anysite-lead-generation
Lead generation and prospecting using anysite MCP server for LinkedIn prospect discovery, email finding, company research, and contact enrichment. Extract contacts from websites, find decision-makers at target companies, and build qualified prospect lists for sales, recruiting, and business development. Supports LinkedIn (primary), web scraping for contact extraction, and Instagram business discovery. Use when users need to build prospect lists, find decision-makers, extract contact information, research potential customers, or enrich existing leads with additional data.
What this skill does
# anysite Lead Generation
Professional lead generation and prospecting using the anysite MCP server. Find prospects on LinkedIn, discover verified emails, extract contacts from websites, and build comprehensive lead lists for sales, recruiting, and business development.
## Overview
The anysite Lead Generation skill helps you:
- **Find qualified prospects** on LinkedIn using advanced search filters
- **Enrich profiles** with work history, education, and skills
- **Discover email addresses** through LinkedIn email finding
- **Extract contact information** from company websites
- **Research companies** to identify target accounts
- **Build prospect lists** formatted for CRM import
This skill provides comprehensive lead generation capabilities with the added benefit of zero configuration and immediate execution through anysite MCP.
## Supported Platforms
- **LinkedIn** (Primary): People search, profile enrichment, email discovery, company research, employee listings
- **Web Scraping**: Contact extraction from websites, sitemap parsing, general web data
- **Instagram**: Business account discovery and profile analysis (supplementary)
- **Y Combinator**: Startup company and founder research (supplementary)
## v2 API Overview
All data fetching uses the universal `execute()` tool with four parameters: `source`, `category`, `endpoint`, `params`. Supporting tools:
- **`execute(source, category, endpoint, params)`** - Fetch data. Returns first page of items + `cache_key`.
- **`get_page(cache_key, offset, limit)`** - Load additional pages from a previous execute() result using the returned `cache_key` and `next_offset`.
- **`query_cache(cache_key, conditions, sort_by, aggregate, group_by)`** - Filter, sort, count, or aggregate already-fetched data without a new API call.
- **`export_data(cache_key, format)`** - Export a full dataset as CSV, JSON, or JSONL. Returns a download URL.
- **`discover(source, category)`** - Inspect available endpoints and their accepted params (use when unsure about params).
### Error Handling
v2 responses may include an `llm_hint` field with human-readable guidance when something goes wrong (e.g., invalid params, rate limits). Always check for `llm_hint` in the response and follow its advice before retrying.
## Quick Start
### Step 1: Identify Your Lead Source
Choose the appropriate data source based on your prospecting goal:
| Goal | v2 Call | Use Case |
|------|---------|----------|
| Find prospects by title/company | `execute("linkedin", "search", "search_users", {...})` | B2B prospecting, targeted outreach |
| Enrich existing leads | `execute("linkedin", "user", "get", {"user": ...})` | Add work history, education, skills |
| Find verified emails | `execute("linkedin", "email", "find", {"user": ...})` | Email outreach campaigns |
| Extract website contacts | `execute("webparser", "parse", "parse", {"url": ...})` | Get emails/phones from contact pages |
| Research target companies | `execute("linkedin", "search", "search_companies", {...})` | Account-based marketing (ABM) |
| Find company employees | `execute("linkedin", "search", "search_users", {...})` + company filter | Multi-threading into accounts |
### Step 2: Execute Data Collection
Use anysite MCP v2 tools directly to gather lead data:
**Example: Find Sales VPs in San Francisco**
```
Tool: mcp__anysite__execute
Parameters:
- source: "linkedin"
- category: "search"
- endpoint: "search_users"
- params: {"title": "VP Sales", "location": "San Francisco Bay Area", "count": 25}
```
**Example: Enrich a LinkedIn Profile**
```
Tool: mcp__anysite__execute
Parameters:
- source: "linkedin"
- category: "user"
- endpoint: "get"
