@bendyline/gilde 0.1.26 → 0.1.28

package/data/craftbook-templates/vo/voiceover-script/versions/1.0.1/test.json

@@ -0,0 +1,103 @@
+{
+  "schemaVersion": 1,
+  "title": "Voiceover / TTS Script smoke eval",
+  "objective": "Self-contained smoke eval for the Voiceover / TTS Script craftbook using the media generic harness.",
+  "tags": [
+    "media"
+  ],
+  "prompt": "Our media files are all listd in source/media-index.csv. Can you put together the production plan for them as media-plan.json?",
+  "setup": {
+    "projectName": "Voiceover / TTS Script Eval",
+    "about": "Self-contained eval project for voiceover-script. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/media-plan.json.",
+    "missionObjectives": "Use the Voiceover / TTS Script craftbook/template, read the seeded local fixtures, and write media-plan.json without network calls, real credentials, or live services.",
+    "files": [
+      {
+        "path": "source/brief.md",
+        "content": "# Voiceover / TTS Script Eval Brief\n\nClient: Boreal Desk, a home-office accessories company.\nAudience: operations leads who need an artifact they can use this week.\n\nFixed source facts for grounding:\n- The returns desk pilot covered 18 SKUs.\n- Median first response improved from 18 hours to 6 hours.\n- Preventable refund leakage fell from 14.2% to 8.9%.\n- The top unresolved complaint is status silence after photo submission.\n- Required next actions are automated status emails, barcode-exception training, and a weekly Finance exception export.\n\nUse these facts when the task asks for prose, analysis, copy, UI content, or test data. Do not use live web services, real credentials, or current outside data.\n\nCraftbook under test: voiceover-script - Voiceover / TTS Script.\n"
+      },
+      {
+        "path": "source/media-index.csv",
+        "content": "filename,type,duration_or_size,notes\npilot-interview.wav,audio,00:02:15,mentions response time and status silence\nreturns-desk.png,image,1600x900,shows intake form and photo evidence step\nlaunch-clip.mp4,video,00:01:05,shows barcode exception handling\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Producer"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "media-plan.json is a valid JSON media-production manifest grounded in seeded fixture metadata.",
+    "deliverables": [
+      {
+        "path": "media-plan.json",
+        "kind": "json",
+        "minBytes": 700,
+        "checks": [
+          {
+            "kind": "sniff",
+            "file": "media-plan.json",
+            "sniff": "json-valid"
+          },
+          {
+            "kind": "contains",
+            "file": "media-plan.json",
+            "pattern": "pilot-interview\\.wav|returns-desk\\.png|launch-clip\\.mp4",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "media-plan.json",
+            "pattern": "outputs|assets|steps|cues|verification",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "media-plan.json",
+            "pattern": "accessibility|alt|caption|transcript|metadata",
+            "flags": "i"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "media-plan.json",
+      "kind": "json"
+    },
+    "axes": [
+      {
+        "name": "completeness",
+        "description": "The manifest covers sources, outputs, and processing steps end to end."
+      },
+      {
+        "name": "grounding",
+        "description": "Only seeded media fixtures are referenced, with faithful metadata."
+      },
+      {
+        "name": "accessibility",
+        "description": "Alt text, captions, or transcripts are planned wherever the class requires."
+      },
+      {
+        "name": "precision",
+        "description": "Timestamps, crops, and cues are specific enough to execute."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "media fixture handling",
+    "structured manifest",
+    "verification metadata"
+  ],
+  "extensions": {
+    "legacySimulators": [
+      {
+        "id": "voiceover-script-media-fixtures",
+        "kind": "data-source",
+        "status": "implemented",
+        "description": "Seeded local media index replacing real audio, video, image generation, and external media metadata services."
