protocol-9-runner
Audits numerical claims and financial figures for validity and evidence.
Install
mkdir -p .claude/skills/protocol-9-runner && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14505" && unzip -o skill.zip -d .claude/skills/protocol-9-runner && rm skill.zipInstalls to .claude/skills/protocol-9-runner
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.
Executable Reality Audit for any GENGROUP deliverable touching numbers, finances, or planning. Auto-invoke when text contains P9 triggers (efficiency words like "+N млн", "удвоит", "уникальный актив", "база уже есть", "никто в РФ", or contextual triggers like external presentations, copied benchmarks, range estimates wider than 2x). Marks every figure as [ДАННЫЕ] or [ГИПОТЕЗА], runs 5 Reality Audit questions, applies hard rules, and returns a verdict.Key capabilities
- →Audit GENGROUP deliverables with numbers, finances, or planning
- →Tag every figure as verified data or hypothesis
- →Apply 5 Reality Audit questions to tasks
- →Enforce hard rules to block tasks
- →Route tasks through DATA, FENIX, and MARCO for verdicts
How it works
The skill automatically invokes when specific triggers are detected, tags all figures as data or hypothesis, applies a set of five audit questions and hard rules, and then routes the deliverable for multi-disciplinary verification before issuing a final verdict.
Inputs & outputs
When to use protocol-9-runner
- →Auditing financial plans
- →Verifying strategic projections
- →Validating numerical claims
About protocol-9-runner
Reviews deliverables for financial or planning claims. It forces tagging of all figures as either verified data or hypothesis, checks against sanity criteria, and returns a quality verdict.
Executable Reality Audit for any GENGROUP deliverable touching numbers, finances, or planning. Auto-invoke when text contains P9 triggers (efficiency words like "+N млн", "удвоит", "уникальный актив", "база уже есть", "никто в РФ", or contextual triggers like external presentations, copied benchmark
When not to use it
- →When skipping Protocol 9 due to urgency
- →When rounding numbers for aesthetic purposes
- →When accepting wide ranges as single points
Limitations
- →Figures without tags result in process incompletion.
- →Tasks with ICE ≥500, effect ≥10M ₽, or external presentations require the 5 Reality Audit questions.
- →Any violation of hard rules blocks the task.
How it compares
This skill provides an executable, structured reality audit process with specific tagging, questioning, and rule enforcement, which differs from a subjective or manual review of financial or planning claims.
Compared to similar skills
protocol-9-runner side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| protocol-9-runner (this skill) | 0 | 3mo | No flags | Advanced |
| quant-analyst | 103 | 4mo | No flags | Advanced |
| stock-analyzer | 71 | 3mo | Review | Beginner |
| creating-financial-models | 36 | 10mo | 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.