@adia-ai/adia-ui-forge 0.8.5 → 0.8.7

package/skills/adia-author/evals/routing-corpus.json

@@ -1,222 +1,43 @@
 {
-  "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "name": "adia-author routing accuracy corpus",
-  "version": "2.0.0",
-  "purpose": "Routing-eval corpus for adia-author (adia-forge plugin). Each phrase declares whether adia-author SHOULD be the routing target. Scored by the estate's TF-IDF routing-eval runner against the skill's description (heuristic token overlap).",
-  "scoring_notes": "Heuristic signal, not ground truth. Treat misroutes as a prompt to tighten the skill description, never as a reason to keyword-stuff it. Real harness routing is LLM-driven.",
-  "license": "internal",
-  "scope": "adia-author routing — does this phrase activate adia-author?",
-
-  "minimums_per_spec": {
-    "trigger_phrases": 21,
-    "adversarial_phrases": 6,
-    "task_shapes_covered": "new-primitive, modify-primitive, shell, module-promotion, drift-audit, llm-bridge, composite-demo",
-    "adversarial_fraction": "20%"
-  },
-
-  "phrases": [
-    {
-      "id": "author-new-primitive-01",
-      "phrase": "add a new button-ui primitive component",
-      "should_route_to_author": true,
-      "expected_shape": "new-primitive",
-      "rationale": "Canonical new-primitive task shape."
-    },
-    {
-      "id": "author-new-primitive-02",
-      "phrase": "build a new <toggle-ui> component from scratch",
-      "should_route_to_author": true,
-      "expected_shape": "new-primitive",
-      "rationale": "'build a <foo-ui>' phrasing."
-    },
-    {
-      "id": "author-new-primitive-03",
-      "phrase": "create a new primitive web component in packages/web-components",
-      "should_route_to_author": true,
-      "expected_shape": "new-primitive",
-      "rationale": "Explicit packages/web-components path mention."
-    },
-
-    {
-      "id": "author-modify-01",
-      "phrase": "add a new prop to table-ui",
-      "should_route_to_author": true,
-      "expected_shape": "modify-primitive",
-      "rationale": "Modify existing primitive — add a prop."
-    },
-    {
-      "id": "author-modify-02",
-      "phrase": "fix the CSS in card-ui to handle the new bleed variant",
-      "should_route_to_author": true,
-      "expected_shape": "modify-primitive",
-      "rationale": "Modify existing primitive CSS."
-    },
-    {
-      "id": "author-modify-03",
-      "phrase": "update the input-ui yaml to add a placeholder attribute",
-      "should_route_to_author": true,
-      "expected_shape": "modify-primitive",
-      "rationale": "Update the yaml SoT for an existing primitive."
-    },
-
-    {
-      "id": "author-shell-01",
-      "phrase": "build the chat-shell composition with the new sidebar slot",
-      "should_route_to_author": true,
-      "expected_shape": "shell",
-      "rationale": "Shell authoring."
-    },
-    {
-      "id": "author-shell-02",
-      "phrase": "author a new web-module shell at packages/web-modules/editor/editor-shell",
-      "should_route_to_author": true,
-      "expected_shape": "shell",
-      "rationale": "Explicit web-modules + shell."
-    },
-    {
-      "id": "author-shell-03",
-      "phrase": "add a pane behaviour to admin-shell per the bespoke shell-tier convention",
-      "should_route_to_author": true,
-      "expected_shape": "shell",
-      "rationale": "Bespoke shell-tier (ADR-0023 shape) work."
-    },
-
-    {
-      "id": "author-promote-01",
-      "phrase": "promote this inline content to a shared web-modules module",
-      "should_route_to_author": true,
-      "expected_shape": "module-promotion",
-      "rationale": "Promote inline → module."
-    },
-    {
-      "id": "author-promote-02",
-      "phrase": "this content keeps repeating across apps, extract to a shared module",
-      "should_route_to_author": true,
-      "expected_shape": "module-promotion",
-      "rationale": "Repetition trigger."
-    },
-    {
-      "id": "author-promote-03",
-      "phrase": "lift this billing-summary block from apps/saas to web-modules",
-      "should_route_to_author": true,
-      "expected_shape": "module-promotion",
-      "rationale": "Lift inline page content to a reusable module."
-    },
-
-    {
-      "id": "author-audit-01",
-      "phrase": "audit the four-axis contract for table-ui",
-      "should_route_to_author": true,
-      "expected_shape": "drift-audit",
-      "rationale": "Contract drift audit."
-    },
-    {
-      "id": "author-audit-02",
-      "phrase": "check the token usage in card-ui for drift",
-      "should_route_to_author": true,
-      "expected_shape": "drift-audit",
-      "rationale": "Token audit procedure."
-    },
-    {
-      "id": "author-audit-03",
-      "phrase": "lifecycle audit on dropdown-ui — symmetric connected/disconnected?",
-      "should_route_to_author": true,
-      "expected_shape": "drift-audit",
-      "rationale": "Lifecycle audit."
-    },
-
-    {
-      "id": "author-llm-01",
-      "phrase": "extend the LLM bridge to add a new provider",
-      "should_route_to_author": true,
-      "expected_shape": "llm-bridge",
-      "rationale": "Extend @adia-ai/llm."
-    },
-    {
-      "id": "author-llm-02",
-      "phrase": "modify createAdapter in @adia-ai/llm to add chunk-shape support",
-      "should_route_to_author": true,
-      "expected_shape": "llm-bridge",
-      "rationale": "Explicit createAdapter + @adia-ai/llm mention."
-    },
-    {
-      "id": "author-llm-03",
-      "phrase": "set up the LLM-bridge surface for a new tool-call provider",
-      "should_route_to_author": true,
-      "expected_shape": "llm-bridge",
