@koda-sl/baker-cli 0.141.0-dev.5c3f9a4ae → 0.142.0-dev.c858bcc46

package/README.md

@@ -2452,7 +2452,7 @@ baker actions log --from 2026-06-01 --to 2026-06-15   # explicit ISO window (ove
 baker actions get <action-id>
 baker actions status temp_hero jx123       # batch resolve real IDs and temp_* refs
 
-baker actions claim <action-id>            # live — returns action details + a fast-model list of skills to load (recommendedSkills)
+baker actions claim <action-id>            # live — returns action details + recommendedSkills + a routing hint (load owning skills and tool docs)
 baker actions release <action-id>
 
 baker actions create --name "Build hero" --priority high --tags landing,creative --description "..."
@@ -2517,7 +2517,7 @@ baker actions draft clear                   # drop everything staged in this cha
 Permissions enforced server-side:
 
 - Only `claim`/`release` mutate live state.
-- `claim` returns action details (`id`, `name`, `description`) plus `recommendedSkills` — a fast model reads the action's name/description/tags against the local `.claude/skills/` catalog and returns the skills (`{ name, reason }`) most worth loading for the work, echoed as `/skill — reason` lines in `hints`. It is best-effort: if the catalog is absent or the model call fails, the claim still succeeds and falls back to the generic "review and load relevant skills" hint.
+- `claim` returns action details (`id`, `name`, `description`) plus `recommendedSkills` — a fast model reads the action's name/description/tags against the local `.claude/skills/` catalog and returns the skills (`{ name, reason }`) most worth loading for the work, echoed as `/skill — reason` lines in `hints`. It is best-effort: if the catalog is absent or the model call fails, the claim still succeeds and falls back to a generic review hint. Every claim also carries a routing hint: actions often span several surfaces, so load every skill that owns part of the work and read the tool doc (`__tooling__/docs/tools/baker/<family>.md`) for each baker CLI family the work needs.
 - `complete` and `unlink` require the action to be claimed by the current chat — otherwise the API returns `FORBIDDEN` with a hint to claim first. Completing is the record that the work is done, so it stays claim-gated.
 - `update` and `discard` do NOT require a claim — a chat may edit or retire an action it never claimed. They are blocked only when another chat currently holds the claim (`CONFLICT` with that chat's title).
 - Claiming an action already claimed by another chat returns `CONFLICT` with the other chat's title — pick a different action.
@@ -4626,6 +4626,21 @@ baker creatives publish ./canvas/<run_id>/<final>.png --title "Spring Offer 4x5"
 
 Without `--slug` the command behaves as before (one creative record per published image). With `--slug` it upserts the repo-convention row — the same one the dashboard's Creatives tab and the `src/creatives/{slug}/` folder describe — so publish, repo sync, and run history all land on a single record regardless of order.
 
+## Landing Quality (`baker landing`)
+
+Deterministic design-quality critic for landing pages — an offline, no-LLM detector for the well-known "AI slop" tells (gradient text, overused fonts like Inter, side-tab colored borders, cream/parchment grounds, purple-on-heading palettes, buzzword copy, broken images, and more). It scores a landing's `.astro` source and returns findings tiered **block / warn / advisory**.
+
+```bash
+baker landing critique spring-offer      # score src/pages/spring-offer/
+baker landing critique spring-offer --full   # also print advisory-tier findings
+```
+
+- **Advisory by design — findings never fail it.** A finding is guidance, not a gate; the command errors (exit 2) only on a wrong slug (`NOT_FOUND` / `INVALID_SLUG`, with `error.fix.availableSlugs`).
+- **BRAND.md is the allowlist.** A font, hue, or ground that the client's `src/brand/BRAND.md` (mirrored into `src/styles/global.css` `@theme`, hex or oklch) commits is a decision, not a tell — matched values downgrade to advisory `brandDrift` so the critic never fights a real brand.
+- **Records a freshness snapshot** to `.cache/landing-critique/<slug>.json` (the source hash it scored). The publish quality gate reads it to enforce that every changed landing was critiqued and ships no block-tier tell. Re-run after edits so the snapshot stays fresh.
+
+Output is the standard envelope `{ ok, data, hints }` with `data = { advisory, slug, overall, counts, dimensions, findings }`. `dimensions` scores seven design families (typography, color, borders_depth, motion, spacing, copy, integrity) 0–1 (higher is better); `counts` is the block/warn/advisory tally.
+
 ## Help & Discovery
 
 Every command supports `--help` for usage info: