メニュー
Run the end-to-end text-to-signal ML pipeline and save a grounded report. Usage /pipeline
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Value a public company's equity end-to-end (FCFE at CAPM cost of equity) with an IB deal team — multi-year EDGAR data, scenario forecasting, Monte-Carlo DCF, dual-source comps, a verification gate, and an investment-committee sign-off. Run `/valuation <cik|ticker>`.
Value a public company end-to-end from its CIK or ticker. Run `/valuation <cik|ticker>`. Orchestrates EDGAR fetch, three parallel valuation lanes (Monte-Carlo DCF, dual-source comparables, qualitative/risk), and reconciliation into a fair-value median + P10–P90, benchmarked against the real market price.
Generate a professional 2-page report on a publicly-traded company as a self-contained HTML website. Given a company name, orchestrates five subagents in order (Generalist, Data Retriever, Data Scientist, Financial Analyst, Report Writer) — pulling the latest 10-K from SEC EDGAR, cleaning the financials, analyzing them, and writing the report. Use when the user asks for a company report, equity write-up, or 10-K-based analysis. Triggers include "write a report on <company>", "company report for <X>", "/company-report".
One sentence on what this command does and when to invoke it. Usage /my-skill "<arg>"
Answer a question about the bundled NovaCorp filings, grounded and graded. Usage /ask "<question>"
Route a research question, gather grounded evidence, and write a cited brief. Usage /brief "<question>"
| name | pipeline |
| description | Run the end-to-end text-to-signal ML pipeline and save a grounded report. Usage /pipeline |
Turn the labelled financial text in data/labeled/headlines.csv into features, train the
classifier, score it out of sample, and save a report citing the measured accuracy.
python -m tools.features "Earnings beat expectations and revenue surged."python -m tools.model "Earnings missed and the stock plunged on weak demand."python -m tools.evaluate --test-frac 0.3 --seed 42reports/pipeline.md containing only facts from the tool output:
tp, tn, fp, fn),P(up).
Quote every number exactly as the tools printed it. State no accuracy you did not run.If accuracy < 0.8, say the pipeline did not clear the floor — do not round up or excuse it.
Try these:
/pipeline ← full run on the default split.--seed and re-run to see how the held-out estimate moves.data/labeled/headlines.csv and re-run python -m pytest -q.