@bendyline/gilde 0.1.37 → 0.1.39

package/data/craftbook-templates/re/reception-report/versions/1.0.1/test.json

@@ -0,0 +1,169 @@
+{
+  "schemaVersion": 1,
+  "title": "Weekly reception review with a reconciliation gap",
+  "objective": "Prove that reception-report stamps the missing corpusRef onto a published post, builds a ledger covering every published post, and writes a grounded report with exactly one next-post action.",
+  "tags": [
+    "corpus"
+  ],
+  "prompt": "Run the Reception Report craftbook for this project. Treat every synced record in the artifacts drawer as inside the review window (the lookback parameter is set very wide for this eval). One published post — returns-faq — is missing its corpusRef; reconcile it against the synced records, build the reception ledger covering all three published posts, and write the weekly reception report with its single one-click next-post action.",
+  "setup": {
+    "projectName": "Reception Report Eval",
+    "about": "Weekly reception review eval for a small furniture workshop's Bluesky presence. Three published posts sit in the workspace posts tree — one missing its corpusRef — and their live records with engagement counts sit in the artifacts drawer.",
+    "missionObjectives": "Reconcile posts/2026-08-08-returns-faq/variants/bluesky.md with its live record (stamp corpusRef), build tasks/eval/reports/reception-ledger.md covering summer-sale, behind-the-scenes, and returns-faq with verbatim counts, analyze against the account baseline, and write the reception report with exactly one gezel-action block firing draft-social-post.",
+    "files": [
+      {
+        "path": "posts/index.json",
+        "content": "{\n  \"entries\": [\n    {\n      \"slug\": \"summer-sale\",\n      \"folder\": \"posts/2026-07-28-summer-sale\",\n      \"title\": \"Summer sale on seconds\",\n      \"status\": \"published\",\n      \"platforms\": [\"bluesky\"],\n      \"created\": \"2026-07-28\"\n    },\n    {\n      \"slug\": \"behind-the-scenes\",\n      \"folder\": \"posts/2026-08-03-behind-the-scenes\",\n      \"title\": \"Behind the scenes at the bench\",\n      \"status\": \"published\",\n      \"platforms\": [\"bluesky\"],\n      \"created\": \"2026-08-03\"\n    },\n    {\n      \"slug\": \"returns-faq\",\n      \"folder\": \"posts/2026-08-08-returns-faq\",\n      \"title\": \"Your returns questions, answered\",\n      \"status\": \"published\",\n      \"platforms\": [\"bluesky\"],\n      \"created\": \"2026-08-08\"\n    }\n  ]\n}\n"
+      },
+      {
+        "path": "posts/2026-07-28-summer-sale/post.md",
+        "content": "---\nstatus: published\ntitle: Summer sale on seconds\nslug: summer-sale\nplatforms: [bluesky]\ncreated: 2026-07-28\ntags: [sale]\n---\nSeconds shelf is full: benches and boxes with honest scars, priced to leave. Ends Sunday.\n"
+      },
+      {
+        "path": "posts/2026-07-28-summer-sale/variants/bluesky.md",
+        "content": "---\nplatform: bluesky\ncharCount: 96\nstatus: published\npublishedAt: 2026-07-28T09:00:00Z\npostId: at://did:plc:bankenbeitel/app.bsky.feed.post/3ksale001\npermalink: https://bsky.app/profile/bankenbeitel.bsky.social/post/3ksale001\ncorpusRef: data/bluesky/posts/2026-07/2026-07-28-summer-sale.md\n---\nSeconds shelf is full: benches and boxes with honest scars, priced to leave. Ends Sunday.\n"
+      },
+      {
+        "path": "posts/2026-08-03-behind-the-scenes/post.md",
