Improve user/agent facing skills

[drbenvincent]

Summary

• Rename the user-facing skills so their responsibilities are explicit: choosing-causalpy-methods now handles method/design selection, while running-causalpy-experiments handles fitting, model setup, summaries, plots, and interpretation.
• Expand the method-selection skill from a short DiD/ITS/SC decision tree into a broader CausalPy experiment router covering current public experiments, data-shape requirements, assumptions, risks, and handoff guidance.
• Expand the execution skill with method-specific reference pages for the broader experiment surface, including newer or previously uncovered workflows such as Piecewise ITS, SDiD, panel regression, staggered DiD, IPW, IV, PrePostNEGD, and regression kink.
• Add scale-aware custom prior guidance for PyMC-backed workflows so agents know when to standardize predictors/outcomes, how to set priors for common CausalPy models, and what fit sanity checks to run before trusting posterior effects.
• Tighten the new execution references so agent examples avoid unsupported outputs, include the required data setup where examples previously used placeholder df, and use cp.checks.* names for sensitivity checks.
• Update Cursor command pointers and the skills README to use the new skill names.

Follow-up

• After this lands, manually update the distributed skills on Decision Hub so users receive the renamed and expanded skill content.

Test plan

• prek run --files causalpy/skills/running-causalpy-experiments/SKILL.md causalpy/skills/running-causalpy-experiments/reference/regression_kink.md causalpy/skills/running-causalpy-experiments/reference/panel_regression.md causalpy/skills/running-causalpy-experiments/reference/inverse_propensity_weighting.md causalpy/skills/running-causalpy-experiments/reference/piecewise_its.md causalpy/skills/running-causalpy-experiments/reference/staggered_did.md causalpy/skills/running-causalpy-experiments/reference/instrumental_variable.md causalpy/skills/running-causalpy-experiments/reference/synthetic_control.md causalpy/skills/running-causalpy-experiments/reference/regression_discontinuity.md
• prek run --all-files

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 95.07%. Comparing base (d5d1fe0) to head (3bb7850).

Additional details and impacted files

@@           Coverage Diff           @@
##             main     #929   +/-   ##
=======================================
  Coverage   95.07%   95.07%           
=======================================
  Files          87       87           
  Lines       13701    13701           
  Branches      812      812           
=======================================
  Hits        13026    13026           
  Misses        479      479           
  Partials      196      196           

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[read-the-docs-community]

Documentation build overview

📚 causalpy | 🛠️ Build #32839730 | 📁 Comparing 3bb7850 against latest (d5d1fe0)

  🔍 Preview build  

1 file changed

± 404.html

[drbenvincent]

Pushed a follow-up commit: 3bb7850d.

This fixes the agent-facing issues from review by making the RegressionKink example match the actual treated/formula requirements, removing unsupported effect_summary() calls for IPW and panel regression, adding minimal data setup to template examples, and qualifying sensitivity-check references with cp.checks.*.

Verification:

• prek run --files causalpy/skills/running-causalpy-experiments/SKILL.md causalpy/skills/running-causalpy-experiments/reference/regression_kink.md causalpy/skills/running-causalpy-experiments/reference/panel_regression.md causalpy/skills/running-causalpy-experiments/reference/inverse_propensity_weighting.md causalpy/skills/running-causalpy-experiments/reference/piecewise_its.md causalpy/skills/running-causalpy-experiments/reference/staggered_did.md causalpy/skills/running-causalpy-experiments/reference/instrumental_variable.md causalpy/skills/running-causalpy-experiments/reference/synthetic_control.md causalpy/skills/running-causalpy-experiments/reference/regression_discontinuity.md
• prek run --all-files