@bendyline/gilde 0.1.38 → 0.1.39

package/data/craftbook-templates/in/interactive-quiz/versions/1.0.2/craftbook.json

@@ -0,0 +1,155 @@
+{
+  "id": "interactive-quiz",
+  "name": "Interactive Quiz Widget",
+  "description": "Build a single-file interactive quiz or assessment — multiple-choice, true/false, or a scored personality quiz — that asks questions one at a time, tracks the score, gives feedback, and shows a results screen. Authors the question bank, answer keys, and scoring logic first, designs the question and results UI, then implements stateful question flow with correct scoring. Quizzes break when the score is miscounted or the results screen never appears, so the content phase locks the answer key and the score-to-result mapping before any markup.\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. Content (planner) — question bank, answer keys, scoring + results → gated on artifact `{{workPath}}/content.md` (markdown-notes)\n2. Design (designer) — question card, option states, results layout → gated on artifact `{{workPath}}/design.md` (markdown-notes)\n3. Build (developer) — implement index.html with question flow + scoring → 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": "content",
+  "triggers": [
+    "quiz app",
+    "make a quiz",
+    "trivia game",
+    "assessment widget",
+    "personality quiz",
+    "multiple choice quiz"
+  ],
+  "steps": [
+    {
+      "id": "content",
+      "name": "Content",
+      "description": "question bank, answer keys, scoring + results",
+      "prompt": "Author the quiz content. (1) Write the questions with their options and mark the correct answer(s) for each (the answer key) — for a scored personality quiz, map options to point buckets instead. (2) Define the scoring rule (one point per correct, or weighted) and the score-to-result mapping (e.g. 0-3 = beginner, 4-7 = ...). (3) Decide flow: one question per screen, whether to show immediate per-question feedback, and progress. (4) Define the results screen content. (5) Write an acceptance-criteria checklist of 5-8 items, e.g. 'each question shows its options', 'selecting an answer advances or enables Next', 'the score counts correct answers accurately', 'a progress indicator updates', 'the results screen shows the final score and the mapped result', 'a restart resets the quiz', 'no console errors'. Write to {{workPath}}/content.md and via write_task_note. No HTML yet.\n\nThe deliverable `{{workPath}}/content.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": "{{workPath}}/content.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/content.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/content.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "content",
+        "maxAttempts": 3
+      },
+      "next": "design"
+    },
+    {
+      "id": "design",
+      "name": "Design",
+      "description": "question card, option states, results layout",
+      "prompt": "Design the quiz UI. (1) Pick a friendly palette (hex) and type. (2) Design the question card: question text, option buttons, and selected/correct/incorrect states (if showing feedback). (3) Design the progress indicator and the Next/submit affordance. (4) Design the results screen with the score and mapped outcome and a restart button. (5) Self-contained CSS, responsive. Write the visual spec to {{workPath}}/design.md and via write_task_note. No HTML yet.\n\nThe deliverable `{{workPath}}/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": "{{workPath}}/design.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/design.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/design.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "design",
+        "maxAttempts": 3
+      },
+      "next": "build"
+    },
+    {
+      "id": "build",
+      "name": "Build",
+      "description": "implement index.html with question flow + scoring",
+      "prompt": "Implement index.html with inline CSS/JS to the content and design. (1) Hold the question bank, the current index, and the score in state. (2) Render the current question and options; on selection, record the answer, update the score per the rule, show feedback if specified, and advance (or enable Next). (3) Update the progress indicator each question. (4) After the last question, render the results screen with the accurate final score and the mapped result. (5) Wire a restart that resets index and score. 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": "Take the quiz twice — once all-correct, once all-wrong. Open index.html if possible, else trace the scoring. Check EACH criterion from {{workPath}}/content.md and write PASS/FAIL with a reason: do questions show options, does selecting advance, is the score counted ACCURATELY (all-correct = max, all-wrong = min), does progress update, does the results screen show the right score and mapped result, does restart reset, zero console errors? A miscounted score is a FAIL — 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": "1.0.2",
+  "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/in/interactive-quiz/versions/1.0.2/test.json

