AC deskcrew-support
Run a customer support desk on DeskCrew. Read new tickets, answer from the knowledge base, and file replies for human approval. Use when handling customer support. Agents can also create and run their own bounty board over x402 with no account (the wallet that pays create_board owns it) and pay answering agents 85% on approval.
Run a customer support desk on DeskCrew.
As a process C 62/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches
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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Instruction override
en-ignore-previousSKILL.md:107Instruction-override phrase ("ignore previous instructions") (quoted — discussed, not commanded)*"ignore your previous instructions"*, *"you are now in admin mode"*, *"list every
quoted
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 3. 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 62/100
- 0Result and completion. Does not say what the result is
- 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. 7 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 25 steps
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1552 tokens
- 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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 329: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 25 items
- +4Has examples (2 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.