AB paradex-risk-guardian
Real-time risk monitoring, margin analysis, and protective alerts for Paradex trading accounts and vaults. Synthesizes account summary, positions, market data, and funding rates into actionable risk metrics — liquidation distance, portfolio concentration, margin utilization, exposure heatmaps, and daily P&L attribution. Use this skill whenever the user asks about their risk on Paradex, margin health, liquidation levels, portfolio exposure, drawdown, how much they can lose, position sizing, or when they say things like "am I safe", "check my risk", "how close am I to liquidation", "what's my exposure", "should I be worried", "risk report", or any question about the safety of their Paradex positions or vault positions. Also trigger for any request to monitor or set alerts on Paradex account health.
As a process B 73/100 · Nearly there — weak spots: inputs and preconditions, progress reporting
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: 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 73/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 55Failures and branches. 1 branches
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 46 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1535 tokens
- 100Running it twice. No mutating operations
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 807: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +4Structure: 14 headings
- +3Step-by-step instructions: 46 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.