BB drivethru-odoo
Talk to an Odoo ERP through its `drivethru_mcp` MCP server — discover the available Odoo tools at runtime and call them to look up eBay products/inventory, push eBay orders and read tracking, run the Accounts Payable PO→vendor-bill flow, review documents in the Documents app against their purchase orders and fix incorrect PO line pricing (the "check the Purchasing folder against the POs" / vendor-invoice pricing-review workflow, filing each document into Matched or Questions), schedule MRP production batches, drive vendor replenishment purchasing (run the replenishment report → curate lines → add to a PO → hand style/color/size/qty to the vendor's purchasing skill → write pricing + confirmation back and confirm the PO), and retrieve internal SOPs / best practices / policies from the Knowledge base scoped to the asking person's permissions. Use whenever the user needs to read from or write to Odoo, especially when you are answering a person inside an Odoo Discuss conversation.
Talk to an Odoo ERP through its drivethrumcp MCP server — discover the available Odoo tools at runtime and call them to look up eBay products/inventory, push…
As a process B 68/100 · Nearly there — weak spots: result and completion, running it twice
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 1
-
high Concealment
en-hide-from-userSKILL.md:39Instruction to hide actions from the user**Never tell the user you can't reach Odoo, that you "don't have the tools in
Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5276 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "emoji" - note
frontmatter-keyunknown frontmatter key "homepage" - note
edit-residuethe text marks something as outdated (lines 352, 357): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 68/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 6 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 5276 tokens
- 85Steps. 41 steps, 1 vague phrases
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 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 990: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -31 of 7 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 14 headings
- +3Step-by-step instructions: 41 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.