feat(evals): add eval suite for setup-override-upstream skill

[justinmclean]

Summary

15 cases across 4 steps covering the override-upstreaming workflow: pre-flight repo/drift checks, override selection dispatch, upstreamability classification, and PR confirmation gating.

Generated-by: Claude (Opus 4.7)

Type of change

• Skill change (.claude/skills/<name>/) — eval fixtures updated below
• Tool / bridge contract (tools/<system>/*.md)
• Python package (tools/*/ with pyproject.toml)
• Groovy reference impl
• Cross-cutting (RFC, AGENTS.md, sandbox, privacy-LLM)
• Documentation (docs/, README.md, CONTRIBUTING.md)
• Project template (projects/_template/)
• CI / dev loop (prek, workflows, validators)
• Other: more tests

Test plan

• prek run --all-files passes
• For Python packages touched: uv run pytest / ruff check / mypy passes
• For Groovy bridges touched: command-line invocation tested end-to-end
• For skill changes: eval suite passes for the affected skill
  (PYTHONPATH=tools/skill-evals/src python3 -m skill_evals.runner tools/skill-evals/evals/<skill>/)
• For skill behaviour changes: a new or updated eval fixture is included in this PR
  (a regression test for the bug fixed / the behaviour added — see CONTRIBUTING.md)
• Other:

[potiuk]

LGTM — 15 cases across the four highest-signal decision points in
setup-override-upstream (pre-flight repo/drift, override pick, upstreamability
classification, PR confirm). All four step-configs resolve to real SKILL.md
headings. The two prompt-injection cases (override-pick and upstreamability)
correctly preserve real-state output rather than the injected answer. Runner
walks all 15 cases without parse errors.

---

This review was drafted by an AI-assisted tool and confirmed by an Apache Steward
maintainer. The maintainer approving this PR has read the findings and signed off.
If something feels off, please reply on the PR and a maintainer will follow up.

More on how Apache Steward handles maintainer review:
CONTRIBUTING.md.