+      }
+    ]
+  }
+}

package/data/craftbook-templates/we/weak-spot-drill/versions/1.0.1/craftbook.json

@@ -0,0 +1,154 @@
+{
+  "id": "weak-spot-drill",
+  "name": "Weak-Spot Drill",
+  "description": "Stop practicing what you already know: read the review record, name the actual weak spots with the numbers as evidence, and build a short targeted drill plus the follow-up schedule that closes them. Locks the ranked weak list FIRST — from the deck's boxes and miss counts, not vibes — then builds the drill page around only that material, then writes the plan that says when the spot counts as closed. Use for targeted practice, 'I keep missing the same ones', closing weak spots, drilling trouble topics, and study sessions that skip what already sticks.\n\nA gallery craftbook generated from an archetype spec. It runs\n`phase → (per-phase gate) → … → evaluate → (loop) → finish`. Each build\nphase that produces a checkable artifact is followed by a **runtime\ngate-checkpoint** — the runtime verifies the artifact and routes with no\nmodel turn, looping back to redo the phase on a miss. The final `evaluate`\nstep holds a static deliverable gate plus a reviewer QA pass. What it adds\nover the generic `build-loop`: a specialist role per phase, a\ndomain-correct ordering, and a concrete per-phase quality bar.\n\nDeliverables marked \"artifact\" land in the project's artifacts drawer (`write_artifact` / `read_artifact`), not the shipped workspace — review output is not product source.\n\nPhases:\n\n1. Rank the weak spots (studiemaat) — weak spots named from the record, with the numbers as evidence → gated on artifact `notes/scope.md` (markdown-notes)\n2. Build the drill (developer) — short interactive drill.html over only the weak material → gated on `drill.html` (html-page)\n3. Write the follow-up plan (coach) — the schedule that closes each weak spot → gated on artifact `report.md` (markdown-report)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "scope",
+  "triggers": [
+    "drill my weak spots",
+    "i keep missing the same ones",
+    "targeted practice from the results",
+    "what am i weakest on",
+    "make me a drill"
+  ],
+  "steps": [
+    {
+      "id": "scope",
+      "name": "Rank the weak spots",
+      "description": "weak spots named from the record, with the numbers as evidence",
+      "prompt": "Find the real weak spots before building anything. Step 1: read deck.json from the workspace — every card's box and its got-it/missed stats are the review record. Step 2: rank the weakness with evidence — cards stuck in box 1, cards missed as often as got, and the themes those cards cluster into; write each weak spot with its numbers ('irregular verbs: 5 of 6 cards in box 1, 11 misses against 4 got-its'), never a hunch. Step 3: lock the drill rules — only ranked weak material goes in, ten to fifteen items, each item coming at the card's idea from a fresh angle rather than repeating the card verbatim. Step 4: write an acceptance-criteria checklist ('every drill item traces to a ranked weak card', 'no item drills material the record says is strong', 'the drill checks answers on the spot', 'the follow-up plan says when each spot counts as closed'). Call write_task_note with the ranked list + checklist and write notes/scope.md.\n\nThe deliverable `notes/scope.md` lands in the project's artifacts drawer — write it with `write_artifact` and read it back with `read_artifact`; the shipped workspace stays untouched.",
+      "suggestedRole": "studiemaat",
+      "advanceWhen": {
+        "file": "notes/scope.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "notes/scope.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "notes/scope.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "scope",
+        "maxAttempts": 3
+      },
+      "next": "drill"
+    },
+    {
+      "id": "drill",
+      "name": "Build the drill",
+      "description": "short interactive drill.html over only the weak material",
+      "prompt": "Build the drill as one self-contained page at drill.html. Step 1: write the items from the ranked weak spots only — a strong card in the drill is a miss against the scope; come at each weak idea from a new angle (reversed prompt, a fill-in, a which-of-these) instead of re-showing the card. Step 2: make it interactive — the taker answers item by item, gets told right or wrong on the spot with the correct answer shown, and sees a simple tally at the end. Step 3: keep the tone warm — a drill on weak material stings enough already; the feedback should coach, not scold. Step 4: one file, inline styles and script, and check the script parses before completing. Call write_task_note with the item count and which weak spots each item targets.",
