Menu
Explain a credit decision for an applicant and draft a grounded adverse-action notice. Usage /explain <applicant>
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
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 | explain |
| description | Explain a credit decision for an applicant and draft a grounded adverse-action notice. Usage /explain <applicant> |
Run the attribute → check → write loop and save a report.
python -m tools.attribute "<applicant>" > reports/_attribution.json
Read it; note the decision, probability, and the most negative features.python -m tools.check --attribution reports/_attribution.json
If ok is false, stop and re-run step 1 — a non-additive attribution is not faithful
and may not be used.decision == "approve", write a short approval note; no adverse-action reasons.decision == "deny", write an adverse-action notice (adverse-action-writer
agent): the principal reasons are the features with the most negative phi, at most
four, each cited by its adverse_action_reason. Never cite a protected attribute.reports/<applicant>.md:
phi,Every factor in the notice must come from reports/_attribution.json. No outside reasons,
no protected attributes, no numbers the tool did not produce.
Try these to start:
/explain alice ← denied; recent delinquencies dominate./explain carol ← denied; high credit utilization dominates./explain bob ← approved; no adverse-action reasons.