BB yubit
Use this skill whenever the user wants to do anything on the Yubit exchange: check prices, query wallet/spot/TradFi/earn/perp balances, transfer funds, inspect positions/orders/history/wallet flow records, place or cancel perp orders, manage leverage or mode, set take-profit / stop-loss, or troubleshoot exchange requests.
As a process B 65/100 · Nearly there — weak spots: result and completion, inputs and preconditions, execution cost
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 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
- 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
✓ No critical or high findings
Medium and low: 1
-
medium Concealment
en-hide-from-userSKILL.md:662Instruction to hide actions from the user (detector / deny-list definition)- `perpCreateTpSl` returns success but TP/SL still 0.0: position was not matched (likely missing `pzLinkId`). Re-query and retry with correct `pzLinkId`. Do not tell user "success" until confirmed by
detector
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 11895 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 65/100
- 0Result and completion. Does not say what the result is
- 30Inputs and preconditions. Does not say what the process needs to start
- 40Execution cost. Instruction body is 11895 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 85Steps. 388 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 50 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 35 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
- +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
- +4No input/output examples
- +2Single-language instructions
- +3Description length 323: enough signal without eating the budget
- +4Structure: 38 headings
- +3Step-by-step instructions: 388 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.