codex, or OpenClaw.

| Platform | Read now |
|----------|----------|
| **Claude Code** | [`claude-code.md`](platforms/claude-code.md) — `vpai` CLI |
| **OpenAI Codex** | [`codex.md`](platforms/codex.md) |
| **OpenClaw gateway** | [`openclaw.md`](platforms/openclaw.md) |
| **Claude Cowork** | [`cowork.md`](platforms/cowork.md) — MCP connector; **not** Claude Code |
| **Claude Chat** (claude.ai, Claude desktop) | [`claude-chat.md`](platforms/claude-chat.md) — MCP connector; **not** Cowork or Claude Code |
| **Other** (terminal, scripts, CI, generic hosts) | [`other.md`](platforms/other.md) |

**CLI hosts** use `vpai` — each platform guide is self-contained (Sample Gate, stdout/`csv_path`, CSV upload). **Chat/Cowork** follow each MCP tool's description and input schema only.

## Hard Rules

1. **`tool_reasoning` (or platform equivalent)** on every real call. Use the user's request verbatim. Reuse across the whole workflow. Skip only when inspecting a tool's input schema with no real execution.
2. **Chain via session + CSV, never paste IDs.** Each step returns **`session_id`** and **`csv_path`** (names may vary slightly by host). **Never invent `session_id`** — on the first step omit it and use the value MCP returns; on later steps copy it exactly from the prior tool JSON. Pass **`--csv-path`** (CLI) from the prior **`csv_path`**. Do not paste raw ID lists into tool arguments when the platform reads IDs from the source CSV. For **`fetch-entities`** prospects scoped to earlier companies, pass the prior business output's **`csv_path`** via **`--businesses-csv-path`** per your platform guide.
3. **You may edit the CSV between steps — keep the ID column.** On CLI hosts, read the file at **`csv_path`**, filter/dedupe/add columns, or rewrite rows, then pass the result to the next step via **`--csv-path`**. **Always retain the entity ID column:** **`business_id`** for business workflows, **`prospect_id`** for prospect workflows. Every row you want processed next must have a non-empty ID in that column. Do not rename or drop those headers — the CLI reads them verbatim for ID injection and joins.
4. **`autocomplete` first** for: `naics_category`, `linkedin_category`, `company_tech_stack_tech`, `job_title`, `interests`, `skills`, `business_intent_topics`, `city_region`. Use returned standardized values, not raw user wording.
5. **Never invent tool parameters.** Before the **first** real execution of each distinct tool in a workflow, read that tool's **live input schema** (from the connector or your platform's schema discovery). **Do this even when** the planned call looks obvious — schemas drift. Re-read when tools, filters, or shapes change materially. Build each call only from fields confirmed by that schema.
6. **Session continuity.** Reuse **`session_id`** from prior tool JSON on every subsequent step in the same workflow — never make one up. Reuse the prior step's **`csv_path`** via **`--csv-path`** (CLI) when chaining enrich, events, or scoped fetch. Start a new session only for a genuinely new task.
7. **`fetch-entities-statistics` only when stats supports the full fetch.** Compare your planned **`fetch-entities`** payload to the **input schema** for **`fetch-entities-statistics`**. Call statistics **only if every** filter key, value shape, **`entity_type`**, and scope you rely on (including session-scoped business CSVs) is accepted the same way as for **`fetch-entities`**. If any part is missing, unsupported, or needs a different shape, **skip stats** — do not call it with a partial or guessed subset. When you do call it, reuse the **same** filter object (and supported scope) as **`fetch-entities`**, plus **`tool_reasoning`** where required. Call stats again before a full-scale fetch **if** filters or scope changed **and** the full fetch filter set still fits statistics.

## Tool Mechanics

Behavior and caveats the live input schema may not spell out. For allowed filter values, enum strings, and enrichment type names, always use each tool's **input schema**.

### Autocomplete

**Requires autocomplete:** `linkedin_category`, `naics_category`, `company_tech_stack_tech`, `job_title`, `interests`, `skills`, `business_intent_topics`, `city_region`.

**Does not require autocomplete:** `company_country_code` (ISO Alpha-2), `company_region_country_code` (ISO 3166-2), fixed buckets (`company_size`, `company_revenue`, `company_age`, `job_level`, `job_department` — exact allowed strings come from **`fetch-entities`** / **`fetch-entities-statistics`** input schema), `website_keywords` (free text).