+      "suggestedRole": "developer",
+      "advanceWhen": {
+        "file": "drill.html",
+        "minBytes": 1,
+        "sniff": "html-complete"
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "drill.html",
+            "bytes": 2000
+          },
+          {
+            "kind": "htmlLint",
+            "file": "drill.html"
+          },
+          {
+            "kind": "cssMinBytes",
+            "bytes": 400,
+            "file": "drill.html"
+          },
+          {
+            "kind": "jsParses",
+            "file": "drill.html"
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkHtmlComplete",
+            "scope": "standard",
+            "inputs": {
+              "file": "drill.html"
+            }
+          }
+        ],
+        "onReject": "drill",
+        "maxAttempts": 3
+      },
+      "next": "plan"
+    },
+    {
+      "id": "plan",
+      "name": "Write the follow-up plan",
+      "description": "the schedule that closes each weak spot",
+      "prompt": "Write the follow-up at report.md. Step 1: restate the ranked weak spots with their numbers — the report should make sense to someone who never saw the scope notes. Step 2: give the schedule — when to run the drill again, which cards to put back into review through the project's study capabilities, and the spacing between passes. Step 3: define closed — the concrete signal (a clean drill run, the cards climbing out of box 1) that says a spot no longer needs drilling. Step 4: end with one encouraging, honest line about the trend. Keep it under a page. Write report.md and call write_task_note with the report path and the next review date.\n\nThe deliverable `report.md` lands in the project's artifacts drawer — write it with `write_artifact` and read it back with `read_artifact`; the shipped workspace stays untouched.",
+      "suggestedRole": "coach",
+      "advanceWhen": {
+        "file": "report.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "report.md",
+            "bytes": 800,
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i",
+            "label": "at least one markdown heading",
+            "artifact": true
+          }
+        ],
+        "onReject": "plan",
+        "maxAttempts": 4
+      },
+      "next": "evaluate"
+    },
+    {
+      "id": "evaluate",
+      "name": "Evaluate",
+      "description": "Grade the deliverable against every acceptance criterion. All pass → finish; any fail → loop back and fix the gap.",
+      "prompt": "Open drill.html, report.md, and deck.json and verify every criterion from notes/scope.md: every drill item traces to a ranked weak card — spot-check each against the record, an item drilling strong material means the drill is padding, and a generic quiz over the whole deck is the classic failure; the drill checks answers on the spot; the report restates the weak spots with their numbers, schedules the re-runs and re-reviews, and defines when each spot counts as closed. Write PASS/FAIL per criterion; on any failure, name the item or spot and loop back to drill.\n\nThe deliverable lives in the project's artifacts drawer — open `report.md` with `read_artifact`, not `read_file`.\n\nThen route — this is the whole point of the loop:\n\n- **Every criterion PASSES →** call `advance_task_step({ ref, stepId: \"evaluate\", next: \"finish\" })`.\n- **Any criterion FAILS →** write the specific gaps to notes, then call `advance_task_step({ ref, stepId: \"evaluate\", next: \"drill\" })` to loop back. The builder fixes exactly those gaps.\n\nNever route to `finish` while any criterion is unmet. The build phase's completion gate already blocked a grossly-incomplete deliverable; your job is the judgment an automated check cannot make (does it actually work, read well, look right). After ~3 unproductive loops, stop and report DONE_WITH_CONCERNS so the user can step in.",
+      "suggestedRole": "reviewer",
+      "consumes": [
+        {
+          "file": "report.md",
+          "artifact": true
+        }
+      ],
+      "next": "drill"
+    },
+    {
+      "id": "finish",
+      "name": "Finish",
+      "description": "All acceptance criteria met. Stamp a short summary and report DONE.",
+      "prompt": "Every acceptance criterion passed. Write a one-paragraph DONE summary to task notes via `write_task_note`: what was built, the deliverable path(s), and a one-line confirmation that each criterion is met. Then report DONE.",