- params: {"user": "linkedin.com/in/johndoe", "with_experience": true, "with_education": true, "with_skills": true}
```
**Example: Find Email Address**
```
Tool: mcp__anysite__execute
Parameters:
- source: "linkedin"
- category: "email"
- endpoint: "find"
- params: {"user": "johndoe"}
```
**Example: Extract Contacts from Website**
```
Tool: mcp__anysite__execute
Parameters:
- source: "webparser"
- category: "parse"
- endpoint: "parse"
- params: {"url": "https://company.com/contact", "extract_contacts": true, "strip_all_tags": true}
```
### Step 3: Process and Analyze Results
After execute() returns data with a `cache_key`, use v2 post-processing:
- **Filter results**: `query_cache(cache_key, conditions=[{"field": "title", "operator": "contains", "value": "VP"}])`
- **Sort results**: `query_cache(cache_key, sort_by=[{"field": "follower_count", "order": "desc"}])`
- **Count results**: `query_cache(cache_key, aggregate=[{"function": "count", "field": "*"}])`
- **Get more pages**: `get_page(cache_key, offset=next_offset, limit=10)`
Also review the returned data for:
- **Profile completeness**: Work history, education, skills presence
- **Contact quality**: Email deliverability, phone format
- **Relevance scoring**: Title match, company fit, location alignment
- **Enrichment opportunities**: Missing data that can be filled
### Step 4: Format Output
Choose your preferred output format:
**Chat Summary (Default)**
- Displays top prospects with key details
- Includes actionable next steps
- Shows data quality metrics
**CSV Export (via v2 export_data)**
```
Tool: mcp__anysite__export_data
Parameters:
- cache_key: <cache_key from execute>
- format: "csv"
```
Returns a download URL. Ready for CRM import (Salesforce, HubSpot, etc.)
**JSON Export (via v2 export_data)**
```
Tool: mcp__anysite__export_data
Parameters:
- cache_key: <cache_key from execute>
- format: "json"
```
Returns a download URL. Structured data for custom integration.
## Common Workflows
### Workflow 1: LinkedIn B2B Prospecting
**Scenario**: Find 50 qualified prospects at SaaS companies in specific roles
**Steps**:
1. **Search for prospects**
```
Tool: mcp__anysite__execute
Parameters:
- source: "linkedin"
- category: "search"
- endpoint: "search_users"
- params: {"keywords": "SaaS software cloud", "title": "Head of Marketing, VP Marketing, CMO", "location": "United States", "company_keywords": "software", "count": 50}
```
2. **Enrich top prospects** (for first 10-20 results)
```
For each prospect from step 1:
Tool: mcp__anysite__execute
Parameters:
- source: "linkedin"
- category: "user"
- endpoint: "get"
- params: {"user": "<prospect_username>", "with_experience": true, "with_education": true}
```
3. **Find email addresses**
```
For each qualified prospect:
Tool: mcp__anysite__execute
Parameters:
- source: "linkedin"
- category: "email"
- endpoint: "find"
- params: {"user": "<prospect_username>"}
```
4. **Export to CRM**
```
Tool: mcp__anysite__export_data
Parameters:
- cache_key: <cache_key from search>
- format: "csv"
```
Import the CSV to your CRM system and set up outreach sequences.
**Expected Output**:
- 50 prospects with LinkedIn profiles
- 10-20 enriched profiles with complete work history
- 5-15 verified email addresses
- CSV file ready for CRM import
### Workflow 2: Account-Based Marketing (ABM)
**Scenario**: Find decision-makers at specific target companies
**Steps**:
1. **Research target companies**
```
Tool: mcp__anysite__execute
Parameters:
- source: "linkedin"
- category: "search"
- endpoint: "search_companies"
- params: {"keywords": "<your ICP description>", "industry": "<target industry>", "employee_count": ["51-200", "201-500"], "location": "<target location>", "count": 20}
```
2. **Get company details**
```
For each target company:
Tool: mcp__anysite__execute
Parameters:
- source: "linkedin"
- category: "company"
- endpoint: "get"
- params: {"company": "<company_identifier or URL>"}
```
3. **Find employees at target companies**
```
For each target company:
Tool: mcp__anysite__execute
Parameters:
- source: "linkedin"
- category: "search"
- endpoint: "search_users"
- params: {"company_keywords": "<Company Name>", "title": "VP, Director, Head of, Chief", "count": 10}
```
4. **Enrich decision-makers**
```
For each decision-maker:
Tool: mcp__anysiRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.