BC seo-audit
Audit a webpage's SEO and generate a scored report with actionable fixes. USE WHEN: - User provides a URL and asks to check/audit/review its SEO - User asks "how's my site's SEO?" or "what SEO issues does [URL] have?" - User wants to improve search rankings for a specific page - User asks to review meta tags, headings, or on-page optimization DON'T USE WHEN: - User wants keyword research or content strategy (that's research, not an audit) - User wants to track rankings over time (use a rank tracking tool) - User wants technical site-wide crawl analysis (this audits single pages, not full sites) - User wants Google Search Console or Analytics data (requires API access, not page scraping) - User wants to fix SEO issues (this diagnoses — fixing is a separate step) - User wants backlink analysis (requires third-party tools like Ahrefs/Moz) OUTPUTS: Markdown report with overall score (0-100), category breakdowns (Meta, Content, Technical, Performance), critical issues, warnings, and prioritized recommendations. INPUTS: A single URL to audit. Optionally: target keywords to check against.
Audit a webpage's SEO and generate a scored report with actionable fixes.
As a process C 50/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- Shorten the description to 1024 characters.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1103 chars, limit 1024
Process rating: all ten parameters 50/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 100Steps. 37 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 598 tokens
- 100Running it twice. No mutating operations
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +3Description length 1102: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 10 headings
- +3Step-by-step instructions: 37 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.