agentic skills for academic demo

[vedika-saravanan]

Description

Adds an academic CUDA-QX VQE/QAOA skill plus supporting evaluation tooling for comparing skill-guided answers against a no-skill baseline.

Changes

• Add the cudaq-academic-vqe-qaoa skill with install, VQE, QAOA, and metrics references
• Add prompt and assertion files for the academic VQE/QAOA comparison workflow
• Add evaluate_metrics.py for deterministic assertion-based scoring
• Add compare_runs.py for initializing paired run files and comparing with-skill vs without-skill results
• Add record_responses.py to simplify capturing multiline baseline responses
• Add BASELINE_COLLECTION.md with clean baseline collection instructions
• Document that generated run files under runs/ are local validation artifacts and are gitignored

Validation

• Verified eval Python scripts compile
• Verified eval JSON files parse
• Ran compare_runs.py init in a temporary directory
• Ran compare_runs.py compare against the initialized temp run files
• Locally validated a populated with-skill run during development with 100% pass rate, 21/21 coverage, and 0 forbidden hits

Notes

Generated .agents/evals/academic-vqe-qaoa/runs/*.json
(codex_with_skill.json
codex_without_skill.json) files are not included in this PR because the runs/ directory is gitignored. They should be treated as local validation artifacts unless explicitly force-added for a validation snapshot.

Token counts should be treated as approximate unless exact model usage metadata is present.

compare_runs.py, record_responses.py, and BASELINE_COLLECTION.md are included as eval workflow tooling. This PR should contain only the skill and not the eval collection workflow, those helper files should be removed.

Runtime / performance impact

Self-review checklist

Please confirm each item before requesting review. Check [x] or strike
through and explain.

Before requesting review

• I reviewed my own full diff in GitHub or my editor.
• PR is in Draft if it is not yet ready for review.
• Temporary / debugging changes have been removed.
• Local test logs reviewed; no unexplained warnings or errors.
• CI logs reviewed; no unexplained warnings or errors.
• Full CI has been run.

Scope and size

• PR is under ~1000 lines, or an exception is justified in the description.
• Refactoring-only changes are isolated in their own PR(s).
• No existing tests were disabled or modified just to make this PR pass
  (if so, an issue has been raised).

Tests

• New functionality has new tests.
• Tests fail if the new functionality is broken (including crashes), not
  just when it is missing.
• Negative tests added where exceptions are expected.
• Truth data added where simple EXPECT_* / assert checks are
  insufficient for algorithmic correctness.
• CI runtime impact considered; team notified if significant.

Documentation

• Public-facing APIs have Doxygen docs.
• User-visible behavior changes have public docs, or a follow-up is
  tracked.

Code style

• Naming follows the existing convention (snake_case vs camelCase) for
  the area being modified.

Dependencies

• No new third-party dependencies, or the team has been notified and
  OSRB tickets filed.