+        "content": "---\nstatus: published\ntitle: Behind the scenes at the bench\nslug: behind-the-scenes\nplatforms: [bluesky]\ncreated: 2026-08-03\ntags: [workshop]\n---\nWhat a Tuesday actually looks like here: glue squeeze-out, sharpening breaks, and the radio arguing with itself.\n"
+      },
+      {
+        "path": "posts/2026-08-03-behind-the-scenes/variants/bluesky.md",
+        "content": "---\nplatform: bluesky\ncharCount: 113\nstatus: published\npublishedAt: 2026-08-03T10:30:00Z\npostId: at://did:plc:bankenbeitel/app.bsky.feed.post/3kbts0001\npermalink: https://bsky.app/profile/bankenbeitel.bsky.social/post/3kbts0001\ncorpusRef: data/bluesky/posts/2026-08/2026-08-03-behind-the-scenes.md\n---\nWhat a Tuesday actually looks like here: glue squeeze-out, sharpening breaks, and the radio arguing with itself.\n"
+      },
+      {
+        "path": "posts/2026-08-08-returns-faq/post.md",
+        "content": "---\nstatus: published\ntitle: Your returns questions, answered\nslug: returns-faq\nplatforms: [bluesky]\ncreated: 2026-08-08\ntags: [returns]\n---\nYour returns questions, answered: what the new desk takes back, how long it takes, and what needs no receipt.\n"
+      },
+      {
+        "path": "posts/2026-08-08-returns-faq/variants/bluesky.md",
+        "content": "---\nplatform: bluesky\ncharCount: 109\nstatus: published\npublishedAt: 2026-08-08T09:15:00Z\npostId: at://did:plc:bankenbeitel/app.bsky.feed.post/3kfaq0001\npermalink: https://bsky.app/profile/bankenbeitel.bsky.social/post/3kfaq0001\n---\nYour returns questions, answered: what the new desk takes back, how long it takes, and what needs no receipt.\n"
+      },
+      {
+        "path": "data/bluesky/_meta.json",
+        "surface": "artifact",
+        "content": "{\n  \"bindingId\": \"bluesky-workshop\",\n  \"typeId\": \"bluesky-posts\",\n  \"displayName\": \"Bluesky — @bankenbeitel.bsky.social\",\n  \"completeness\": \"window\",\n  \"lastSyncedAt\": \"2026-08-12T05:00:00Z\"\n}\n"
+      },
+      {
+        "path": "data/bluesky/posts/2026-07/2026-07-28-summer-sale.md",
+        "surface": "artifact",
+        "content": "---\nrecord: post\nplatform: bluesky\npostId: at://did:plc:bankenbeitel/app.bsky.feed.post/3ksale001\npermalink: https://bsky.app/profile/bankenbeitel.bsky.social/post/3ksale001\nauthor: bankenbeitel.bsky.social\ncreatedAt: 2026-07-28T09:00:00Z\nlikes: 18\nreposts: 3\nreplies: 2\nmetrics_updated_at: 2026-08-12T05:00:00Z\n---\nSeconds shelf is full: benches and boxes with honest scars, priced to leave. Ends Sunday.\n"
+      },
+      {
+        "path": "data/bluesky/posts/2026-08/2026-08-03-behind-the-scenes.md",
+        "surface": "artifact",
+        "content": "---\nrecord: post\nplatform: bluesky\npostId: at://did:plc:bankenbeitel/app.bsky.feed.post/3kbts0001\npermalink: https://bsky.app/profile/bankenbeitel.bsky.social/post/3kbts0001\nauthor: bankenbeitel.bsky.social\ncreatedAt: 2026-08-03T10:30:00Z\nlikes: 57\nreposts: 21\nreplies: 9\nmetrics_updated_at: 2026-08-12T05:00:00Z\n---\nWhat a Tuesday actually looks like here: glue squeeze-out, sharpening breaks, and the radio arguing with itself.\n"
+      },
+      {
+        "path": "data/bluesky/posts/2026-08/2026-08-08-returns-faq.md",
+        "surface": "artifact",
+        "content": "---\nrecord: post\nplatform: bluesky\npostId: at://did:plc:bankenbeitel/app.bsky.feed.post/3kfaq0001\npermalink: https://bsky.app/profile/bankenbeitel.bsky.social/post/3kfaq0001\nauthor: bankenbeitel.bsky.social\ncreatedAt: 2026-08-08T09:15:00Z\nlikes: 24\nreposts: 6\nreplies: 11\nmetrics_updated_at: 2026-08-12T05:00:00Z\n---\nYour returns questions, answered: what the new desk takes back, how long it takes, and what needs no receipt.\n"
