Replaces LLM stochastic inference with a deterministic tool for math, finance, tax, and statistics.
Install
mkdir -p .claude/skills/sootool && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/10737" && unzip -o skill.zip -d .claude/skills/sootool && rm skill.zipInstalls to .claude/skills/sootool
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
LLM 확률 추론 한계를 결정론 계산 도구로 대체. 산수·세무·금융·통계 요청 감지 시 자동 호출.Key capabilities
- →Calculate financial metrics
- →Determine tax liabilities
- →Perform statistical tests
- →Convert units
How it works
It delegates numeric and analytical requests to specialized computational tools to ensure precision.
Inputs & outputs
When to use sootool
- →Calculating NPV or IRR
- →Determining tax liabilities
- →Performing t-tests
- →Converting currencies
About this skill
When to invoke
수치 계산이 포함된 모든 요청에서 LLM 직접 연산 대신 SooTool 도구를 호출한다.
| Signal | Tool |
|---|---|
| Numbers + arithmetic | core.add / sub / mul / div or core.batch |
| income/capital gains/acquisition tax | tax.kr_income / tax.capital_gains_kr / realestate.kr_acquisition_tax |
| VAT / supply amount | accounting.vat_extract / accounting.vat_add |
| NPV / IRR / PV / FV / discount rate | finance.pv / fv / npv / irr |
| Depreciation | accounting.depreciation_straight_line / declining_balance |
| Business days / holidays | datetime.add_business_days / count_business_days |
| t-test / confidence interval / p-value | stats.ttest_* / stats.ci_mean |
| Probability PDF/CDF | probability.normal_* / binomial_* / poisson_* |
| Matrix / vector operations | geometry.matrix_* / vector_* |
| Unit conversion | units.convert / units.temperature |
| Currency conversion | units.fx_convert / fx_triangulate |
| Multiple scenarios | core.batch |
| Chain previous result to next calculation | core.pipeline |
| Bond yield / duration | finance.bond_ytm / bond_duration |
| Option pricing / Greeks | finance.black_scholes |
Active usage contract
- Session start: call
sootool.skill_guide()to load the trigger table. - Any response containing numbers must be preceded by a tool call.
- Cite
tracefrom the tool response in your answer. - Never compute arithmetic inline in a prompt.
Tool routing
Numeric request
├─ tax / regulatory → tax.* or realestate.* (year arg REQUIRED)
├─ VAT / accounting → accounting.*
├─ financial math → finance.*
├─ statistics → stats.*
├─ probability → probability.*
├─ N scenarios → core.batch
├─ chained steps → core.pipeline
└─ simple arith → core.add / sub / mul / div
Anti-patterns
- Do NOT write
40000000 × 0.15 = 6000000in the prompt — call core.mul. - Do NOT omit
yearwhen calling tax.* — results in UnsupportedPolicyError or wrong rates. - Do NOT call core.add 10 times — use core.batch instead.
- Do NOT ignore
status: "skipped"in pipeline responses. - Do NOT use trace_level="none" for tax/accounting — audit trail is required.
Playbooks (abbreviated)
payroll_to_net: core.pipeline(mul 12 → tax.kr_income → sub net)
vat_batch_summary: core.batch(vat_extract x N) → core.add supply/vat totals
loan_compare_3: core.batch(loan_schedule x 3 rates)
npv_sensitivity: core.batch(npv x 9 discount rates)
bond_yield_duration: core.batch(bond_ytm + bond_duration)
ab_test_full: ttest_two_sample + ci_mean(A) + ci_mean(B)
When not to use it
- →Inline arithmetic
- →Non-numeric analysis
Limitations
- →Requires tool invocation for all numbers
How it compares
It replaces LLM probabilistic inference with deterministic calculation tools.
Compared to similar skills
sootool side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| sootool (this skill) | 0 | 3mo | No flags | Intermediate |
| quant-analyst | 103 | 2mo | No flags | Advanced |
| stock-analyzer | 71 | 2mo | Review | Beginner |
| creating-financial-models | 36 | 8mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
quant-analyst
zenobi-us
Expert quantitative analyst specializing in financial modeling, algorithmic trading, and risk analytics. Masters statistical methods, derivatives pricing, and high-frequency trading with focus on mathematical rigor, performance optimization, and profitable strategy development.
stock-analyzer
FrancyJGLisboa
Provides comprehensive technical analysis for stocks and ETFs using RSI, MACD, Bollinger Bands, and other indicators. Activates when user requests stock analysis, technical indicators, trading signals, or market data for specific ticker symbols.
creating-financial-models
anthropics
This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment decisions
reconciliation
anthropics
Reconcile accounts by comparing GL balances to subledgers, bank statements, or third-party data. Use when performing bank reconciliations, GL-to-subledger recs, intercompany reconciliations, or identifying and categorizing reconciling items.
analyzing-financial-statements
anthropics
This skill calculates key financial ratios and metrics from financial statement data for investment analysis
us-stock-analysis
tradermonty
Comprehensive US stock analysis including fundamental analysis (financial metrics, business quality, valuation), technical analysis (indicators, chart patterns, support/resistance), stock comparisons, and investment report generation. Use when user requests analysis of US stock tickers (e.g., "analyze AAPL", "compare TSLA vs NVDA", "give me a report on Microsoft"), evaluation of financial metrics, technical chart analysis, or investment recommendations for American stocks.