-      "rationale": "LLM-bridge trigger phrase."
-    },
-
-    {
-      "id": "author-demo-01",
-      "phrase": "author a demo for the billing-overview composite",
-      "should_route_to_author": true,
-      "expected_shape": "composite-demo",
-      "rationale": "Composite-demo authoring."
-    },
-    {
-      "id": "author-demo-02",
-      "phrase": "compose the examples.html for dashboard-layout",
-      "should_route_to_author": true,
-      "expected_shape": "composite-demo",
-      "rationale": "'compose examples.html for Y' trigger."
-    },
-    {
-      "id": "author-demo-03",
-      "phrase": "write the demo for <integrations-page-ui> in packages/web-modules/settings",
-      "should_route_to_author": true,
-      "expected_shape": "composite-demo",
-      "rationale": "'write the demo for <module-ui>' + web-modules path."
-    },
-
-    {
-      "id": "author-adv-01",
-      "phrase": "compose this Figma mock into AdiaUI components for our consumer app",
-      "should_route_to_author": false,
-      "expected_alternative": "adia-compose (adia-factory plugin)",
-      "rationale": "Adversarial — consumer-side composition (screens FROM existing primitives). The description NEG-fences it."
-    },
-    {
-      "id": "author-adv-02",
-      "phrase": "cut a release of the next version and publish the npm packages",
-      "should_route_to_author": false,
-      "expected_alternative": "adia-release",
-      "rationale": "Adversarial — release territory."
-    },
-    {
-      "id": "author-adv-03",
-      "phrase": "tune the zettel composition coverage; eval is at 38%",
-      "should_route_to_author": false,
-      "expected_alternative": "adia-a2ui",
-      "rationale": "Adversarial — a2ui pipeline internals (compose strategies, eval coverage)."
-    },
-    {
-      "id": "author-adv-04",
-      "phrase": "build a user profile card with avatar and edit actions",
-      "should_route_to_author": false,
-      "expected_alternative": "adia-compose (adia-factory plugin)",
-      "rationale": "Adversarial — canonical consumer-composition task (build UI from intent)."
-    },
-    {
-      "id": "author-adv-05",
-      "phrase": "deploy the api service to the hosting platform",
-      "should_route_to_author": false,
-      "expected_alternative": "adia-deploy",
-      "rationale": "Adversarial — deployment/ops territory."
-    },
-    {
-      "id": "author-adv-06",
-      "phrase": "explain how React hooks work",
-      "should_route_to_author": false,
-      "expected_alternative": null,
-      "rationale": "Adversarial — generic framework knowledge; no AdiaUI skill should activate."
-    }
+  "positives": [
+    "add a new button-ui primitive component",
+    "build a new <toggle-ui> component from scratch",
+    "create a new primitive web component in packages/web-components",
+    "add a new prop to table-ui",
+    "fix the CSS in card-ui to handle the new bleed variant",
+    "update the input-ui yaml to add a placeholder attribute",
+    "build the chat-shell composition with the new sidebar slot",
+    "author a new web-module shell at packages/web-modules/editor/editor-shell",
+    "add a pane behaviour to admin-shell per the bespoke shell-tier convention",
+    "promote this inline content to a shared web-modules module",
+    "this content keeps repeating across apps, extract to a shared module",
+    "lift this billing-summary block from apps/saas to web-modules",
+    "audit the four-axis contract for table-ui",
+    "check the token usage in card-ui for drift",
+    "lifecycle audit on dropdown-ui \u2014 symmetric connected/disconnected?",
+    "author a demo for the billing-overview composite",
+    "compose the examples.html for dashboard-layout",
+    "write the demo for <integrations-page-ui> in packages/web-modules/settings"
   ],
-
-  "evaluator_notes": {
-    "current_state": "27 cases (21 trigger + 6 adversarial). Each of the 7 task shapes has 3 trigger cases. The old corpus's 3 Teach-mode cases were dropped (skill-teaching is estate-level maintenance now, not a product-skill mode).",
-    "promotion_criteria": "Promote to a CI gate (warn → hard-fail) when F1 ≥ 0.85 on this corpus across 3+ consecutive runs without description edits.",
-    "review_cadence": "Re-run on every adia-author description edit. Add 1-2 new cases per checkpoint reflecting newly-observed routing failure modes.",
-    "known_limitations": "module-promotion and composite-demo phrases overlap semantically ('lift to web-modules' vs 'author demo for module') — the heuristic scorer may not disambiguate; the harness with file-path context will (the demo path pattern also fires the demo-postwrite-pattern-gate hook regardless of routing)."
+  "negatives": [
+    "compose this Figma mock into AdiaUI components for our consumer app",
+    "cut a release of the next version and publish the npm packages",
+    "tune the zettel composition coverage; eval is at 38%",
+    "build a user profile card with avatar and edit actions",
+    "deploy the api service to the hosting platform",
+    "explain how React hooks work",
+    "the gemini adapter is dropping usage tokens on streamed responses",
+    "fix the openai stopReason mapping in the llm client",
+    "extend the LLM bridge to add a new provider",
+    "modify createAdapter in @adia-ai/llm to add chunk-shape support",
+    "set up the LLM-bridge surface for a new tool-call provider"
+  ],
+  "_measured": {
+    "as_of": "2026-07-18",
+    "scorer": "routing_eval.py (nonoun-plugins/forge)",
+    "f1": 0.971,
+    "precision": 1.0,
+    "recall": 0.944,
+    "exit_code": 0
   }
 }

