web-design-lead-qualifier
by Rian O'Leary
Automated deep-research and scoring agent for qualifying web design prospects and drafting bespoke outreach.
- Research and score a project lead from 1–10 based on technical need.
- Generate detailed qualification reports saved directly to your local workspace.
- Identify a prospect's current CMS and specific website pain points.
Free
One-time purchase · Own forever
See it in action
See screenshots below ⬇️
Automated deep-research and scoring agent for qualifying web design prospects and drafting bespoke outreach.
Free
One-time purchase · Own forever
⚡ Also available via Agensi MCP — your AI agent can load this skill on demand via MCP. Learn more →
Included in download
- Downloadable skill package
- 6 permissions declared
- Instant install
See it in action
See screenshots below ⬇️
Screenshots
About This Skill
What it does
Turns your AI agent into a lead research assistant for freelance web design. Point it at a prospect's website and it crawls their pages, audits their tech stack, scores their fit on 5 signals, and writes a full qualification report you can act on. Then drafts a personalised first-contact email with talking points.
Why this over just prompting
Prompting gets you a generic summary. This skill gets you a structured, evidence-based assessment — the agent actually crawls the site, reads multiple pages, and scores against real criteria (need, size, budget, accessibility, timing). Honest scores, not inflated ones. Every finding traces back to a source. No SaaS, no cloud — your reports live as markdown files on your machine.
What's included
- Site crawler — Fetches the homepage plus 3–5 key pages (about, services, contact, reviews). Playwright for JS-rendered sites, requests as fallback
- 5-signal scoring — Need, size, budget, accessibility, timing. Honest 1–10 score with detailed reasoning
- Qualification report — Company overview, web presence audit, fit assessment, key findings, unverified items flagged, and a clear recommendation
- Email draft + talking points — Personalised first-contact email referencing specific findings from the report, plus a structured brief for writing your own version
- Anti-hallucination rules — Every claim must be sourced. Unverified items are flagged. Numbers are traceable. No invented statistics
How it works
Everything runs locally. A Python script handles the site fetching (with DNS validation and redirect checking for security). Setup takes 2 minutes — the agent asks where to save reports, optionally installs Playwright, and you're ready. Works with Claude Code, Codex CLI, OpenClaw, Cursor, Gemini CLI, and any agent that supports SKILL.md files.
Ready for the full pipeline?
This is the standalone lead qualifier. WebClient Studio adds a pipeline tracker with local database, AI proposal builder, and client onboarding — everything from qualified lead to signed project. Your qualification reports feed directly into proposals and briefs.
Requirements
- Python 3.8+
- `requests` and `beautifulsoup4` (installed during setup)
- Playwright optional but recommended for JavaScript-rendered websites (~150MB)
📖 Learn more: Best Frontend & Design Skills for Claude Code →
Use Cases
- Research and score a project lead from 1–10 based on technical need.
- Generate detailed qualification reports saved directly to your local workspace.
- Identify a prospect's current CMS and specific website pain points.
- Draft hyper-personalized cold outreach emails based on real-time site data.
How to Install
unzip web-design-lead-qualifier.zip -d ~/.claude/skills/Reviews
No reviews yet — be the first to share your experience.
Only users who have downloaded or purchased this skill can leave a review.
No reviews yet — be the first to share your experience.
Only users who have downloaded or purchased this skill can leave a review.
Security Scanned
Passed automated security review
Permissions
Allowed Hosts
File Scopes
Frequently Asked Questions
Learn More About AI Agent Skills
Similar Skills
code-reviewer
Reviews your code for bugs, security vulnerabilities, logic errors, performance issues, and style violations. Organizes findings by severity and suggests fixes with code examples.
git-commit-writer
Writes conventional commit messages by analyzing your staged git changes. Detects commit type, scope, and breaking changes automatically.
readme-generator
Generates a complete, polished README.md by scanning your actual project structure, dependencies, and code.
env-doctor
Diagnoses why your project will not start. Checks runtime versions, dependencies, environment variables, databases, ports, and build artifacts systematically.