Borrowing it
Nothing to install: this file belongs to fbabelle/PrettySeriousResearcher. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fbabelle/PrettySeriousResearcher/main/.claude/skills/research-finance-rigor/SKILL.mdgit clone --depth 1 https://github.com/fbabelle/PrettySeriousResearcherWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/fbabelle/prettyseriousresearcher/research-finance-rigor)<a href="https://agentmods.dev/skills/fbabelle/prettyseriousresearcher/research-finance-rigor"><img src="https://agentmods.dev/badge/skills/fbabelle/prettyseriousresearcher/research-finance-rigor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fbabelle/prettyseriousresearcher/research-finance-rigor"><img src="https://agentmods.dev/badge/skills/fbabelle/prettyseriousresearcher/research-finance-rigor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00057 | $0.01317 |
| Opus 5 | $0.00028 | $0.00659 |
| Sonnet 5 | $0.00011 | $0.00263 |
| Haiku 4.5 | $0.00006 | $0.00132 |
Grade A, and why
research-finance-rigor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research finance-rigor — the AI×finance validity gate
Finance ML is where credible-looking results quietly die: a backtest that leaks future information, a Sharpe inflated by trying 200 configs and reporting the best, an alpha that evaporates under transaction costs, a dataset with survivorship bias. This gate enforces the two things a finance reviewer (and reality) will check — the data is clean and licensed, and the numbers are statistically honest — so a finance-leaning paper doesn't get desk-rejected or, worse, published wrong.
When it fires
Only for finance/market-facing topics (equity/factor/portfolio/trading/forecasting/microstructure/risk). research-topic-selection tags the topic as finance-leaning; this gate then has three touchpoints:
- Design-time (
research-algo-design) — bake the controls into the method before building (point-in-time features, temporal splits, cost model). - Run-time (
research-experiments) — enforce the anti-leakage sandbox and the statistical battery on every run. - Reporting (
research-writing/research-provenance) — every headline metric is reported after-cost, out-of-sample, and multiple-testing-aware.
1) Data licensing & provenance checkpoint (owned here)
Data is the binding constraint in AI×finance, so confirm it up front (a dead-end topic is one that needs data you can't license):
- Licensing & access — CRSP/Compustat/WRDS, Bloomberg/Refinitiv terms vs free tiers (FRED, Yahoo, SEC EDGAR, Polygon/IEX). Record what's licensed and what's not.
- Point-in-time, not restated — features must reflect what was knowable at the time; restated fundamentals are look-ahead.
- Survivorship & selection — delisted/dead names must be in the universe; a survivors-only backtest is biased upward.
- Provenance trail — record vendor, snapshot date, and point-in-time handling so results are checkable (feeds the appendix reproducibility statement).
- Ready-made bundles are not data — a framework's downloadable market bundle must be checked for currency, provenance and status (crawler source, end date, "disabled" notices, open issues on adjustments) before it enters the pipeline; several end years before the evaluation window. Price the vendor tiers from their own pages (points/tier thresholds, per-interface minimums, call caps, ToS on redistribution) — the tier that unlocks adjustment factors, delisted lists and index weights is usually cheap, the free tier usually isn't enough.
- Point-in-time index membership is the hard requirement — no free source gives it directly. Triangulate: a snapshot-by-date API looped daily/weekly, the index provider's official announcements for effective dates, and vendor monthly weights, merged into a
(code, start, end)interval table; smoke-test that delisted names keep their price history; use a fixed-anchor price adjustment (a vendor's forward-adjusted series anchored on a later date is look-ahead).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago Changed · +2 lines 5b9d0cb555bd
- 11d ago First seen · 50 lines · 57 tokens per session scan A ab89c19adf82
research-finance-rigor is a skill published in the GitHub repository fbabelle/PrettySeriousResearcher (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 57 tokens to every session and 1,317 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
monte-carlo
Use when the user wants Monte Carlo simulation of a PlanExe model — sampling from bounds to produce output distributions (mean/std/percentiles), threshold pass probabilities, and Pearson-correlation sensitivity rankings — given an extract-parameters-from-full JSON, a generate-bounds JSON, a generate-calculations…
cointegration-analysis
Cointegration testing for pairs trading using Engle-Granger, Johansen, and rolling stability analysis.
fin-paper-figure
Generate academic-quality figures (>=300 DPI) for economics and finance papers.
quant-experiment-runtime
Quant research experiment executor: discover an offline source database under the workdir's code-repo, build a panel, run a Research Artifact's entry point to compute research-object values, and evaluate IC/ICIR/RANKIC/coverage metrics. Runtime = Experiment Executor; it runs a Research Artifact via a Python-native…
fin-paper-writing
A workflow for turning a research outline and study design into a complete economics or finance paper. It coordinates drafting, figure creation, consistency checks, review rounds, LaTeX compilation, and submission checks.
fin-viz-launch
A tool for turning research data and a written description into academic charts. It can choose a suitable chart type, create plotting code with matplotlib or seaborn, and save the result as a high-resolution PDF, SVG, or PNG.