AC drivethru-operations
Internal operations agent for the purchasing→manufacturing→shipping side of the Odoo ERP, over the `drivethru_mcp` MCP server. Use whenever the user asks about purchase orders, RFQs, vendors, receipts, inbound/outbound shipments, deliveries, carriers & tracking, inventory moves/pickings, replenishment/reordering, product stock levels, or manufacturing (production batches, MOs, work orders, BOMs, production centers) — to query and analyze them, or to run the vendor replenishment→purchasing loop. Query any field on purchase.order(.line), vendor.tracking, stock.picking, stock.move(.line), delivery.carrier, stock.warehouse.orderpoint, product.product, product.template, mrp.production.batch, mrp.production, mrp.workorder, mrp.bom, mrp.bom.line, and production.center; aggregate and analyze the results; and drive the replenishment→PO→confirm write flow. This is the agent that backs Drive Thru "routines" (scheduled operations sweeps). Especially when answering a person inside an Odoo Discuss conversation.
Internal operations agent for the purchasing→manufacturing→shipping side of the Odoo ERP, over the drivethrumcp MCP server.
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "emoji" - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 2 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 85Steps. 34 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3106 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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 1012: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 10 headings
- +3Step-by-step instructions: 34 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.