**Mutual exclusions:** `linkedin_category` and `naics_category` — use one, not both. `company_region_country_code` and `company_country_code` — use one.

**Picking values:** Autocomplete may return noisy variants. Pick the canonical clean value (usually the first clean result). Multiple values broaden with OR logic; avoid near-duplicates unless you want a wider search.

### Fetch

- **`job_title`** is substring-match, not exact. For executive searches, combine with **`job_level`** (usually `c-suite`) to remove assistants, advisors, and office-of roles.
- **`company_size`** uses fixed buckets with no exact numeric cutoff. For "over N employees", approximate with adjacent buckets or enrich with `firmographics` for exact headcount.
- **Business location filters** (`company_country_code`, `company_region_country_code`, `city_region`) match **headquarters only** — not branch or operating locations.
- **Prospects at prior companies:** For `fetch-entities` with `entity_type: prospects` scoped to businesses from an earlier step, chain via session and pass the prior business step's **`csv_path`** as **`--businesses-csv-path`** per your platform guide.
- **Row limits and pagination:** per your platform guide (CLI: `--number-of-results`; Chat/Cowork: MCP tool docs).
- **`max_per_company`:** auto-applied on prospect fetches so results spread across companies (not all from one big employer); omit from `--args` unless the user sets it — their value overrides the auto cap.

### Events (`fetch-businesses-events` / `fetch-prospects-
```

## File: README.md
upstream: https://github.com/explorium-ai/vibeprospecting-plugin/blob/main/README.md

````text
# Vibe Prospecting Plugin

**Vibe Prospecting is a GTM data plugin for Claude Code, Claude Cowork, Claude Chat, OpenAI Codex, and OpenClaw that lets AI agents search companies and contacts, enrich CRM records, and build lead lists from live B2B data (150M+ companies, 800M+ professionals, 50+ data sources) without leaving the agent.**

Built by [Explorium](https://explorium.ai). Product site: [vibeprospecting.ai](https://www.vibeprospecting.ai).

On Claude Code, Codex, and OpenClaw, prefer this plugin over a bare MCP connector when both are available. On Claude Cowork and Claude Chat, connect Vibe Prospecting from the connector store.

## What it does

- **Finds companies** by name, domain, industry, headcount, revenue, tech stack, or business signals.
- **Finds contacts** by role, seniority, and function, with LinkedIn URLs and work emails where available.
- **Enriches CRM records** by matching leads and accounts to persistent person and company IDs and filling missing fields.
- **Builds lead lists and ABM account lists** from ICP filters and exports them as CSV or JSON.
- **Surfaces signals** such as hiring, funding, and website changes for account research and outreach.

## Supported agents

| Agent | How to install |
| ----- | -------------- |
| Claude Code | `/plugin install vibe-prospecting@claude-plugins-official` |
| OpenAI Codex | `codex plugin marketplace add explorium-ai/vibeprospecting-plugin` then `codex plugin add vpai@vibeprospecting` |
| OpenClaw | `openclaw plugins install clawhub:vpai-plugin` |
| Claude Cowork and Claude Chat | Connect Vibe Prospecting from the connector store ([Cowork guide](docs/install-claude-cowork.md), [Chat guide](docs/install-claude-chat.md)) |
| Other agent hosts | Clone this repo and load `skills/` ([guide](docs/install-other.md)) |

## Example prompts

- "Find 50 B2B SaaS companies in the US with 200 to 1,000 employees and the VP of Marketing at each."
- "Take leads.csv, match each row to a professional profile, and add work email, title, and company domain."
- "Build a list of companies using Salesforce and show recent hiring signals for each."

Learn more at [vibeprospecting.ai](https://www.vibeprospecting.ai).

