Agent skill

Lead Generation Research Guide

by RightNow-AI in RightNow-AI/openfang

Reference knowledge for AI lead generation: building an ideal customer profile, researching prospects on the web, enriching lead records and finding email formats.

Apache-2.0Auto-check passedSales & Support

Install Lead Generation Research Guide

skills CLI
$ npx skills add RightNow-AI/openfang --skill lead-hand-skill -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install RightNow-AI/openfang lead-hand-skill --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/RightNow-AI/openfang.git skills-src && mkdir -p .claude/skills && cp -r skills-src/crates/openfang-hands/bundled/lead .claude/skills/lead-hand-skill && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
lead-hand-skill
GitHub stars
18k
Token cost
~1.8k tokens
SKILL.md length
509 words
Files
2
Skills in repo
68
Repo updated
First seen
Licence
Apache-2.0

At a glance

Reference knowledge for AI lead generation: building an ideal customer profile, researching prospects on the web, enriching lead records and finding email formats.

  • Works in 7 steps: Industry: What vertical does your ideal… → Company size: How many employees? What… → Geography: Where are they located? → …
  • Defining an ideal customer profile before prospecting
  • SKILL.md covers Ideal Customer Profile (ICP)…, Web Research Techniques for…, Lead Enrichment Patterns and Lead Scoring Framework, plus 3 more sections
  • Reaches acme.com and linkedin.com

What it does

The skill is a reference of lead-generation practice for an agent that finds and qualifies prospects. It starts with building an ideal customer profile from seven questions covering industry, company size, geography, technology, budget signals, decision-maker and pain points, and it gives a table of startup, SMB and enterprise size bands with typical budgets and sales cycles.

It then covers web research, with search query patterns for finding companies in a vertical and a ranked list of sources, from company websites and Crunchbase to public LinkedIn profiles, press releases, job boards, directories, news and social media. Enrichment is split into basic, standard and deep tiers, running from name, title and company through employee count, tech stack and social profiles to funding rounds, recent news and executive changes, plus common corporate email formats to try in order. The description also names scoring, deduplication and report generation, but the excerpt is cut off before those parts.

When your agent uses it

  • Defining an ideal customer profile before prospecting
  • Researching companies and decision-makers in a target industry
  • Enriching a list of leads with company and contact details

Example prompts

  • “Help me write an ICP for selling an HR analytics tool to mid-sized logistics companies.”
  • “Find fintech startups in Berlin that are hiring engineers and note their funding and tech stack.”
  • “Which sources should I trust most to confirm who runs sales at a target company?”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Industry: What vertical does your ideal customer operate in?
  2. Company size: How many employees? What revenue range?
  3. Geography: Where are they located?
  4. Technology: What tech stack do they use?
  5. Budget signals: Are they funded? Growing? Hiring?
  6. Decision-maker: Who has buying authority? (title, seniority)
  7. Pain points: What problems does your product solve for them?

What it can do on your machine

Read from SKILL.md and the folder at commit acf2587. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are csv, json and markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • acme.com
    • linkedin.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Lead Generation Research Guide loads about 1.8k tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 509 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~32
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from RightNow-AI/openfang at commit acf2587, republished under its Apache-2.0 licence (© RightNow-AI). 509 words, ~1,768 tokens.

Download SKILL.mdSave it as .claude/skills/lead-hand-skill/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
lead-hand-skill
description
Expert knowledge for AI lead generation — web research, enrichment, scoring, deduplication, and report generation
version
1.0.0
runtime
prompt_only

Lead Generation Expert Knowledge

Ideal Customer Profile (ICP) Construction

A good ICP answers these questions:

  1. Industry: What vertical does your ideal customer operate in?
  2. Company size: How many employees? What revenue range?
  3. Geography: Where are they located?
  4. Technology: What tech stack do they use?
  5. Budget signals: Are they funded? Growing? Hiring?
  6. Decision-maker: Who has buying authority? (title, seniority)
  7. Pain points: What problems does your product solve for them?
Company Size Categories
CategoryEmployeesTypical BudgetSales Cycle
Startup1-50$1K-$25K/yr1-4 weeks
SMB50-500$25K-$250K/yr1-3 months
Enterprise500+$250K+/yr3-12 months

Web Research Techniques for Lead Discovery

Search Query Patterns
# Find companies in a vertical
"[industry] companies" site:crunchbase.com
"top [industry] startups [year]"
"[industry] companies [city/region]"

