Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →staskh/insider-trading
Get insider trading activity (SEC Form 4 filings) for one or more stocks.
Passed 13 of 18 test cases with the skill, and 9 of 18 without it.
and 4 more in the full report
7 fixed9 passed either way4 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
In what specific US timezone must all output timestamps and time-based calculations be formatted for the generated_at JSON field?
| Checked | Without skill | With skill |
|---|---|---|
| Timestamps and calculations use the America/New_York timezone. | Missed | Passed |
The instructions your model reads when the skill loads.
Fetch recent insider transactions from Yahoo Finance (SEC Form 4 data).
Note: If
uvis not installed orpyproject.tomlis not found, replaceuv run pythonwithpythonin all commands below.
uv run python scripts/insider_trading.py SYMBOLS [--days DAYS]
SYMBOLS - Single ticker or comma-separated list (e.g., NVDA or NVDA,PLTR,GOOG)--days - Trailing days to look back (default: 90)Returns JSON with:
transactions - List of insider trades with insider name, role, transaction type, shares, price, value, date, ownership typesummary - Net sentiment (net_buying, net_selling, neutral), buy/sell counts and valuesFor multiple symbols, results are ranked by net buying value (most buying first).
yfinanceAll timestamps and time-based calculations must use the America/New_York timezone. All JSON output must include generated_at (NY time string) and data_delay fields.
test cases passed, vs 9 / 18 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.