+      "suggestedRole": "developer",
+      "terminal": true
+    }
+  ],
+  "version": "1.0.1",
+  "releasedAt": "2026-08-14T00:00:00Z"
+}

package/data/craftbook-templates/we/weak-spot-drill/versions/1.0.1/test.json

@@ -0,0 +1,124 @@
+{
+  "schemaVersion": 1,
+  "title": "Weak-Spot Drill — evidence-ranked, targeted, scheduled",
+  "objective": "Measure whether the weak-spot-drill craftbook reads the deck's review record, names the weak spots with numbers, and builds a drill over ONLY that material — plus a follow-up plan that says when each spot counts as closed.",
+  "tags": [
+    "html-page"
+  ],
+  "prompt": "i keep bombing the same stuff — can you figure out my weak spots from the results and make me a targetted drill?",
+  "setup": {
+    "projectName": "Music Theory Flashcards",
+    "about": "Study Buddy project for music theory. The deck and its review record live at workspace/deck.json — each card carries its Leitner box and got-it/missed stats. The drill goes to workspace/drill.html and the follow-up plan to workspace/report.md.",
+    "missionObjectives": "Targeting is the whole point: the drill covers only what the record marks weak, with the numbers as evidence, and the plan schedules the way back. No live services, no real credentials.",
+    "files": [
+      {
+        "path": "deck.json",
+        "content": "{\n  \"version\": 1,\n  \"subject\": \"Music theory basics\",\n  \"cards\": [\n    {\n      \"id\": \"card-1\",\n      \"front\": \"treble clef, second line from bottom\",\n      \"back\": \"G\",\n      \"box\": 3,\n      \"lastReviewedAt\": \"2026-07-15T18:00:00.000Z\",\n      \"createdAt\": \"2026-06-20T09:00:00.000Z\",\n      \"stats\": {\n        \"gotIt\": 7,\n        \"missed\": 1\n      }\n    },\n    {\n      \"id\": \"card-2\",\n      \"front\": \"bass clef, middle line\",\n      \"back\": \"D\",\n      \"box\": 3,\n      \"lastReviewedAt\": \"2026-07-15T18:00:00.000Z\",\n      \"createdAt\": \"2026-06-20T09:00:00.000Z\",\n      \"stats\": {\n        \"gotIt\": 7,\n        \"missed\": 1\n      }\n    },\n    {\n      \"id\": \"card-3\",\n      \"front\": \"ledger line above treble staff\",\n      \"back\": \"A5\",\n      \"box\": 3,\n      \"lastReviewedAt\": \"2026-07-15T18:00:00.000Z\",\n      \"createdAt\": \"2026-06-20T09:00:00.000Z\",\n      \"stats\": {\n        \"gotIt\": 7,\n        \"missed\": 1\n      }\n    },\n    {\n      \"id\": \"card-4\",\n      \"front\": \"treble clef, top space\",\n      \"back\": \"E5\",\n      \"box\": 3,\n      \"lastReviewedAt\": \"2026-07-15T18:00:00.000Z\",\n      \"createdAt\": \"2026-06-20T09:00:00.000Z\",\n      \"stats\": {\n        \"gotIt\": 7,\n        \"missed\": 1\n      }\n    },\n    {\n      \"id\": \"card-5\",\n      \"front\": \"bass clef, bottom line\",\n      \"back\": \"G2\",\n      \"box\": 3,\n      \"lastReviewedAt\": \"2026-07-15T18:00:00.000Z\",\n      \"createdAt\": \"2026-06-20T09:00:00.000Z\",\n      \"stats\": {\n        \"gotIt\": 7,\n        \"missed\": 1\n      }\n    },\n    {\n      \"id\": \"card-6\",\n      \"front\": \"C up to A\",\n      \"back\": \"major sixth\",\n      \"box\": 1,\n      \"lastReviewedAt\": \"2026-07-15T18:00:00.000Z\",\n      \"createdAt\": \"2026-06-20T09:00:00.000Z\",\n      \"stats\": {\n        \"gotIt\": 1,\n        \"missed\": 7\n      }\n    },\n    {\n      \"id\": \"card-7\",\n      \"front\": \"E up to B flat\",\n      \"back\": \"diminished fifth (tritone)\",\n      \"box\": 1,\n      \"lastReviewedAt\": \"2026-07-15T18:00:00.000Z\",\n      \"createdAt\": \"2026-06-20T09:00:00.000Z\",\n      \"stats\": {\n        \"gotIt\": 1,\n        \"missed\": 7\n      }\n    },\n    {\n      \"id\": \"card-8\",\n      \"front\": \"F up to D flat\",\n      \"back\": \"minor sixth\",\n      \"box\": 1,\n      \"lastReviewedAt\": \"2026-07-15T18:00:00.000Z\",\n      \"createdAt\": \"2026-06-20T09:00:00.000Z\",\n      \"stats\": {\n        \"gotIt\": 1,\n        \"missed\": 7\n      }\n    },\n    {\n      \"id\": \"card-9\",\n      \"front\": \"G up to F\",\n      \"back\": \"minor seventh\",\n      \"box\": 1,\n      \"lastReviewedAt\": \"2026-07-15T18:00:00.000Z\",\n      \"createdAt\": \"2026-06-20T09:00:00.000Z\",\n      \"stats\": {\n        \"gotIt\": 1,\n        \"missed\": 7\n      }\n    },\n    {\n      \"id\": \"card-10\",\n      \"front\": \"B up to F sharp\",\n      \"back\": \"perfect fifth\",\n      \"box\": 1,\n      \"lastReviewedAt\": \"2026-07-15T18:00:00.000Z\",\n      \"createdAt\": \"2026-06-20T09:00:00.000Z\",\n      \"stats\": {\n        \"gotIt\": 1,\n        \"missed\": 7\n      }\n    },\n    {\n      \"id\": \"card-11\",\n      \"front\": \"key with 3 sharps\",\n      \"back\": \"A major / F sharp minor\",\n      \"box\": 1,\n      \"lastReviewedAt\": \"2026-07-15T18:00:00.000Z\",\n      \"createdAt\": \"2026-06-20T09:00:00.000Z\",\n      \"stats\": {\n        \"gotIt\": 2,\n        \"missed\": 6\n      }\n    },\n    {\n      \"id\": \"card-12\",\n      \"front\": \"key with 4 flats\",\n      \"back\": \"A flat major / F minor\",\n      \"box\": 1,\n      \"lastReviewedAt\": \"2026-07-15T18:00:00.000Z\",\n      \"createdAt\": \"2026-06-20T09:00:00.000Z\",\n      \"stats\": {\n        \"gotIt\": 2,\n        \"missed\": 6\n      }\n    },\n    {\n      \"id\": \"card-13\",\n      \"front\": \"key with 5 sharps\",\n      \"back\": \"B major / G sharp minor\",\n      \"box\": 1,\n      \"lastReviewedAt\": \"2026-07-15T18:00:00.000Z\",\n      \"createdAt\": \"2026-06-20T09:00:00.000Z\",\n      \"stats\": {\n        \"gotIt\": 2,\n        \"missed\": 6\n      }\n    },\n    {\n      \"id\": \"card-14\",\n      \"front\": \"key with 2 flats\",\n      \"back\": \"B flat major / G minor\",\n      \"box\": 1,\n      \"lastReviewedAt\": \"2026-07-15T18:00:00.000Z\",\n      \"createdAt\": \"2026-06-20T09:00:00.000Z\",\n      \"stats\": {\n        \"gotIt\": 2,\n        \"missed\": 6\n      }\n    },\n    {\n      \"id\": \"card-15\",\n      \"front\": \"key with 6 flats\",\n      \"back\": \"G flat major / E flat minor\",\n      \"box\": 1,\n      \"lastReviewedAt\": \"2026-07-15T18:00:00.000Z\",\n      \"createdAt\": \"2026-06-20T09:00:00.000Z\",\n      \"stats\": {\n        \"gotIt\": 2,\n        \"missed\": 6\n      }\n    },\n    {\n      \"id\": \"card-16\",\n      \"front\": \"dotted quarter note in 4/4\",\n      \"back\": \"1.5 beats\",\n      \"box\": 2,\n      \"lastReviewedAt\": \"2026-07-15T18:00:00.000Z\",\n      \"createdAt\": \"2026-06-20T09:00:00.000Z\",\n      \"stats\": {\n        \"gotIt\": 5,\n        \"missed\": 1\n      }\n    },\n    {\n      \"id\": \"card-17\",\n      \"front\": \"how many sixteenths in a half note\",\n      \"back\": \"8\",\n      \"box\": 2,\n      \"lastReviewedAt\": \"2026-07-15T18:00:00.000Z\",\n      \"createdAt\": \"2026-06-20T09:00:00.000Z\",\n      \"stats\": {\n        \"gotIt\": 5,\n        \"missed\": 1\n      }\n    },\n    {\n      \"id\": \"card-18\",\n      \"front\": \"6/8 feels in\",\n      \"back\": \"two (compound duple)\",\n      \"box\": 2,\n      \"lastReviewedAt\": \"2026-07-15T18:00:00.000Z\",\n      \"createdAt\": \"2026-06-20T09:00:00.000Z\",\n      \"stats\": {\n        \"gotIt\": 5,\n        \"missed\": 1\n      }\n    },\n    {\n      \"id\": \"card-19\",\n      \"front\": \"triplet eighths over one beat\",\n      \"back\": \"3 evenly\",\n      \"box\": 2,\n      \"lastReviewedAt\": \"2026-07-15T18:00:00.000Z\",\n      \"createdAt\": \"2026-06-20T09:00:00.000Z\",\n      \"stats\": {\n        \"gotIt\": 5,\n        \"missed\": 1\n      }\n    },\n    {\n      \"id\": \"card-20\",\n      \"front\": \"whole rest lasts\",\n      \"back\": \"a full measure\",\n      \"box\": 2,\n      \"lastReviewedAt\": \"2026-07-15T18:00:00.000Z\",\n      \"createdAt\": \"2026-06-20T09:00:00.000Z\",\n      \"stats\": {\n        \"gotIt\": 5,\n        \"missed\": 1\n      }\n    }\n  ],\n  \"dueCardIds\": [],\n  \"updatedAt\": \"2026-07-18T08:00:00.000Z\"\n}\n"
+      }
+    ],
+    "worker": {
+      "name": "Fenna",
+      "role": "Study coach"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "drill.html is a short interactive drill over only the record's weak material (intervals, key signatures); report.md ranks the weak spots with numbers and schedules the follow-up.",
+    "deliverables": [
+      {
+        "path": "drill.html",
+        "kind": "html-page",
+        "minBytes": 2000,
+        "checks": [
+          {
+            "kind": "jsParses",
+            "file": "drill.html"
+          },
+          {
+            "kind": "cssMinBytes",
+            "bytes": 400,
+            "file": "drill.html"
+          },
+          {
+            "kind": "contains",
+            "file": "drill.html",
+            "pattern": "interval|sixth|tritone|fifth|seventh",
+            "flags": "i",
+            "label": "weak interval material drilled"
+          },
+          {
+            "kind": "contains",
+            "file": "drill.html",
+            "pattern": "key signature|sharps|flats",
+            "flags": "i",