+      }
+    ],
+    "craftbookParams": {
+      "lookbackDays": "3650",
+      "workPath": "tasks/eval"
+    },
+    "worker": {
+      "name": "Sten",
+      "role": "Omroeper"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "The returns-faq variant gained its corpusRef, the ledger covers all three published posts with verbatim counts, and the reception report at its stable path carries exactly one gezel-action block firing draft-social-post.",
+    "checks": [
+      {
+        "kind": "contains",
+        "file": "posts/2026-08-08-returns-faq/variants/bluesky.md",
+        "pattern": "corpusRef:",
+        "label": "the missing corpusRef was reconciled"
+      },
+      {
+        "kind": "minBytes",
+        "file": "tasks/eval/reports/reception-ledger.md",
+        "bytes": 150,
+        "artifact": true
+      },
+      {
+        "kind": "contains",
+        "file": "tasks/eval/reports/reception-ledger.md",
+        "pattern": "summer-sale",
+        "label": "ledger covers summer-sale",
+        "artifact": true
+      },
+      {
+        "kind": "contains",
+        "file": "tasks/eval/reports/reception-ledger.md",
+        "pattern": "behind-the-scenes",
+        "label": "ledger covers behind-the-scenes",
+        "artifact": true
+      },
+      {
+        "kind": "contains",
+        "file": "tasks/eval/reports/reception-ledger.md",
+        "pattern": "returns-faq",
+        "label": "ledger covers returns-faq",
+        "artifact": true
+      },
+      {
+        "kind": "minBytes",
+        "file": "tasks/eval/reports/reception-report-latest.md",
+        "bytes": 400,
+        "artifact": true
+      },
+      {
+        "kind": "contains",
+        "file": "tasks/eval/reports/reception-report-latest.md",
+        "pattern": "```gezel-action",
+        "label": "report carries the next-post action",
+        "artifact": true
+      },
+      {
+        "kind": "contains",
+        "file": "tasks/eval/reports/reception-report-latest.md",
+        "pattern": "craftbookId: draft-social-post",
+        "label": "the action fires draft-social-post",
+        "artifact": true
+      }
+    ],
+    "taskGraph": {
+      "requireCraftbookTask": true,
+      "requireTerminalStep": true
+    },
+    "unchangedFixtures": [
+      "posts/index.json",
+      "posts/2026-07-28-summer-sale/post.md",
+      "posts/2026-07-28-summer-sale/variants/bluesky.md",
+      "posts/2026-08-03-behind-the-scenes/post.md",
+      "posts/2026-08-03-behind-the-scenes/variants/bluesky.md",
+      "posts/2026-08-08-returns-faq/post.md"
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "tasks/eval/reports/reception-report-latest.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "grounding",
+        "description": "No metric appears in the report that is absent from the ledger; the ledger counts match the seeded records verbatim (18/3/2, 57/21/9, 24/6/11)."
+      },
+      {
+        "name": "insight",
+        "description": "The findings read the data honestly: behind-the-scenes over-performed, returns-faq drew reply-heavy engagement, and small-sample caveats are stated."
+      },
+      {
+        "name": "actionability",
+        "description": "Exactly one gezel-action block, valid flat YAML with a stable id, firing draft-social-post with a topic seeded from the strongest theme."
+      }
+    ],
+    "contextNote": "Only the returns-faq bluesky variant should gain frontmatter this run; the other seeded post files stay byte-identical. The report is an artifacts-drawer file."
