CC drivethru-digitize-outsourcing
Outsource embroidery digitizing end to end for BaconCo (Odoo). On a routine, read the `digitize.demand` records that are Ready to send out, pull the decoration's embroidery artwork + specs (production PNG, AI source file, height/width, thread-colour names, ship date), download the two files, decide rush from the ship date, submit the job to the outside digitizer via the `artworklady-digitizing` skill with a brief that states the size and colours, and — only on a confirmed submission — transition the demand to Outsource in Odoo. Talks to Odoo through the `drivethru_mcp` MCP server (digitize_demand_* + decoration_* tools) and hands the actual portal submission to the `artworklady-digitizing` skill. Idempotent: it only ever works Ready demands and marks them outsourced after a confirmed send, so a retry can't double-post. Use whenever the user asks to outsource digitizing, send embroidery jobs to the digitizer / Artwork Lady, receive digitized files back, or run the digitizing-outsourcing routine. It also runs the RETURN leg: for demands already Outsourced, fetch the finished stitch file (DST) from the digitizer by job number and upload it to Odoo via `digitize_demand_upload`, advancing the demand Outsource → Sew Out, then parse the job's Production Worksheet PDF and push its stitch count, sewn size, and Stop-Sequence thread colours onto the decoration via `digitize_demand_apply_worksheet`, and file the vendor's returned files (worksheet PDF, DST, native design) away on the agent's own persistent storage — organized by job, retrievable on request, not in Odoo.
Outsource embroidery digitizing end to end for BaconCo (Odoo).
As a process C 52/100 · Has gaps — References files that are not bundled: ../artworklady-digitizing/SKILL.md
How to improve
- Shorten the description to 1024 characters.
- The text references files that are not there: add them or drop the references.
- 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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1584 chars, limit 1024 - warning
missing-refreference to a missing file: ../artworklady-digitizing/SKILL.md - note
description-budgetdescription takes 1584 of the ~15000-char shared budget for all skills - note
frontmatter-keyunknown frontmatter key "emoji" - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 52/100
- 0Tools and files. 1 referenced file(s) missing: ../artworklady-digitizing/SKILL.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4314 tokens
- 100Steps. 34 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (6 tags): a typed call is more reliable
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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1583: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +4Structure: 14 headings
- +3Step-by-step instructions: 34 items
- +4Has examples (13 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 48.