AC ebay-lister
Turn photos of an item into a real, LIVE eBay listing — identifies the item, researches sold-comp pricing, assesses condition, fills the essential listing fields, then drives your logged-in Chrome to eBay, fills the Create-listing form (photos included), and PUBLISHES it. Triggers on `/sell`, or messages like "sell this on ebay", "list this on ebay", "make me an ebay listing", "what's this worth + list it" — especially when photos are attached. On "List it" eBay validates and the script fills any required field from the payload and retries; if it still can't satisfy a required field it falls back to saving a DRAFT (never publishes junk) and reports what's missing.
Turn photos of an item into a real, LIVE eBay listing — identifies the item, researches sold-comp pricing, assesses condition, fills the essential listing…
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions
How to improve
- 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: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 62/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (bash, python, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 85Steps. 29 steps, 1 vague phrases
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3327 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low 12 top-level sections: this looks like several domains in one skill
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 672: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 29 items
- +4Has examples (3 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.