+  },
+  "qualityFocus": [
+    "reconciliation touches only the variant missing corpusRef",
+    "ledger counts copied verbatim from records",
+    "exactly one next-post action, never inventing craftbook ids"
+  ]
+}

package/data/craftbook-templates/re/recipe-capture/versions/1.0.2/craftbook.json

@@ -0,0 +1,152 @@
+{
+  "id": "recipe-capture",
+  "name": "Capture a Recipe Card",
+  "description": "Rescue a handwritten recipe card without sanding off its soul: transcribe the original faithfully — spelling quirks, margin notes, and all — standardize quantities in a separate block alongside (never instead of) the original wording, and pin the provenance note: whose card, whose kitchen, what they always changed. Locks the capture rules FIRST, then captures each card into the book, then logs what needs a test-cook and what to ask the family. Use for capturing recipe cards, 'get oma's cards into the book', preserving family recipes, and recipe transcription.\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. Scope the capture (kitchen-master) — card intake notes read, capture rules locked → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. Capture the cards (archivist) — one faithful recipe file per card, recorded in the book → gated on artifact `{{workPath}}/capture.md` (markdown-notes)\n3. Write the capture log (copywriter) — what went in, what needs a test-cook, questions for the family → gated on artifact `{{workPath}}/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": [
+    "capture a recipe card",
+    "get this recipe into the book",
+    "transcribe oma's card",
+    "add a family recipe",
+    "preserve this recipe"
+  ],
+  "steps": [
+    {
+      "id": "scope",
+      "name": "Scope the capture",
+      "description": "card intake notes read, capture rules locked",
+      "prompt": "Define the capture before transcribing a word. Step 1: read the card intake notes waiting in inbox/ and the recipe book's store (recipes.json) — what is already in the book and how entries are shaped. Step 2: lock the capture rules — the original wording is preserved exactly, spelling quirks, margin notes and all; every recipe carries its provenance (whose card, whose kitchen, what they always changed); the standardized ingredients-and-steps block sits alongside the original text, clearly separated, never replacing it; anything unreadable becomes a question, not a guess. Step 3: write an acceptance-criteria checklist ('every card captured as its own recipe file under recipes/', 'original text verbatim with margin notes kept and marked', 'provenance line on every recipe', 'standardized block separate from the original', 'each captured recipe recorded in the book's store'). Call write_task_note with the card count + rules + checklist and write {{workPath}}/scope.md.\n\nThe deliverable `{{workPath}}/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": "kitchen-master",
+      "advanceWhen": {
+        "file": "{{workPath}}/scope.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/scope.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/scope.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "scope",
+        "maxAttempts": 3
+      },
+      "next": "capture"
+    },
+    {
+      "id": "capture",
+      "name": "Capture the cards",
+      "description": "one faithful recipe file per card, recorded in the book",
+      "prompt": "Capture each card against the locked rules. Step 1: for every card note in inbox/, write a recipe file under recipes/ — a title, the provenance line, the original text transcribed faithfully (margin notes included and marked as margin notes), and then a clearly separated standardized block with an Ingredients list and numbered steps. Step 2: record each captured recipe in the book's store through the project's recipe capabilities — title, provenance, and the file it lives in. Step 3: where the card is ambiguous or unreadable, keep the original as written and add the question inline rather than smoothing it over. Step 4: write a per-card capture log to {{workPath}}/capture.md — what was captured, what was preserved as-is, what needs asking. Call write_task_note with the captured count.\n\nThe deliverable `{{workPath}}/capture.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": "archivist",
+      "advanceWhen": {
+        "file": "{{workPath}}/capture.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/capture.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/capture.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "capture",
+        "maxAttempts": 3
+      },
+      "next": "report"
+    },
+    {
+      "id": "report",
+      "name": "Write the capture log",
