woz-kblisted

# /woz-kb — reviewer knowledge-base tuning One skill, two subcommands: - **`woz-kb tune`** — the start-to-finish orchestrator: distill → backtest → learn (autotuner new-personas + per-PR missed-fixes) → re-measure the lift. Dry-run by default; `--apply` writes to the KB. Use this to onboard/tune a new repo or a whole org. - **`woz-kb backtest`** — the building blocks for power users: the raw backtest run plus `--tune`, `--missed-report`, `--org-tune`, `--ab-compare` (unchanged). The first positional arg selects the subcommand; if omitted it defaults to `backtest` (back-compat). ## When to use TRIGGER on: "tune the reviewer", "tune this repo", "onboard a repo", "tune the org", "backtest the reviewer", "how well does the reviewer do", or `/woz-kb`. DO NOT use for: reviewing the current branch (`/woz-review`), past-session recall (`/woz-recall`), or browsing the KB (`/woz-knowledge`). --- ## `woz-kb tune` — start-to-finish ```bash node --no-warnings=ExperimentalWarning ${CLAUDE_PLUGIN_ROOT}/scripts/woz-kb.js tune \ --repo with-woz/wozcode \ --anthropic-api-key-file ~/.woz/.anthropic-backtest-key ``` Pipeline per repo: **(1)** trigger a KB refresh → **(2)** distill human PR comments into baseline persona-hints → **(3)** training backtest (20 PRs × 3 rounds, or reuse a cached run) → **(4)** learn: the autotuner contributes **new personas** (its unique cross-PR synthesis), then missed-fixes contributes the **per-PR durable persona-hints** → **(5)** re-measure on the s