Skills
A skill is a package of structured files that teaches an AI coding agent how to work with a specific tool or framework. The skill below was generated by Great Docs from this project’s documentation. Install it in your agent and it will be able to run commands, edit configuration, write content, and troubleshoot problems without step-by-step guidance from you.
Any agent — install with npx:
npx skills add https://aeturrell.github.io/specification_curve/Codex / OpenCode
Tell the agent:
Fetch the skill file at https://aeturrell.github.io/specification_curve/skill.md and follow the instructions.Manual — download the skill file:
curl -O https://aeturrell.github.io/specification_curve/skill.mdOr browse the SKILL.md file.
SKILL.md
--- name: specification_curve description: > Specification curve analysis for econometrics, built on pyfixest. Use when writing Python code that uses the specification_curve package. license: MIT compatibility: Requires Python >=3.12. --- # Specification Curve Specification curve analysis for econometrics, built on pyfixest ## Installation ```bash pip install specification_curve ``` ## API overview ### Classes The main entry point. Describe the specifications, estimate them, and plot the curve. - `SpecificationCurve`: Runs and plots every variant of a regression specification ### Functions Plot a results table directly, and select subsets of specifications. - `plot_curve`: Draws a specification curve - `subsets_by`: Builds a ``subsets`` argument with one sample per level of a column ### Example data Data sets used in the documentation and tests. - `load_example_panel`: Generates a synthetic firm-year panel - `load_example_data1`: Retrieves example data from a file included with the package - `load_example_data2`: Generates example data with one outcome and four regressors - `load_example_data3`: Generates example data with two outcomes, where the true effect of x1 is 0.4 ## Resources - [Full documentation](https://aeturrell.github.io/specification_curve/) - [llms.txt](llms.txt) — Indexed API reference for LLMs - [llms-full.txt](llms-full.txt) — Comprehensive documentation for LLMs