+      "description": "what went in, what needs a test-cook, questions for the family",
+      "prompt": "Write the capture log for the family from your notes. Step 1: list what went into the book this session — each recipe with whose card it was. Step 2: name what needs a test-cook before it counts as verified, and why (an ambiguous quantity, a step that assumes the cook's hands already knew). Step 3: list the questions for the family — margin notes worth explaining, names and dates worth pinning down — so the next phone call captures them. Step 4: keep it warm; this is family history in food form. Write {{workPath}}/report.md and call write_task_note with the captured count and the top question.\n\nThe deliverable `{{workPath}}/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": "copywriter",
+      "advanceWhen": {
+        "file": "{{workPath}}/report.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/report.md",
+            "bytes": 800,
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "{{workPath}}/report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i",
+            "label": "at least one markdown heading",
+            "artifact": true
+          }
+        ],
+        "onReject": "report",
+        "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 {{workPath}}/report.md, {{workPath}}/capture.md, and the recipe files under recipes/ and verify every criterion from {{workPath}}/scope.md: every inbox card became its own recipe file, the original wording is verbatim (spot-check phrases against the card notes — no silent corrections), margin notes survived and are marked as such, every recipe carries a provenance line, the standardized block is present and separate from the original, and each captured recipe is recorded in the book's store. Write PASS/FAIL per criterion; on any failure, name the gap and loop back to capture.\n\nThe deliverable lives in the project's artifacts drawer — open `{{workPath}}/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: \"capture\" })` 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": "{{workPath}}/report.md",
+          "artifact": true
+        }
+      ],
+      "next": "capture"
+    },
+    {
+      "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": "1.0.2",
+  "releasedAt": "2026-08-21T00:00:00Z",
+  "paramSchema": {
+    "type": "object",
+    "properties": {
+      "workPath": {
+        "type": "string",
+        "title": "Working folder",
+        "description": "Per-task working folder in the artifacts drawer. Defaults to this task's own folder so runs never collide; override with a stable name when you deliberately want runs to share files.",
+        "default": "{{task.dir}}"
+      }
+    }
+  },
+  "minGezelVersion": "1.26233"
+}

package/data/craftbook-templates/re/recipe-capture/versions/1.0.2/test.json

@@ -0,0 +1,131 @@
+{
+  "schemaVersion": 1,
+  "title": "Capture a Recipe Card smoke eval",
+  "objective": "Task-specific eval for the Capture a Recipe Card craftbook: two pre-extracted card scans become faithful recipe files with provenance and a separate standardized block, recorded in the book's store.",
+  "tags": [
+    "corpus"
+  ],
+  "prompt": "scanned two of omas cards — the transcriptions are in inbox/card-1.txt and inbox/card-2.txt. can you get them into the book propperly?",
+  "setup": {
+    "projectName": "Family Recipe Book — Card Capture Eval",
+    "about": "Self-contained eval project for recipe-capture. The card photos have already been pre-extracted into plain-text scan notes under inbox/ (the text as written, plus margin notes). Captured recipes go under recipes/ and are recorded in recipes.json; the capture log goes to tasks/eval/report.md.",
+    "missionObjectives": "Use the Capture a Recipe Card craftbook/template, work only from the seeded card notes, and finish with the recipe files, an updated recipes.json, and tasks/eval/report.md — no network calls, real credentials, or live services.",
+    "files": [
+      {
+        "path": "inbox/card-1.txt",
+        "content": "CARD SCAN NOTE (pre-extracted from photo card-1.jpg)\n\nTitle on card: Appelkoek\nHandwriting: Oma Riet's, blue ink, grease spot lower right corner\n\nText as written:\n'2 kopjes flour, 150 g butter (cold!), 3/4 kopje brown sugar, 2 apples - the sour ones, 1 tsp cinnamon, pinch of salt. Rub butter into flour. Sugar, then apples in thin slices. Oven: hot, until it smells right, about 40 min.'\n\nMargin note, pencil, different hand: 'she always used twice the butter'\n"
+      },
+      {
+        "path": "inbox/card-2.txt",