+            "label": "weak key-signature material drilled"
+          },
+          {
+            "kind": "judge",
+            "file": "drill.html",
+            "rubric": "The drill items target only the material the review record marks weak (intervals and key signatures — box 1, missed-heavy); material the record marks strong stays out, and each item comes at the idea from a fresh angle rather than repeating a card verbatim.",
+            "sourceFiles": [
+              "deck.json"
+            ],
+            "label": "targeting"
+          }
+        ]
+      },
+      {
+        "path": "report.md",
+        "kind": "markdown-report",
+        "minBytes": 800,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "review|schedule|next",
+            "flags": "i",
+            "label": "follow-up scheduled"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "\\d",
+            "label": "the evidence has numbers"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "drill.html",
+      "kind": "html"
+    },
+    "axes": [
+      {
+        "name": "targeting",
+        "description": "Every drill item traces to a card the record marks weak; strong material stays out — a generic whole-deck quiz misses the point."
+      },
+      {
+        "name": "difficulty calibration",
+        "description": "Items come at the weak ideas from fresh angles at a level that stretches without drowning."
+      },
+      {
+        "name": "encouragement",
+        "description": "Feedback coaches rather than scolds — right answers explained, misses met warmly."
+      },
+      {
+        "name": "follow-up",
+        "description": "The plan restates the evidence, schedules re-runs and re-reviews, and defines when a spot counts as closed."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "evidence-based targeting",
+    "on-the-spot feedback",
+    "closure criteria"
+  ]
+}

package/data/craftbook-templates/we/web-app-crud/versions/1.0.1/craftbook.json

@@ -0,0 +1,143 @@
+{
+  "id": "web-app-crud",
+  "name": "CRUD Web App",
+  "description": "Build a small single-file CRUD web app — a todo list, notes, contacts, or inventory manager — with create, read, update, and delete plus localStorage persistence so data survives a reload. Locks the data model and the four operations first, then a clean list-plus-form UI design, then builds vanilla JS with real state and persistence. CRUD apps fail when delete or edit silently does nothing or data vanishes on reload, so the model phase pins every operation's behavior before coding, the ordering that gets a small model to a genuinely working app.\n\nA gallery craftbook generated from an archetype spec. It runs\n`phase → (per-phase gate) → … → evaluate → (loop) → finish`. Each build\nphase that produces a checkable artifact is followed by a **runtime\ngate-checkpoint** — the runtime verifies the artifact and routes with no\nmodel turn, looping back to redo the phase on a miss. The final `evaluate`\nstep holds a static deliverable gate plus a reviewer QA pass. What it adds\nover the generic `build-loop`: a specialist role per phase, a\ndomain-correct ordering, and a concrete per-phase quality bar.\n\nDeliverables marked \"artifact\" land in the project's artifacts drawer (`write_artifact` / `read_artifact`), not the shipped workspace — review output is not product source.\n\nPhases:\n\n1. Model scope (planner) — entity fields + the four CRUD operations → gated on artifact `notes/model-scope.md` (markdown-notes)\n2. UI design (designer) — list + form layout, item states, empty state → gated on artifact `notes/ui-design.md` (markdown-notes)\n3. Build (developer) — implement index.html with full CRUD + persistence → gated on `index.html` (html-page)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "model-scope",
+  "triggers": [
+    "crud app",
+    "todo app",
+    "notes app",
+    "build a web app",
+    "contacts manager",
+    "inventory app"
+  ],
+  "steps": [
+    {
+      "id": "model-scope",
+      "name": "Model scope",
+      "description": "entity fields + the four CRUD operations",
+      "prompt": "Pin the data model and operations. (1) Define the entity and its fields (e.g. todo: id, text, done, createdAt) and any validation (required fields). (2) Specify each operation precisely: Create (form -> new record), Read (list/render, any sort/filter), Update (edit in place or via form), Delete (with confirm?). (3) Decide persistence: localStorage key and shape; data must survive reload. (4) Note empty-state behavior. (5) Write an acceptance-criteria checklist of 6-8 items, e.g. 'adding creates a visible item', 'editing updates the item', 'deleting removes it', 'data persists across reload', 'invalid input is rejected', 'an empty-state message shows when there are no items', 'no console errors'. Write to notes/model-scope.md and via write_task_note. No design or HTML yet.\n\nThe deliverable `notes/model-scope.md` lands in the project's artifacts drawer — write it with `write_artifact` and read it back with `read_artifact`; the shipped workspace stays untouched.",