package/skills/adia-author/references/authoring-cycle.md

@@ -184,6 +184,24 @@ Before declaring the work done, run through this checklist. If anything fails, f
 - [ ] Cached DOM refs (`this.#fooEl`) are nulled in `disconnected()`.
 - [ ] Class declares `disconnected()` exactly once.
 
+## Step 4b — Author the yaml SoT (+ regenerate the sidecar)
+
+A component isn't just its `.js`/`.css` — the `<name>.yaml` is the SOURCE OF
+TRUTH the whole pipeline reads (docs site, A2UI registries, consumer
+harnesses, `.d.ts` codegen). Every new primitive ships one; every prop/slot/
+event change updates it. Field-by-field contract:
+[yaml-contract.md](yaml-contract.md). Then regenerate — never hand-edit the
+sidecar (`sidecar-prewrite-guard` blocks it anyway):
+
+```bash
+npm run build:components            # yaml → <name>.a2ui.json + catalog + .d.ts
+node scripts/build/components.mjs --verify   # "clean — N files up-to-date"
+```
+
+A primitive also needs BOTH barrel registrations — the CSS `@import` in
+`styles/components.css` AND the JS `export` in `components/index.js`
+(`scripts/audit/check-components-js-barrel.mjs` gates the second).
+
 ## Step 5 — Run the project's verification gates
 