+        "content": "CARD SCAN NOTE (pre-extracted from photo card-2.jpg)\n\nTitle on card: Speculaas\nHandwriting: Oma Riet's, black ink, top corner torn\n\nText as written:\n'250 g flour, 125 g cold butter, 100 g dark brown sugar, 2 tbsp speculaaskruiden, 3 tbsp milk, pinch salt. Knead, rest overnight (cold). Roll thin. Oven 160 for 20-25 min.'\n\nMargin note, same hand: 'St Nicolaas - double batch'\n"
+      },
+      {
+        "path": "recipes.json",
+        "content": "[]\n"
+      }
+    ],
+    "worker": {
+      "name": "Bep",
+      "role": "Archivist"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "Both cards become recipe files under recipes/ with provenance kept beside the food, the store records each capture, and the log flags what needs a test-cook.",
+    "deliverables": [
+      {
+        "path": "tasks/eval/report.md",
+        "kind": "markdown-report",
+        "minBytes": 500,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "Oma|Riet",
+            "label": "provenance carried into the capture log"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "\\?",
+            "label": "questions for the family are actually asked"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "test[- ]?cook|try (it|the)|verify",
+            "flags": "i",
+            "label": "test-cook needs named"
+          }
+        ]
+      }
+    ],
+    "checks": [
+      {
+        "kind": "fileCount",
+        "ext": [
+          "md"
+        ],
+        "min": 2,
+        "dir": "recipes"
+      },
+      {
+        "kind": "recordSchema",
+        "file": "recipes.json",
+        "fields": [
+          {
+            "name": "title",
+            "type": "nonempty"
+          },
+          {
+            "name": "provenance",
+            "type": "nonempty"
+          },
+          {
+            "name": "file",
+            "type": "nonempty"
+          }
+        ],
+        "minRows": 2
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "tasks/eval/report.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "provenance",
+        "description": "Every recipe names whose card it was, and the margin notes survive, marked as margin notes."
+      },
+      {
+        "name": "fidelity",
+        "description": "Original wording and quantities are transcribed exactly — no silent corrections or smoothing."
+      },
+      {
+        "name": "standardization",
+        "description": "A clear standardized ingredients-and-steps block sits alongside, never replacing, the original."
+      },
+      {
+        "name": "warmth",
+        "description": "The capture log reads like family history in food form, not a data-entry receipt."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "verbatim transcription",
+    "provenance preservation",
+    "original-versus-standardized separation"
+  ]
+}

package/data/craftbook-templates/re/record-a-relative/versions/1.0.2/craftbook.json

@@ -0,0 +1,127 @@
+{
+  "id": "record-a-relative",
+  "name": "Record a Relative",
+  "description": "Bank an elder's interview while the telling is fresh: file the transcript, pull the people, places, and dates into the family record with their source, and write the follow-up questions — because the questions you didn't ask are the ones that vanish. Locks the extraction rules FIRST (every fact carries its quote, uncertain stays uncertain), then files the transcript, then updates the tree and surfaces the conflicts. Use for filing a family interview, recording a relative's stories, pulling facts into the tree, and 'we interviewed grandma'.\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. Scope the extraction (genealogist) — target branch, extraction rules, fact-sourcing checklist → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. File the transcript (archivist) — speaker-labeled transcript with a header, under interviews/\n3. Extract the facts (genealogist) — facts with quotes into the tree, conflicts surfaced, follow-ups → gated on artifact `{{workPath}}/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": [
+    "file the interview with oma",
+    "we interviewed grandma",
+    "pull the family facts from the transcript",
+    "record a relative",
+    "bank the elder interview"
+  ],
+  "steps": [
+    {
+      "id": "scope",
+      "name": "Scope the extraction",
+      "description": "target branch, extraction rules, fact-sourcing checklist",
