Lightweight Calculation Skill
Use this skill when the research task needs a small reproducible calculation but does not need full table normalization. Keep the calculation narrow and source-grounded.
Required Execution Standard
- Identify the exact input values and their source references.
- Use
executewith a short Python script for arithmetic, ratios, probability conversion, expected value, weighted averages, confidence/range arithmetic, or unit conversion. - Do not hand-compute values in prose when the arithmetic affects a finding.
- Use
/workspacefor sandbox-local files. Sandbox code cannot read or write/shared/directly. - Return the final result in your
ResearchNotesafter the successfulexecutecall (not viawrite_file);run_research_batchpersists your returned notes to/shared/. - State assumptions, rounding rules, missing inputs, and source references.
Execution Pattern
- Gather the relevant figures from source-tool output or research notes.
- Run a compact Python calculation with explicit variables.
- Inspect output and fix any code issue before using the result.
- Include a short calculation summary (Markdown or JSON) in your
ResearchNotesfor synthesis. - Cite the original source IDs in the eventual
ResearchFinding; the calculation artifact is supporting work, not a substitute for sources.
Python Template
from decimal import Decimal, ROUND_HALF_UP
inputs = {
"market_probability": Decimal("0.62"),
"payout_if_yes": Decimal("1.00"),
"price": Decimal("0.62"),
}
expected_value = inputs["market_probability"] * inputs["payout_if_yes"] - inputs["price"]
percentage = (inputs["market_probability"] * Decimal("100")).quantize(
Decimal("0.1"),
rounding=ROUND_HALF_UP,
)
print(f"Implied probability: {percentage}%")
print(f"Expected value per $1 payout contract: {expected_value:.3f}")
print("Assumptions: probability and price are current source values.")
Output Guidance
Keep the saved artifact short:
# Calculation Check: [topic]
- Inputs: ...
- Formula: ...
- Result: ...
- Rounding: ...
- Caveats: ...