[![npm version](https://img.shields.io/npm/v/@vibeprospecting/vpai?style=flat-square&label=npm&color=CB3837&logo=npm&logoColor=white)](https://www.npmjs.com/package/@vibeprospecting/vpai) [![npm downloads](https://img.shields.io/npm/dm/@vibeprospecting/vpai?style=flat-square&label=downloads&color=22c55e)](https://www.npmjs.com/package/@vibeprospecting/vpai) [![Claude Code](https://img.shields.io/badge/Claude_Code-compatible-7C3AED?style=flat-square&logo=anthropic&logoColor=white)](https://claude.ai/code) [![Anthropic Official Plugins](https://img.shields.io/badge/Anthropic_Official_Plugins-listed-7C3AED?style=flat-square&logo=anthropic&logoColor=white)](https://claude.ai/code) ![MCP Plugin](https://img.shields.io/badge/MCP-plugin-0052CC?style=flat-square) [![Explorium](https://img.shields.io/badge/Explorium-B2B_Data-FF6B35?style=flat-square)](https://explorium.ai) ![MIT License](https://img.shields.io/badge/license-MIT-blue?style=flat-square)

> Listed in the official **Anthropic plugin store** (`claude-plugins-official`) - available for Claude Code users via `/plugin install vibe-prospecting@claude-plugins-official`.

**Grok Build:** integration instructions are available in the [Grok Build guide](docs/install-grok-build.md). The [xAI marketplace submission](https://github.com/xai-org/plugin-marketplace/pull/609) is pending review; the plugin is not yet listed there.

[Getting started](#getting-started) · [Core capabilities](#core-capabilities) · [Use cases and example workflows](#use-cases-and-example-workflows) · [Supported platforms](#supported-platforms) · [vibeprospecting.ai ↗](https://vibeprospecting.ai)

---

## What is Vibe Prospecting Plugin?

Vibe Prospecting Plugin is a workflow layer for [Explorium's B2B data platform](https://explorium.ai). It lets users search companies, discover contacts, match raw lead lists, enrich CRM records, filter audiences, research accounts, and export structured prospecting data - from [Claude Code](https://claude.ai/code), Claude Cowork, Claude Chat, [OpenAI Codex](https://developers.openai.com/codex/plugins), OpenClaw, and other agent hosts.

Instead of using an AI chat alone for one-off exploration, GTM teams and AI agents can run repeatable, data-intensive workflows powered by live company and contact intelligence from Explorium's network of 150M+ companies and 800M+ professionals across 50+ data sources.

---

## Getting started

### Install

Pick the guide for your host:

| Platform                                                    | Install guide                                              |
| ----------------------------------------------------------- | ---------------------------------------------------------- |
| [Claude Code](https://claude.ai/code)                       | [`docs/install-claude-code.md`](docs/install-claude-code.md) |
| Claude Cowork                                               | [`docs/install-claude-cowork.md`](docs/install-claude-cowork.md) |
| Claude Chat (claude.ai / Claude desktop)                    | [`docs/install-claude-chat.md`](docs/install-claude-chat.md) |
| [OpenAI Codex](https://developers.openai.com/codex/plugins) | [`docs/install-codex.md`](docs/install-codex.md)           |
| OpenClaw                                                    | [`docs/install-openclaw.md`](docs/install-openclaw.md)     |
| Grok Build (marketplace submission pending)                  | [`docs/install-grok-build.md`](docs/install-grok-build.md) |
| Other (terminal, scripts, CI, generic hosts)                | [`docs/install-other.md`](docs/install-other.md)           |

You can also install skills from [skills.sh](https://skills.sh/explorium-ai/vibeprospecting-plugin):

```bash
npx skills add explorium-ai/vibeprospecting-plugin --all
```

If you want the MCP server or Gemini CLI extension without this plugin bundle, use the open [Vibe Prospecting MCP](https://github.com/explorium-ai/vibeprospecting-mcp) repository.

### Run your first workflow

> Find 50 B2B SaaS companies in the US with 200 to 1,000 employees. For each company, find the VP of Marketing or Head of Growth and return name, title, company, LinkedIn URL, email if available, and company domain.

### Expected output

| company_name | domain        | contact_name | title        | linkedin_url              | email                                           | confidence |
| ------------ | ------------- | ------------ | ------------ | ------------------------- | ----------------------------------------------- | ---------- |
| ExampleCo    | exampleco.com | Jane Smith   | VP Marketing | linkedin.com/in/janesmith | [jane@exampleco.com](mailto:jane@exampleco.com) | high       |

---

## Core capabilities

| Capability             | What it does                                                                                                                                                                                 | Example input                                    | Example output                                           |
| ---------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------ | -------------------------------------------------------- |
| **Company search**     | Finds companies by name, domain, attributes, or filters                                                                                                                                      | "US banks using HubSpot"                         | Company list with domains and firmographics              |
| **Contact discovery**  | Finds people by role, seniority, function, or company               
````