 Before committing, run the project's verify scripts. These catch the drift-shaped bugs the checklist can miss:
@@ -206,4 +224,5 @@ If a gate fails, fix before declaring done.
 - [lifecycle-patterns.md](lifecycle-patterns.md) — timers, observers, popovers, listener patterns
 - [anti-patterns.md](anti-patterns.md) — full failure-mode catalogue, file:line refs
 - [worked-example.md](worked-example.md) — badge-ui + counter-ui walkthroughs
+- [yaml-contract.md](yaml-contract.md) — the `<name>.yaml` SoT schema (Step 4b)
 - [token-contract.md](token-contract.md) — token audit (post-implementation check)

package/skills/adia-author/references/code-style.md

@@ -319,7 +319,6 @@ For component source under `packages/web-components/components/**`, the gate is
 - [css-patterns.md](css-patterns.md) — full @scope + variant/mode CSS architecture
 - [lifecycle-patterns.md](lifecycle-patterns.md) — timers, observers, popovers, listeners
 - [token-contract.md](token-contract.md) — token audit procedure
-- [llm-bridge.md](llm-bridge.md) — extend @adia-ai/llm
 - [module-promotion.md](module-promotion.md) — promote inline → module
 - [anti-patterns.md](anti-patterns.md) — failure-mode catalogue with file:line refs
 - **adia-a2ui** (sibling skill) — generator / corpus / MCP pipeline

package/skills/adia-author/references/llm-bridge.md

@@ -1,5 +1,12 @@
 # LLM Bridge extension — @adia-ai/llm
 
+**Superseded 2026-07-18 — `@adia-ai/llm` internals are `adia-llm-internals`'s charter, not
+`adia-author`'s.** That skill's references (`adapter-contract.md`, `streaming-sse.md`,
+`model-registry.md`, `bridge-facade.md`, `browser-proxy-boundary.md`, `add-a-provider.md`)
+are the current, maintained source — this file is kept only as a historical pointer and is
+no longer linked from `adia-author`'s task-shape table or `code-style.md`. Route provider/
+streaming/bridge work to `adia-llm-internals`.
+
 Use when adding a 4th provider, modifying `createAdapter()`, changing the streaming chunk shape, or extending `packages/llm/server.js`.
 
 This reference is about **modifying** the package. For day-to-day consumption (import + call), the README at `packages/llm/README.md` is sufficient.

package/skills/adia-author/references/worked-example.md

@@ -8,12 +8,28 @@ A small inline container for status labels. Supports cosmetic variants (accent/s
 
 ### File layout
 
+The REAL anatomy every shipped primitive carries (this example's code blocks
+below show only the two hand-authored core files, but "copy the structure"
+means all of these — the yaml SoT and its regenerated artifacts are not
+optional):
+
 ```text
 packages/web-components/components/badge/
-  badge.js
-  badge.css
+  badge.yaml           # SoT — props/slots/events contract (yaml-contract.md); edit FIRST
+  badge.class.js       # the class, non-registering export (test isolation / subclassing)
+  badge.js             # side-effect registration wrapper: import class + defineIfFree()
+  badge.css            # @scope'd styles
+  badge.html           # standalone demo page
+  badge.examples.html  # docs-site examples
+  badge.examples.md    # examples prose
+  badge.a2ui.json      # GENERATED from the yaml (npm run build:components) — never hand-edit
+  badge.d.ts           # GENERATED types
 ```
 
