Refresh agent skills layout

[drbenvincent]

Summary

• Move developer workflow skills to .agents/skills/ as the canonical cross-agent home.
• Remove committed compatibility symlinks for .github/skills, .cursor/skills, and .claude/skills; developers can create uncommitted local symlinks if a tool has not caught up with .agents/skills/ discovery.
• Remove obsolete .cursor/commands stubs that only pointed back to skills, including stale entries such as implement.md that referenced a non-existent skill.
• Add the salvaged developer feature-exploration skill from Centralize AI config in .github/ and reorganize skills #925 in the new developer-skill location.
• Add user-facing causal-detective and example-datasets skills under causalpy/skills/, and document the Decision AI Hub follow-up expectation.

Provenance and attribution

• causalpy/skills/causal-detective/: adapted from Carlos Trujillo's work in Centralize AI config and reorganize skills #837 (ab915eb, co-authored with Claude) and carried through Centralize AI config in .github/ and reorganize skills #925; this PR trims and relocates it into the current user-facing causalpy/skills/ structure.
• causalpy/skills/example-datasets/: adapted from Carlos Trujillo's work in Centralize AI config and reorganize skills #837 (78c19f2, co-authored with Claude) and carried through Centralize AI config in .github/ and reorganize skills #925; this PR updates the dataset list against the current cp.load_data() registry.
• .agents/skills/feature-exploration/: adapted from Carlos Trujillo's work in Centralize AI config and reorganize skills #837 (78c19f2, co-authored with Claude) and carried through Centralize AI config in .github/ and reorganize skills #925; this PR rewrites it to match current CausalPy developer workflow rules.
• The .agents/skills/ layout decision, removal of committed compatibility symlinks and Cursor command stubs, and Decision AI Hub follow-up notes are new in this replacement PR.

Test plan

• $CONDA_EXE run -n CausalPy prek run --all-files

Notes

• Replaces the useful, non-stale parts of Centralize AI config in .github/ and reorganize skills #925 without undoing the newer user-skill split from Separate developer and user agent skills #927/Improve user/agent facing skills #929.
• After merge, update the distributed Decision AI Hub copy for changed user-facing skills.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 95.03%. Comparing base (f85604b) to head (c8d4f45).
⚠️ Report is 2 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #952      +/-   ##
==========================================
+ Coverage   94.98%   95.03%   +0.04%     
==========================================
  Files          89       89              
  Lines       13997    14105     +108     
  Branches      842      854      +12     
==========================================
+ Hits        13295    13404     +109     
+ Misses        491      489       -2     
- Partials      211      212       +1     

☔ View full report in Codecov by Harness.
📢 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 #33039720 | 📁 Comparing c8d4f45 against latest (4d2442b)

  🔍 Preview build  

5 files changed · ± 5 modified

± Modified

• 404.html
• genindex.html
• notebooks/staggered_did_pymc.html
• api/generated/causalpy.experiments.staggered_did.StaggeredDifferenceInDifferences.html
• _modules/causalpy/experiments/staggered_did.html