+      "prompt": "Aim the interview at the tree before extracting a single fact. Step 1: read tree.json from the workspace — the people, the branches, the facts already recorded and the ones marked uncertain. Step 2: identify the relative who was interviewed and which branch facts this interview can confirm, correct, or newly supply. Step 3: lock the extraction rules — every fact carries the teller's quote or the transcript line behind it; a fact that conflicts with the tree is surfaced as a conflict, never silently overwritten; uncertain stays uncertain ('she thought it was 1954' is recorded as thought, not fact). Step 4: write the acceptance-criteria checklist from those rules, plus 'the transcript is filed under interviews/' and 'follow-up questions written for the gaps the interview opened'. Call write_task_note with the relative + target branch + checklist and write {{workPath}}/scope.md.\n\nThe deliverable `{{workPath}}/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": "genealogist",
+      "advanceWhen": {
+        "file": "{{workPath}}/scope.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/scope.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/scope.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "scope",
+        "maxAttempts": 3
+      },
+      "next": "file"
+    },
+    {
+      "id": "file",
+      "name": "File the transcript",
+      "description": "speaker-labeled transcript with a header, under interviews/",
+      "prompt": "Get the interview on file where the family can find it in fifty years. Step 1: if a transcript file was provided, start from it; otherwise produce one from the recording through the project's transcription capabilities. Step 2: label the speakers and add a header — who was interviewed, by whom, when and where. Step 3: save it in the interviews/ folder named for the relative and the date (for example interviews/oma-2026-07.md). Keep the telling verbatim — the phrasing is part of the record. Step 4: call write_task_note with the path.",
+      "suggestedRole": "archivist",
+      "next": "extract"
+    },
+    {
+      "id": "extract",
+      "name": "Extract the facts",
+      "description": "facts with quotes into the tree, conflicts surfaced, follow-ups",
+      "prompt": "Pull the facts into the record with their sources. Step 1: walk the transcript and list every person, place, date, and event it attests — each with the quote behind it. Step 2: compare against tree.json: which facts confirm the tree, which are new, and which conflict with what is recorded — update the tree through the project's family-record capabilities for confirmations and additions, and surface every conflict for the owner instead of picking a winner. Step 3: write {{workPath}}/report.md: the facts captured (each with its quote), the conflicts with the existing tree stated plainly, and the follow-up questions to ask while asking is still possible. Step 4: call write_task_note with the fact count, the conflict count, and the top follow-up question.\n\nThe deliverable `{{workPath}}/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": "genealogist",
+      "advanceWhen": {
+        "file": "{{workPath}}/report.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/report.md",
+            "bytes": 1200,
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "{{workPath}}/report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i",
+            "label": "at least one markdown heading",
+            "artifact": true
+          }
+        ],
+        "onReject": "extract",
+        "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 {{workPath}}/report.md beside the interview transcript and tree.json and verify every criterion from {{workPath}}/scope.md: every fact in the report carries a quote that actually appears in the transcript (spot-check five — a quote that isn't there is fabrication), every date and name in the report exists in the transcript or the tree, conflicts with the tree are surfaced as conflicts rather than silently resolved, uncertain memories are recorded as uncertain, and the follow-up questions are real questions aimed at real gaps. Write PASS/FAIL per criterion; on any failure, name the gap and loop back to extract.\n\nThe deliverable lives in the project's artifacts drawer — open `{{workPath}}/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: \"extract\" })` 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": "{{workPath}}/report.md",
+          "artifact": true
+        }
+      ],
+      "next": "extract"
+    },
+    {
+      "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": "1.0.2",
+  "releasedAt": "2026-08-21T00:00:00Z",
+  "paramSchema": {
+    "type": "object",
+    "properties": {
+      "workPath": {
+        "type": "string",
+        "title": "Working folder",
+        "description": "Per-task working folder in the artifacts drawer. Defaults to this task's own folder so runs never collide; override with a stable name when you deliberately want runs to share files.",
+        "default": "{{task.dir}}"
+      }
+    }
+  },
+  "minGezelVersion": "1.26233"
+}