Inference Known Good Config

Capture + enforce per-model KNOWN-GOOD serving configs: the REQUIRED serve flags (boot-blockers / crash-at-high-c / deploy-correctness workarounds) plus the champion + the bug each flag avoids, in one queryable registry (perf-tune-report/configs/known-good-configs.yaml) so a hard-won workaround (e.g. Qwen3-Next's gdn_prefill_backend=triton on vLLM 0.22) is NEVER re-discovered the hard way. These are NOT well-known upstream defaults -- several are field-discovered workarounds where the upstream `auto` path is actively broken on the target hardware. `record` after a champion is found, `check` (fail-closed) before any deploy/ship. Keep the registry private -- never post an entry publicly. Triggers on "known-good config", "required flags for <model>", "did we capture the flag combo", "register the config", "check the deploy config", "config drift", "what flags does <model> need", or any combination of "known-good / required / champion config" with "record / check / register / capture / drift / flags / serve".

mkdir -p ~/.claude/skills/inference-known-good-config
curl -L https://claudskills.com/skills/inference-known-good-config/SKILL.md \
  -o ~/.claude/skills/inference-known-good-config/SKILL.md

@misc{inference-known-good-config-2026,
  author    = {cfregly},
  title     = {Inference Known Good Config [Claude Code skill]},
  year      = {2026},
  publisher = {ClaudSkills},
  url       = {https://claudskills.com/skills/inference-known-good-config/}
}