# Find decision-makers
"[title]" "[company]" site:linkedin.com
"[company] team" OR "[company] about us" OR "[company] leadership"

# Growth signals (high-intent leads)
"[company] hiring [role]" — indicates budget and growth
"[company] series [A/B/C]" — recently funded
"[company] expansion" OR "[company] new office"
"[company] product launch [year]"

# Technology signals
"[company] uses [technology]" OR "[company] built with [technology]"
site:stackshare.io "[company]"
site:builtwith.com "[company]"
Source Quality Ranking
  1. Company website (About/Team pages) — most reliable for personnel
  2. Crunchbase — funding, company details, leadership
  3. LinkedIn (public profiles) — titles, tenure, connections
  4. Press releases — announcements, partnerships, funding
  5. Job boards — hiring signals, tech stack requirements
  6. Industry directories — comprehensive company lists
  7. News articles — recent activity, reputation
  8. Social media — engagement, company culture

Lead Enrichment Patterns

Basic Enrichment (always available)
  • Full name (first + last)
  • Job title
  • Company name
  • Company website URL
Standard Enrichment
  • Company employee count (from About page, Crunchbase, or LinkedIn)
  • Company industry classification
  • Company founding year
  • Technology stack (from job postings, StackShare, BuiltWith)
  • Social profiles (LinkedIn URL, Twitter handle)
  • Company description (from meta tags or About page)
Deep Enrichment
  • Recent funding rounds (amount, investors, date)
  • Recent news mentions (last 90 days)
  • Key competitors
  • Estimated revenue range
  • Recent job postings (growth signals)
  • Company blog/content activity (engagement level)
  • Executive team changes
Email Pattern Discovery

Common corporate email formats (try in order):

  1. firstname@company.com (most common for small companies)
  2. firstname.lastname@company.com (most common for larger companies)
  3. first_initial+lastname@company.com (e.g., jsmith@)
  4. firstname+last_initial@company.com (e.g., johns@)

Note: NEVER send unsolicited emails. Email patterns are for reference only.


Lead Scoring Framework

Scoring Rubric (0-100)
ICP Match (30 points max):
  Industry match:     +10
  Company size match: +5
  Geography match:    +5
  Role/title match:   +10

Growth Signals (20 points max):
  Recent funding:     +8
  Actively hiring:    +6
  Product launch:     +3
  Press coverage:     +3

Enrichment Quality (20 points max):
  Email found:        +5
  LinkedIn found:     +5
  Full company data:  +5
  Tech stack known:   +5

Recency (15 points max):
  Active this month:  +15
  Active this quarter:+10
  Active this year:   +5
  No recent activity: +0

Accessibility (15 points max):
  Direct contact:     +15
  Company contact:    +10
  Social only:        +5
  No contact info:    +0
Show full SKILL.md (207 more words)Show less
Score Interpretation
ScoreGradeAction
80-100AHot lead — prioritize outreach
60-79BWarm lead — nurture
40-59CCool lead — enrich further
0-39DCold lead — deprioritize

Deduplication Strategies

Matching Algorithm
  1. Exact match: Normalize company name (lowercase, strip Inc/LLC/Ltd) + person name
  2. Fuzzy match: Levenshtein distance < 2 on company name + same person
  3. Domain match: Same company website domain = same company
  4. Cross-source merge: Same person at same company from different sources → merge enrichment data
Normalization Rules
Company name:
  - Strip legal suffixes: Inc, LLC, Ltd, Corp, Co, GmbH, AG, SA
  - Lowercase
  - Remove "The" prefix
  - Collapse whitespace

Person name:
  - Lowercase
  - Remove middle names/initials
  - Handle "Bob" = "Robert", "Mike" = "Michael" (common nicknames)

