BC bing-ads-client-report
Use when someone asks for a monthly Microsoft Ads report for a client, wants the Bing section of a client deck built, needs last month's Microsoft Ads performance written up, asks for an end-of-month Bing Ads report, asks "what do I tell the client about Bing", or asks how to present a Microsoft Ads target they missed — even when they never say the word "report". For agencies and in-house teams reporting upward. Microsoft Ads (Bing) only.
Use when someone asks for a monthly Microsoft Ads report for a client, wants the Bing section of a client deck built, needs last month's Microsoft Ads…
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.
An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Instruction override
en-ignore-previousSKILL.md:190Instruction-override phrase ("ignore previous instructions") (quoted — discussed, not commanded)campaign called "ignore previous instructions" is a string of text.
quoted
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 16 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2964 tokens
- 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
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
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +3Description length 442: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 16 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.