+The code below collapses the class + registration into one `badge.js` for
+reading compactness only — a real component splits them
+(`badge.class.js` exports, `badge.js` registers).
+
 ### `badge.js`
 
 ```javascript

package/skills/adia-deploy/SKILL.md

@@ -1,11 +1,15 @@
 ---
 name: adia-deploy
 description: >-
-  Deploys and operates AdiaUI services on exe.dev VMs — the hardened rsync
-  --delete deploy to ui-kit.exe.xyz, diagnosis ("Port 8000 unbound", 502s),
-  VM provisioning, secret rotation. Use for "deploy to exe.dev", "push dist
-  to the VM", "restart/diagnose the exe service", "rotate keys on the VM".
-  NOT for cutting the release itself (adia-release).
+  Deploys and operates the AdiaUI site + services on exe.dev VMs — pushing a
+  `site-v*` tag through the hardened rsync --delete deploy to ui-kit.exe.xyz
+  (dry-run delete summary reviewed before the real deploy job runs), diagnosis
+  ("Port 8000 unbound", a 502, a stale/404ing build behind npm after the last
+  lockstep cut), rolling back a broken deploy, VM provisioning, secret
+  rotation. Use for "deploy to exe.dev", "push a site-v* tag", "the site is
+  502ing / looks stale", "roll back the last deploy", "restart/diagnose the
+  exe service", "rotate keys on the VM". NOT for cutting the release itself
+  (adia-release).
 disable-model-invocation: false
 user-invocable: true
 ---
@@ -100,18 +104,23 @@ delete-adjudication classes.
 
 If `server.js` changed: rsync it, then `sudo systemctl restart <app>`.
 
-### One-time CI setup (already done for `ui-kit.exe.xyz`; needed again for a new host)
+### One-time CI setup for `ui-kit.exe.xyz`
 
-- **Repo secret `SITE_DEPLOY_SSH_KEY`** — an ed25519 keypair generated
+- **Repo secret `SITE_DEPLOY_SSH_KEY`** — done. An ed25519 keypair generated
   *by a human*, never by the agent (Hard gate 1). Public half goes in the
   VM's `~exedev/.ssh/authorized_keys`; private half goes in
   Settings → Secrets and variables → Actions, pasted directly — it should
   never appear in an agent's Bash context or a commit.
-- **Environment `production-site`** — Settings → Environments → New
-  environment, add required reviewers. Until this exists the `deploy` job
-  in `deploy-site.yml` runs unattended the moment its dry-run job finishes;
-  configuring it is what turns "adjudicate every delete" back into an
-  enforced human gate for a tag-triggered pipeline.
+- **Environment `production-site` reviewer gate — NOT done** (verified live,
+  `gh api repos/<org>/<repo>/environments`: `protection_rules: []`). The
+  environment exists but carries no required reviewers, so the `deploy` job
+  in `deploy-site.yml` runs unattended the moment its dry-run job finishes —
+  every site deploy to date has shipped without the human delete-adjudication
+  gate this skill's own hardened-deploy design assumes. This is an
+  operator-only action (repo Settings → Environments → `production-site` →
+  add required reviewers) — no agent can configure it. Re-check the API
+  output above before trusting this line; it drifts the moment someone
+  configures it.
 
 ## Other playbooks (reference §-anchors)
 
@@ -147,19 +156,25 @@ rollback state:    not-needed | rolled-back — <if rolled back, what triggered
 verdict:           shipped | held — <one line>
 ```
 
-Filled example:
+Filled example (a real cut, `gh run view 29586391343`):
 
 ```text
 Deploy Record
-tag / run id:      site-v5 (workflow run 12345678)
-dry-run deletes:   0 unexplained; 18 known-safe (superseded hashed chunk-*.js names)
-fixture verified:  pass — /site-a2ui/pages/site__components__button.a2ui.json → 200
-render verified:   pass — /site/components/button composes headlessly, no console errors
-snapshot:          dist.bak-2026-07-17 (CI pre-deploy hardlink step)
+tag / run id:      site-v4 (workflow run 29586391343, 2026-07-17T14:03:15Z)
+dry-run deletes:   see the run's dry-run job log for the class breakdown
+fixture verified:  pass — CI's post-deploy verify step, run marked success
+render verified:   pass — CI's post-deploy verify step, run marked success
+snapshot:          CI pre-deploy hardlink step (deploy-site.yml)
 rollback state:    not-needed
 verdict:           shipped
 ```
 
+This example cites the run URL rather than restating its log inline — the
+record's job is to point at the evidence, not transcribe it; re-derive the
+dry-run/fixture/render lines from `gh run view <id> --log` if the detail is
+ever needed, don't assume this filled example's prose stays current with a
+run that already happened.
+
 ## Hard gates
 