+      "suggestedRole": "planner",
+      "advanceWhen": {
+        "file": "notes/model-scope.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "notes/model-scope.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "notes/model-scope.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "model-scope",
+        "maxAttempts": 3
+      },
+      "next": "ui-design"
+    },
+    {
+      "id": "ui-design",
+      "name": "UI design",
+      "description": "list + form layout, item states, empty state",
+      "prompt": "Design the app UI. (1) Pick a clean palette (hex) and type. (2) Lay out the input/add form and the item list; specify how each item renders with its edit and delete affordances. (3) Design the editing state (inline field or modal) and the confirm-delete interaction. (4) Design the empty state and any filter/sort controls. (5) Self-contained CSS, responsive, no external assets. Write the visual spec to notes/ui-design.md and via write_task_note. No HTML yet.\n\nThe deliverable `notes/ui-design.md` lands in the project's artifacts drawer — write it with `write_artifact` and read it back with `read_artifact`; the shipped workspace stays untouched.",
+      "suggestedRole": "designer",
+      "advanceWhen": {
+        "file": "notes/ui-design.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "notes/ui-design.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "notes/ui-design.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "ui-design",
+        "maxAttempts": 3
+      },
+      "next": "build"
+    },
+    {
+      "id": "build",
+      "name": "Build",
+      "description": "implement index.html with full CRUD + persistence",
+      "prompt": "Implement index.html with inline CSS/JS to the model and UI spec. (1) Keep an in-memory array of records, hydrated from localStorage on load. (2) Create: validate then push and re-render. (3) Read: render the list (with empty state) and any sort/filter. (4) Update: edit a record in place and re-render. (5) Delete: remove (with confirm if specified) and re-render. (6) Persist to localStorage on every mutation so a reload restores state. Vanilla JS, no CDN. On a loop-back, fix only the named gaps without regressing passing criteria. write_task_note the path and passing criteria.",
+      "suggestedRole": "developer",
+      "advanceWhen": {
+        "file": "index.html",
+        "minBytes": 1,
+        "sniff": "html-complete"
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "index.html",
+            "bytes": 800
+          },
+          {
+            "kind": "htmlLint",
+            "file": "index.html"
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkHtmlComplete",
+            "scope": "standard",
+            "inputs": {
+              "file": "index.html"
+            }
+          }
+        ],
+        "onReject": "build",
+        "maxAttempts": 4
+      },
+      "next": "evaluate"
+    },
+    {
+      "id": "evaluate",
+      "name": "Evaluate",
+      "description": "Grade the deliverable against every acceptance criterion. All pass → finish; any fail → loop back and fix the gap.",
+      "prompt": "Exercise every operation. Open index.html if possible, add/edit/delete items, then RELOAD the page. Check EACH criterion from notes/model-scope.md and write PASS/FAIL with a reason: does add create a visible item, does edit update it, does delete remove it, does data persist across reload, is invalid input rejected, does the empty state show, zero console errors? The reload-persistence and the delete are the make-or-break checks — if either fails, FAIL and loop back to build.\n\nThen route — this is the whole point of the loop:\n\n- **Every criterion PASSES →** call `advance_task_step({ ref, stepId: \"evaluate\", next: \"finish\" })`.\n- **Any criterion FAILS →** write the specific gaps to notes, then call `advance_task_step({ ref, stepId: \"evaluate\", next: \"build\" })` to loop back. The builder fixes exactly those gaps.\n\nNever route to `finish` while any criterion is unmet. The build phase's completion gate already blocked a grossly-incomplete deliverable; your job is the judgment an automated check cannot make (does it actually work, read well, look right). After ~3 unproductive loops, stop and report DONE_WITH_CONCERNS so the user can step in.",
