CC artworklady-digitizing
Artwork Lady embroidery-digitizing intake adapter — post a digitizing job into the Art work Lady portal (https://www.artworklady.com), which has no API. A Playwright driver logs in, opens the "Embroidery Digitizing" tab on the /placeorder form, fills the fields (job reference, turnaround, file type, color scheme, message), attaches 1–3 files, and — only when told to — clicks Send and confirms the job posted by watching the real order_form_submit response. Use when a decoration needs to be sent out for digitizing: "send this decoration to Artwork Lady", "post the digitizing job", "submit to the digitizer". It is a THIN PORTAL ADAPTER and touches no ERP: give it a job reference, the field values, and local file paths, and it returns a structured result. Pair it with a routine that polls Odoo `digitize.demand` (or `decoration`), downloads the attachments to disk, calls this skill, and updates the record on success. Submitting is gated behind `confirm: true`; the default is a dry run that fills and validates the form but posts nothing. A `fetch` command also downloads the FINISHED files back from `/orders` by job reference (the return leg), returning the DST path — by scraping our own order row so a job-number collision can't fetch the wrong file.
Artwork Lady embroidery-digitizing intake adapter — post a digitizing job into the Art work Lady portal (https://www.artworklady.com), which has no API. A…
As a process C 50/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1264 chars, limit 1024 - note
frontmatter-keyunknown frontmatter key "emoji" - note
frontmatter-keyunknown frontmatter key "homepage"
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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 7 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 100Steps. 6 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2222 tokens
- 100Progress reporting. Reports progress
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)
- +3Description length 1263: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Structure: 8 headings
- +3Step-by-step instructions: 6 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.