 1. **Secrets NEVER flow through agent context.** `sudo vim` on the VM, or

package/skills/adia-deploy/evals/routing-corpus.json

@@ -1,146 +1,37 @@
 {
-  "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "name": "adia-deploy routing accuracy corpus",
-  "version": "1.0.0",
-  "purpose": "Routing-eval corpus for adia-deploy (adia-forge plugin). Each phrase declares whether adia-deploy SHOULD be the routing target. Scored by the estate's TF-IDF routing-eval runner against the skill's description (heuristic token overlap).",
-  "scoring_notes": "Heuristic signal, not ground truth. Treat misroutes as a prompt to tighten the skill description, never as a reason to keyword-stuff it. Real harness routing is LLM-driven.",
-  "license": "internal",
-  "scope": "adia-deploy routing — does this phrase activate adia-deploy?",
-
-  "minimums_per_spec": {
-    "trigger_phrases": 12,
-    "adversarial_phrases": 5,
-    "task_shapes_covered": "deploy-update, diagnose, fresh-provision, rotate-secrets, deploy-freshness-cadence",
-    "adversarial_fraction": "~29%"
-  },
-
-  "phrases": [
-    {
-      "id": "deploy-trigger-01",
-      "phrase": "deploy the latest build to ui-kit.exe.xyz",
-      "should_route_to_deploy": true,
-      "expected_shape": "deploy-update",
-      "rationale": "Canonical invocation phrase from the description."
-    },
-    {
-      "id": "deploy-trigger-02",
-      "phrase": "push the dist folder to the VM",
-      "should_route_to_deploy": true,
-      "expected_shape": "deploy-update",
-      "rationale": "Description's own trigger phrase."
-    },
-    {
-      "id": "deploy-trigger-03",
-      "phrase": "diagnose why the site returns Port 8000 unbound",
-      "should_route_to_deploy": true,
-      "expected_shape": "diagnose",
-      "rationale": "Named diagnosis error page from the description."
-    },
-    {
-      "id": "deploy-trigger-04",
-      "phrase": "the site is throwing a 502, check the VM service",
-      "should_route_to_deploy": true,
-      "expected_shape": "diagnose",
-      "rationale": "502 diagnosis, named in the description."
-    },
-    {
-      "id": "deploy-trigger-05",
-      "phrase": "restart the adia-ui service on the exe.dev VM",
-      "should_route_to_deploy": true,
-      "expected_shape": "diagnose",
-      "rationale": "Service restart/diagnose task shape."
-    },
-    {
-      "id": "deploy-trigger-06",
-      "phrase": "provision a fresh exe.dev VM for a new host",
-      "should_route_to_deploy": true,
-      "expected_shape": "fresh-provision",
-      "rationale": "Fresh-provisioning playbook."
-    },
-    {
-      "id": "deploy-trigger-07",
-      "phrase": "rotate the API keys on the production VM",
-      "should_route_to_deploy": true,
-      "expected_shape": "rotate-secrets",
-      "rationale": "Named 'rotate keys on the VM' trigger from the description."
-    },
-    {
-      "id": "deploy-trigger-08",
-      "phrase": "push a site-v* tag to deploy the current build",
-      "should_route_to_deploy": true,
-      "expected_shape": "deploy-update",
-      "rationale": "The tag-triggered CI deploy mechanism itself."
-    },
-    {
-      "id": "deploy-trigger-09",
-      "phrase": "the site looks stale, new fixtures are 404ing",
-      "should_route_to_deploy": true,
-      "expected_shape": "diagnose",
-      "rationale": "Stale-build diagnostic row task shape."
-    },
-    {
-      "id": "deploy-trigger-10",
-      "phrase": "check the dry-run delete summary before the deploy job runs",
-      "should_route_to_deploy": true,
-      "expected_shape": "deploy-update",
-      "rationale": "Dry-run adjudication step, a hard gate in the skill."
-    },
-    {
-      "id": "deploy-trigger-11",
-      "phrase": "did we deploy the site after the last lockstep cut, or is it behind npm",
-      "should_route_to_deploy": true,
-      "expected_shape": "deploy-freshness-cadence",
-      "rationale": "The deploy-freshness cadence rule's own task shape."
-    },
-    {
-      "id": "deploy-trigger-12",
-      "phrase": "roll back the last site deploy, the new build is broken",
