メニュー
Generates structured results reports after PyBondLab portfolio formation runs. Auto-apply when running StrategyFormation, BatchStrategyFormation, BatchWithinFirmSortFormation, or any portfolio sorting with PyBondLab.
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
Create a new empirical research project: generates projects/<name>/ with latex, code, scripts, results, literature, and guidance subfolders plus README.md and project-level CLAUDE.md.
Publication-ready figure conventions for empirical finance and economics. Covers matplotlib styling, color palettes, export settings, and common figure types (time series, decile bars, coefficient plots, event studies). Auto-apply when creating any figure, plot, or visualization.
Agent-driven cold-start onboarding. Use the repo shell entrypoint to find or install Python 3.11+, then run the shared bootstrap audit/plan/apply flow and configure WRDS only if the user has it.
Create and compile Beamer presentations following the Rhetoric of Decks philosophy. Use when making seminar or conference slides.
Compile LaTeX to PDF using pdflatex + bibtex cycle
Creates new Claude Code skills, auto-apply skills, or auto-trigger rules, or audits existing ones for quality and effectiveness.
| name | pybondlab-report |
| description | Generates structured results reports after PyBondLab portfolio formation runs. Auto-apply when running StrategyFormation, BatchStrategyFormation, BatchWithinFirmSortFormation, or any portfolio sorting with PyBondLab. |
Automatically generates a structured report folder after every PyBondLab run.
After any call to StrategyFormation.fit(), BatchStrategyFormation.fit(), BatchWithinFirmSortFormation.fit(), or DataUncertaintyAnalysis.fit() — always invoke the reporter before presenting results.
from PyBondLab.report import ResultsReporter
reporter = ResultsReporter(
result=result, # FormationResults or BatchResults
mnemonic='cs_single_5', # short name
script_text=SCRIPT, # the Python code that produced result
output_dir='results', # root directory (or project scripts/tests/{test}/output/)
)
report_path = reporter.generate()
| Strategy | Pattern | Example |
|---|---|---|
| SingleSort | {signal}_single_{nport} | cs_single_5 |
| DoubleSort | {var1}_{var2}_double_{n1}x{n2} | rat_cs_double_3x5 |
| WithinFirmSort | {signal}_wfs | cs_wfs |
| Batch SingleSort | batch_{n_signals}s | batch_3s |
| Batch WithinFirm | batchwfs_{n_signals}s | batchwfs_3s |
| FF-style | ff_{var1}_{var2}_{n1}x{n2} | ff_sze_bbtm_2x3 |
Single strategy: results/{mnemonic}_{YYYY_mm_dd}/ with meta.json, script.py, tables/summary_stats.csv, figures/portfolio_premia.png, figures/factor_bars.png, figures/cumret_turnover.png.
Batch: adds per-signal subfolders + summary/factor_comparison.png, summary/summary_stats.csv, and summary/factor_panel.parquet (sign-corrected tidy panel via extract_panel with NamingConfig(sign_correct=True)).
SCRIPT variable at the top of your codeResultsReporter(result, mnemonic, script_text=SCRIPT).generate()scripts/tests/{test_name}/output/ when working within a project