Output Format Templates

CSV Format
csv
Name,Title,Company,Company URL,LinkedIn,Industry,Size,Score,Discovered,Notes
"Jane Smith","VP Engineering","Acme Corp","https://acme.com","https://linkedin.com/in/janesmith","SaaS","SMB (120 employees)",85,"2025-01-15","Series B funded, hiring 5 engineers"
JSON Format
json
[
  {
    "name": "Jane Smith",
    "title": "VP Engineering",
    "company": "Acme Corp",
    "company_url": "https://acme.com",
    "linkedin": "https://linkedin.com/in/janesmith",
    "industry": "SaaS",
    "company_size": "SMB",
    "employee_count": 120,
    "score": 85,
    "discovered": "2025-01-15",
    "enrichment": {
      "funding": "Series B, $15M",
      "hiring": true,
      "tech_stack": ["React", "Python", "AWS"],
      "recent_news": "Launched enterprise plan Q4 2024"
    },
    "notes": "Strong ICP match, actively growing"
  }
]
Markdown Table Format
markdown
| # | Name | Title | Company | Score | Key Signal |
|---|------|-------|---------|-------|------------|
| 1 | Jane Smith | VP Engineering | Acme Corp | 85 | Series B funded, hiring |
| 2 | John Doe | CTO | Beta Inc | 72 | Product launch Q1 2025 |

Compliance & Ethics

DO
  • Use only publicly available information
  • Respect robots.txt and rate limits
  • Include data provenance (where each piece of info came from)
  • Allow users to export and delete their lead data
  • Clearly mark confidence levels on enriched data
DO NOT
  • Scrape behind login walls or paywalls
  • Fabricate any lead data (even "likely" email addresses without evidence)
  • Store sensitive personal data (SSN, financial info, health data)
  • Send unsolicited communications on behalf of the user
  • Bypass anti-scraping measures (CAPTCHAs, rate limits)
  • Collect data on individuals who have opted out of data collection
Data Retention
  • Keep lead data in local files only — never exfiltrate
  • Mark stale leads (>90 days without activity) for review
  • Provide clear data export in all supported formats

© RightNow-AI, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in crates/openfang-hands/bundled/lead of RightNow-AI/openfang.

  • SKILL.md
  • HAND.toml

Open the folder on GitHubat commit acf2587

Compare with similar skills

Lead Generation Research Guide next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Lead Generation Research Guide compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Lead Generation Research Guide this skillRightNow-AI/openfang18k—~1.8kAutomated safety check: PassApache-2.0
B2B Lead Generationminhnv0807/ai-business-skills610—~1.2kAutomated safety check: PassMIT
Business Contact and Social Links Finderbrowser-act/skills6.1k1 repos~1.6kAutomated safety check: PassMIT
Cold Outreach Sequence BuilderBrianRWagner/ai-marketing-claude-code-skills440—~1.9kAutomated safety check: PassNone
Personalize Emailexplorium-ai/gtm-skills175—~2kAutomated safety check: PassMIT
Cold Outreachericrisco/rsc-harness174—~4.1kAutomated safety check: PassMIT

Similar skills

  • B2B Lead Generation

    minhnv0807/ai-business-skills

    Plans B2B pipeline work from ICP definition and prospecting through lead scoring, outbound sequences, sales assets and MQL to SQL handoff, aiming at qualified pipeline.

    610 GitHub stars~1.2k tokensUpdated 27 days ago
    Sales & SupportAuto-check passed
  • Finds a company's official website and social profiles from its name, or collects social links from a website URL, using BrowserAct templates run by a Python script.

    6.1k GitHub starsUsed in 1 repo~1.6k tokens
    Marketing & SEOAuto-check passed
  • Cold Outreach Sequence Builder

    BrianRWagner/ai-marketing-claude-code-skills

    Builds researched LinkedIn and email outreach for prospects, from a single message to a multi-prospect system, with personalization graded by the signals found.

    440 GitHub stars~1.9k tokensUpdated 6 mo ago
    Sales & SupportAuto-check passed
  • Personalize Email

    explorium-ai/gtm-skills

    Cold email personalization skill for Claude Code and Codex: assemble an intent and firmographic signal pack for one prospect so a downstream LLM can compose a truly personalized outbound email.

    175 GitHub stars~2k tokensUpdated yesterday
    Sales & SupportAuto-check passed
  • Cold Outreach

    ericrisco/rsc-harness

    A skill your agent uses when writing a cold email or LinkedIn DM to a stranger and its cadence: first-touch copy under a word ceiling, 4-7 step bump sequences, per-inbox volume and warm-up limits…

    174 GitHub stars~4.1k tokensUpdated yesterday
    Sales & SupportAuto-check passed
  • Lead Research

    TheCraigHewitt/skills

    When the user wants to research accounts, contacts, or build target lists.

    157 GitHub stars~5.9k tokensUpdated 4 mo ago
    Sales & SupportAuto-check passed

More from RightNow-AI/openfang

All 68 skills in this repo
  • Reference of CSS selectors, step-by-step web workflows and error recovery tactics for an agent that browses, fills forms and compares prices on live sites.