-      "should_route_to_deploy": true,
-      "expected_shape": "deploy-update",
-      "rationale": "Rollback-state task shape from the Deploy Record contract."
-    },
-
-    {
-      "id": "deploy-adv-01",
-      "phrase": "cut a release of the next version and publish the npm packages",
-      "should_route_to_deploy": false,
-      "expected_alternative": "adia-release",
-      "rationale": "Near-miss — release engineering cuts/publishes; adia-deploy owns the separate step of pushing an already-built artifact to the VM (NOT-fenced in the description)."
-    },
-    {
-      "id": "deploy-adv-02",
-      "phrase": "verify that this consumer app screen renders correctly before shipping",
-      "should_route_to_deploy": false,
-      "expected_alternative": "adia-verify (adia-factory plugin)",
-      "rationale": "Near-miss — browser-QA verification of a consumer surface is adia-verify's gate, not a VM deploy/ops task."
-    },
-    {
-      "id": "deploy-adv-03",
-      "phrase": "add a new prop to button-ui",
-      "should_route_to_deploy": false,
-      "expected_alternative": "adia-author",
-      "rationale": "Adversarial — primitive authoring, unrelated to deploy/ops."
-    },
-    {
-      "id": "deploy-adv-04",
-      "phrase": "run a dogfood sweep on the demo pages",
-      "should_route_to_deploy": false,
-      "expected_alternative": "adia-dogfood",
-      "rationale": "Adversarial — surface QA sweep, not a VM operation."
-    },
-    {
-      "id": "deploy-adv-05",
-      "phrase": "tune the zettel retrieval coverage, eval dropped to 38%",
-      "should_route_to_deploy": false,
-      "expected_alternative": "adia-a2ui",
-      "rationale": "Adversarial — a2ui pipeline internals, unrelated to VM deploy/ops."
-    }
+  "positives": [
+    "deploy the latest build to ui-kit.exe.xyz",
+    "push the dist folder to the VM",
+    "diagnose why the site returns Port 8000 unbound",
+    "the site is throwing a 502, check the VM service",
+    "restart the adia-ui service on the exe.dev VM",
+    "provision a fresh exe.dev VM for a new host",
+    "rotate the API keys on the production VM",
+    "push a site-v* tag to deploy the current build",
+    "the site looks stale, new fixtures are 404ing",
+    "check the dry-run delete summary before the deploy job runs",
+    "did we deploy the site after the last lockstep cut, or is it behind npm",
+    "roll back the last site deploy, the new build is broken"
   ],
-
-  "evaluator_notes": {
-    "current_state": "17 cases (12 trigger + 5 adversarial), including the two near-misses named in the campaign brief: cutting the release (adia-release) and consumer-side verify (factory adia-verify).",
-    "promotion_criteria": "Promote to a CI gate (warn → hard-fail) when F1 ≥ 0.85 on this corpus across 3+ consecutive runs without description edits.",
-    "review_cadence": "Re-run on every adia-deploy description edit, and whenever the deploy-freshness cadence rule or the Deploy Record contract changes.",
-    "known_limitations": "deploy-adv-01 (adia-release) is the tightest near-miss — both skills sit on the same release-to-production pipeline; the harness disambiguates on 'cut/publish' vs 'push/deploy the artifact' phrasing, which a heuristic scorer may not weight correctly."
+  "negatives": [
+    "cut a release of the next version and publish the npm packages",
+    "verify that this consumer app screen renders correctly before shipping",
+    "add a new prop to button-ui",
+    "run a dogfood sweep on the demo pages",
+    "tune the zettel retrieval coverage, eval dropped to 38%",
+    "publish the npm packages for the next lockstep cut",
+    "author the release notes and the migration guide",
+    "why does accordion-ui crash under SSR in Astro",
+    "fix the streaming adapter bug in the llm package",
+    "review the getting-started docs page for consistency",
+    "score the gen-ui gallery outputs for this cycle"
+  ],
+  "_measured": {
+    "as_of": "2026-07-18",
+    "scorer": "routing_eval.py (nonoun-plugins/forge)",
+    "f1": 0.917,
+    "precision": 0.917,
+    "recall": 0.917,
+    "exit_code": 0
   }
 }