BC pdp-faq-from-support
Turn customer-support and pre-sales conversations into product-detail-page (PDP) copy—especially FAQs and objection-handling blocks—by mining recent tickets/chats for conversion-blocking doubts and rewriting them as clear, trust-building answers. Use this skill whenever the user mentions support tickets, live chat logs, CS transcripts, "what customers keep asking," pre-purchase objections, PDP FAQ, product page rewrite from customer questions, helpdesk themes (Zendesk, Gorgias, Intercom, etc.), or wants to automate or operationalize a rolling 30-day loop from support insights to on-page content—even if they only say "people ask the same things" or "our FAQ is stale." Also trigger on reducing repetitive CS load via self-serve PDP, conversion friction from unanswered doubts, or aligning PDP claims with what agents actually say. Do NOT use for pure technical SEO keyword stuffing with no support or objection data, legal-only regulatory filings with no merchant PDP copy request, or abstract brand storytelling with no tie to documented customer questions.
As a process C 64/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
How to improve
- Shorten the description to 1024 characters.
- 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: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1065 chars, limit 1024
Process rating: all ten parameters 64/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (pdp-faq-from-support) differs from the folder (pdq-faq-from-support)
- 70Failures and branches. 4 branches
- 100Tools and files. No external tools needed
- 100Steps. 27 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 1245 tokens
- 100Progress reporting. Reports progress
- medium 3 test cases, all positive: not one "should refuse" or "should ask first"
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 1065: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 7 headings
- +3Step-by-step instructions: 27 items
- +4Reference files are cited in the instructions (1 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.