    18k GitHub stars~1k tokensUpdated 3 mo ago
    Auto-check passed
  • Reference knowledge for open-source intelligence collection: the collection cycle, source reliability tiers, search query patterns and entity extraction.

    18k GitHub stars~2.1k tokensUpdated 3 mo ago
    Auto-check passed
  • Video Clipping Reference

    RightNow-AI/openfang

    Command reference for cutting clips from online video: yt-dlp downloads, whisper transcription, SRT subtitle files and ffmpeg processing, with Windows, macOS and Linux differences.

    18k GitHub stars~4.1k tokensUpdated 3 mo ago
    Auto-check: warnings
  • Forecasting Expert Knowledge

    RightNow-AI/openfang

    Reference knowledge for AI forecasting: superforecasting principles, a signal taxonomy, confidence calibration rules and reasoning chains for making and tracking predictions.

    18k GitHub stars~2.5k tokensUpdated 3 mo ago
    Auto-check passed
  • Deep Research Methodology

    RightNow-AI/openfang

    Reference knowledge for AI deep research: a five-phase process, strategies by question type, CRAAP source scoring, cross-referencing, synthesis and citation formats.

    18k GitHub stars~2.6k tokensUpdated 3 mo ago
    Auto-check passed
  • Twitter Hand Skill

    RightNow-AI/openfang

    Expert knowledge for AI Twitter/X management — API v2 reference, content strategy, engagement playbook, safety, and performance tracking

    18k GitHub stars~2.9k tokensUpdated 3 mo ago
    Auto-check passed

Works with

Questions about Lead Generation Research Guide

What does Lead Generation Research Guide do?

Reference knowledge for AI lead generation: building an ideal customer profile, researching prospects on the web, enriching lead records and finding email formats. The skill is a reference of lead-generation practice for an agent that finds and qualifies prospects. It starts with building an ideal customer profile from seven questions covering industry, company size, geography, technology, budget signals, decision-maker and pain points, and it gives a table of startup, SMB and enterprise size bands with typical budgets and sales cycles.

When should I use Lead Generation Research Guide?

Lead Generation Research Guide fits situations like: defining an ideal customer profile before prospecting; researching companies and decision-makers in a target industry; enriching a list of leads with company and contact details.

How do I install Lead Generation Research Guide in Claude Code?

Run `npx skills add RightNow-AI/openfang --skill lead-hand-skill -a claude-code`. Or copy the skill folder (crates/openfang-hands/bundled/lead in RightNow-AI/openfang) into .claude/skills/lead-hand-skill in your project. Claude Code loads it when a task matches its description.

How do I install Lead Generation Research Guide in Codex?

Run `npx skills add RightNow-AI/openfang --skill lead-hand-skill -a codex`. Or copy the skill folder (crates/openfang-hands/bundled/lead in RightNow-AI/openfang) into .agents/skills/lead-hand-skill in your project. Codex loads it when a task matches its description.

Can I use Lead Generation Research Guide in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add RightNow-AI/openfang --skill lead-hand-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/lead-hand-skill, .gemini/skills/lead-hand-skill, .github/skills/lead-hand-skill and .opencode/skills/lead-hand-skill in your project.

What does Lead Generation Research Guide need to run?

SKILL.md names no scripts, command-line tools or credentials: Lead Generation Research Guide is instructions for the agent only.

Does Lead Generation Research Guide access the network?

SKILL.md names 2 domains. In commands or code: acme.com and linkedin.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Lead Generation Research Guide safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Lead Generation Research Guide use?

Lead Generation Research Guide is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Lead Generation Research Guide use?

About 1.8k tokens (SKILL.md is roughly 7.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Lead Generation Research Guide?

Skills that share tags, products or a category with Lead Generation Research Guide: B2B Lead Generation (minhnv0807/ai-business-skills, 610 stars), Business Contact and Social Links Finder (browser-act/skills, 6.1k stars), Cold Outreach Sequence Builder (BrianRWagner/ai-marketing-claude-code-skills, 440 stars) and Personalize Email (explorium-ai/gtm-skills, 175 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Lead Generation Research Guide?

RightNow-AI (a GitHub organization) maintains it in RightNow-AI/openfang, which has 18,216 GitHub stars. The repository holds 68 skills in this directory. The repository was last updated on July 2, 2026.

Source: RightNow-AI/openfang on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.