landing-page-intel

Extract competitor and customer intelligence from any company's landing page HTML. Discovers tech stack, analytics tools, ad pixels, customer logos, SEO metadata, CTAs, hidden elements, and more. No API keys required.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

96%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A lean, highly actionable body: executable commands, a verified CLI reference, and a clearly scoped single-action workflow. Its only notable weaknesses are minor redundancy around the no-API-key/cost messaging and a long inline vendor table that could be split into a reference file.

Suggestions

Collapse the 'Cost' section into the Quick Start line ('Free, no API keys — uses only HTTP requests to fetch public HTML') to remove the duplicated message.

Move the extensive per-vendor enumeration in 'What It Extracts' into a references file, keeping only the category rows inline.

Add a one-line note on handling fetch failures/timeouts (e.g. what --timeout does when a page is slow or blocks scraping) to round out the workflow.

Dimension	Reasoning	Score
Conciseness	The body is efficient — dense tables, no explanations of concepts Claude already knows — but 'No API keys required' is stated in both Quick Start and Cost, and the Cost section adds little beyond that duplication.	4 / 5
Actionability	Quick Start provides four copy-paste-ready commands covering single URL, multi-page, summary output, and file save; the CLI reference table's flags (--url, --pages, --output, --timeout) exactly match the actual script's argparse, so common cases are fully executable.	5 / 5
Workflow Clarity	This is a simple single-task skill and the single action — pip install requests, run the script with --url — is unambiguous; the read-only scrape carries no destructive or risky batch operations requiring validation checkpoints.	5 / 5
Progressive Disclosure	Well-organized sections with the single bundle script correctly referenced by full path (verified to exist with matching flags); however, the long inline 'What It Extracts' vendor enumeration is content that could arguably live in a reference file, leaving minor organization gaps.	4 / 5
	Total	18 / 20 Passed

Description

71%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, capability-rich description with strong natural trigger terms in the landing-page/competitor-intel domain. Its main weakness is the complete absence of a 'when to use' clause, which caps completeness and slightly weakens distinctiveness against neighboring web-analysis skills.

Suggestions

Append an explicit trigger clause, e.g. 'Use when researching a competitor's website, scanning a prospect's marketing site, or mapping a market's GTM tools.'

Add natural synonyms users would say — 'website', 'marketing site', 'homepage', 'competitive analysis' — to broaden trigger-term coverage.

Consider naming the output artifact (JSON report of a company's tech stack and GTM signals) to sharpen what the skill delivers.

Dimension	Reasoning	Score
Specificity	Enumerates multiple concrete actions — 'Extract competitor and customer intelligence', 'Discovers tech stack, analytics tools, ad pixels, customer logos, SEO metadata, CTAs, hidden elements' — giving comprehensive coverage rather than minor gaps.	5 / 5
Completeness	The 'what' is clear and specific, but there is no 'Use when...' clause or any equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Natural terms like 'landing page', 'competitor', 'tech stack', 'SEO', 'CTA' are present, but common variations users would say ('website', 'marketing site', 'homepage', 'competitive analysis') are missing, so it falls short of comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	The 'landing page HTML' intelligence niche is mostly distinct with clear triggers, but 'any company's landing page' is broad enough to create minor overlap risk with generic web-scraping or SEO-analysis skills.	4 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: gooseworks-ai/goose-skills
Path: skills/competitive-intel/capabilities/landing-page-intel/SKILL.md
Commit: cc3e518

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.