+      "suggestedRole": "reviewer",
+      "consumes": [
+        {
+          "file": "index.html"
+        }
+      ],
+      "next": "build"
+    },
+    {
+      "id": "finish",
+      "name": "Finish",
+      "description": "All acceptance criteria met. Stamp a short summary and report DONE.",
+      "prompt": "Every acceptance criterion passed. Write a one-paragraph DONE summary to task notes via `write_task_note`: what was built, the deliverable path(s), and a one-line confirmation that each criterion is met. Then report DONE.",
+      "suggestedRole": "developer",
+      "terminal": true
+    }
+  ],
+  "version": "1.0.1",
+  "releasedAt": "2026-08-14T00:00:00Z"
+}

package/data/craftbook-templates/we/web-app-crud/versions/1.0.1/test.json

@@ -0,0 +1,97 @@
+{
+  "schemaVersion": 1,
+  "title": "CRUD Web App smoke eval",
+  "objective": "Self-contained smoke eval for the CRUD Web App craftbook using the html-page generic harness.",
+  "tags": [
+    "html-page"
+  ],
+  "prompt": "Can you biuld us a little page for this? The content notes are in source/page-content.md. Save it as index.html — one file, nothing fancy needed on our end.",
+  "setup": {
+    "projectName": "CRUD Web App Eval",
+    "about": "Self-contained eval project for web-app-crud. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/index.html.",
+    "missionObjectives": "Use the CRUD Web App craftbook/template, read the seeded local fixtures, and write index.html without network calls, real credentials, or live services.",
+    "files": [
+      {
+        "path": "source/brief.md",
+        "content": "# CRUD Web App Eval Brief\n\nClient: Boreal Desk, a home-office accessories company.\nAudience: operations leads who need an artifact they can use this week.\n\nFixed source facts for grounding:\n- The returns desk pilot covered 18 SKUs.\n- Median first response improved from 18 hours to 6 hours.\n- Preventable refund leakage fell from 14.2% to 8.9%.\n- The top unresolved complaint is status silence after photo submission.\n- Required next actions are automated status emails, barcode-exception training, and a weekly Finance exception export.\n\nUse these facts when the task asks for prose, analysis, copy, UI content, or test data. Do not use live web services, real credentials, or current outside data.\n\nCraftbook under test: web-app-crud - CRUD Web App.\n"
+      },
+      {
+        "path": "source/page-content.md",
+        "content": "# Boreal Desk Support Board\n\nBuild content around a support operations board. Required labels: Open issues, Status silence, Response time, Refund leakage, Next action. Required metric text: 18 hours to 6 hours and 14.2% to 8.9%.\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Developer"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "index.html is a source-grounded self-contained HTML page/tool.",
+    "deliverables": [
+      {
+        "path": "index.html",
+        "kind": "html-page",
+        "minBytes": 3000,
+        "checks": [
+          {
+            "kind": "cssMinBytes",
+            "bytes": 650,
+            "file": "index.html"
+          },
+          {
+            "kind": "jsParses",
+            "file": "index.html"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "Boreal|Support Board|returns",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "18\\s*hours|6\\s*hours|14\\.2%|8\\.9%",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "button|input|filter|tab|card|section|nav",
+            "flags": "i"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "index.html",
+      "kind": "html"
+    },
+    "axes": [
+      {
+        "name": "structure",
+        "description": "Layout and hierarchy fit the content; sections are scannable and coherent."
+      },
+      {
+        "name": "grounding",
+        "description": "Seeded source content is used faithfully — no invented facts or dropped requirements."
+      },
+      {
+        "name": "interactivity",
+        "description": "Controls and states the page claims to offer actually work."
+      },
+      {
+        "name": "polish",
+        "description": "Styling is intentional and responsive rather than unstyled or broken."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "self-contained UI",
+    "source grounding",
+    "responsive structure"
+  ]
+}