docs(eval): align llm-rubric quickstart

[christso]

Summary

• update README/docs/skills/examples away from authored llm-grader guidance toward promptfoo-style llm-rubric
• add nested agentv results compare/trend command aliases and update docs examples
• add a checked-in README quickstart example with default_test.options.rubric_prompt, short-form assertions, structured llm-rubric, and a script grader
• allow authored llm-rubric as the composite LLM aggregator while preserving existing internal plumbing

Validation

• bun test packages/core/test/evaluation/loaders/grader-parser.test.ts
• bun test packages/sdk/test/grader-helpers.test.ts
• bun run build
• bun run typecheck
• bun run validate:examples
• bun run lint
• bun apps/cli/dist/cli.js validate examples/features/readme-quickstart/evals/my-eval.eval.yaml
• live smoke via local OpenAI-compatible endpoint: LOCAL_OPENAI_PROXY_BASE_URL=http://127.0.0.1:10531/v1 LOCAL_OPENAI_PROXY_MODEL=gpt-5.3-codex-spark bun apps/cli/src/cli.ts eval examples/features/readme-quickstart/evals/my-eval.eval.yaml --targets examples/features/readme-quickstart/targets.yaml -> PASS, artifact .agentv/results/2026-07-03T07-13-17-761Z/index.jsonl

Bead: av-ml02

[cloudflare-workers-and-pages]

Deploying agentv with    Cloudflare Pages

Latest commit:	bc8677b
Status:	✅  Deploy successful!
Preview URL:	https://287a802a.agentv.pages.dev
Branch Preview URL:	https://fix-remove-stale-llm-grader.agentv.pages.dev

View logs