AC Prediction Market Arbiter
Cross-platform divergence scanner comparing Kalshi and Polymarket prices on identical events. Fuzzy title matching across 1000+ markets per run, configurable thresholds for volume, divergence percentage, and match quality. Detects arbitrage opportunities and market mispricings automatically. Zero cost — both APIs are free. Part of the OpenClaw Prediction Market Trading Stack — divergences feed into Market Morning Brief and pair with Kalshi Command Center for execution.
As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, consistency
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
-
low Dangerous commands
cmd-cron-mentionSKILL.md:245Mentions editing / listing crontab (documentation of a security skill)# Add to crontab -e:
security skill
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens)
Process rating: all ten parameters 56/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 40Consistency. Frontmatter name (Prediction Market Arbiter) differs from the folder (prediction-market-arbiter)
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 69 steps
- 100Failures and branches. 5 branches, has a failure section
- 100Execution cost. Instruction body is 3385 tokens
- low 20 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
- +1No license
- +2Single-language instructions
- +3Description length 473: enough signal without eating the budget
- +4Structure: 46 headings
- +3Step-by-step instructions: 69 items
- +4Has examples (19 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.