@@ -0,0 +1,102 @@
+{
+  "schemaVersion": 1,
+  "title": "Interactive Quiz Widget smoke eval",
+  "objective": "Self-contained smoke eval for the Interactive Quiz Widget craftbook using the html-game generic harness.",
+  "tags": [
+    "html-game"
+  ],
+  "prompt": "Make us a fun litle browser game around the returns-desk theme — just one file, index.html, that we can open and play.",
+  "setup": {
+    "projectName": "Interactive Quiz Widget Eval",
+    "about": "Self-contained eval project for interactive-quiz. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/index.html.",
+    "missionObjectives": "Use the Interactive Quiz Widget 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": "# Interactive Quiz Widget 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: interactive-quiz - Interactive Quiz Widget.\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Developer"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "index.html is a complete self-contained browser game smoke artifact.",
+    "deliverables": [
+      {
+        "path": "index.html",
+        "kind": "html-game",
+        "minBytes": 3200,
+        "checks": [
+          {
+            "kind": "cssMinBytes",
+            "bytes": 600,
+            "file": "index.html"
+          },
+          {
+            "kind": "jsParses",
+            "file": "index.html"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "<canvas|<svg|requestAnimationFrame",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "score|state|level|turn",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "restart|play again|new game|game over|victory|you win|you lose",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "Boreal|returns|desk",
+            "flags": "i"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "index.html",
+      "kind": "html"
+    },
+    "axes": [
+      {
+        "name": "playability",
+        "description": "The game is actually playable: input works, state advances, and a session can be completed."
+      },
+      {
+        "name": "completeness",
+        "description": "Core loop, scoring/win-lose, and restart are all present rather than stubbed."
+      },
+      {
+        "name": "polish",
+        "description": "Visual design and feedback (motion, states, messages) feel deliberate, not default."
+      },
+      {
+        "name": "robustness",
+        "description": "No console errors, dead controls, or states the player can get stuck in."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "runtime surface",
+    "interaction loop",
+    "self-contained game"
+  ]
+}

package/data/craftbook-templates/in/investigate-root-cause/versions/1.0.2/craftbook.json

@@ -0,0 +1,153 @@
+{
+  "id": "investigate-root-cause",
+  "name": "Root-Cause Investigation",
+  "description": "Debug a defect or production incident down to its true root cause and document the diagnosis with evidence, instead of patching the first symptom. First reproduces the failure reliably and locks what 'understood' means (a confirmed repro, the failing assertion, the exact trigger condition), then narrows the cause by forming and testing hypotheses, bisecting, reading stack traces and logs, and tracing the data path until one hypothesis is proven, then writes a root-cause report with the evidence chain, the smallest fix, and how to prevent recurrence. Use this for debugging, root-cause analysis, investigating a bug or flaky test, diagnosing an incident, or figuring out why something breaks — it produces a proven cause backed by evidence, not a guess.\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. Reproduce & scope (reviewer) — get a reliable repro, lock what 'understood' means → gated on artifact `{{workPath}}/reproduce.md` (markdown-notes)\n2. Narrow the cause (reviewer) — form + test hypotheses until one is proven → gated on artifact `{{workPath}}/narrow.md` (markdown-notes)\n3. Write the root-cause report (reviewer) — diagnosis, evidence chain, smallest fix, prevention → gated on artifact `{{workPath}}/root-cause.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": "reproduce",
+  "triggers": [
+    "investigate this bug",
+    "root cause this",
+    "why is this failing",
+    "debug this",
+    "figure out why it breaks",
+    "diagnose this incident"
+  ],
+  "steps": [
+    {
+      "id": "reproduce",
+      "name": "Reproduce & scope",
+      "description": "get a reliable repro, lock what 'understood' means",
+      "prompt": "Step 1: Capture the symptom precisely — the exact error message, stack trace, failing test, or observed wrong behavior, and the environment it occurs in. Step 2: Establish a RELIABLE reproduction: the minimal steps/inputs that trigger the failure every time. If it is intermittent, note the frequency and any conditions that change it. Step 3: Pin down the boundary — what is the last known-good state (commit, input, version) and the first known-bad state. Step 4: Write an acceptance-criteria checklist for the investigation, e.g. 'the repro triggers the failure deterministically', 'the exact failing line/assertion is identified', 'the cause is proven by evidence, not asserted', 'the proposed fix is the smallest change that resolves the repro'. Step 5: Record the repro steps and the known-good/known-bad boundary to `write_task_note` AND `{{workPath}}/reproduce.md`. No fix yet — confirm you can make it fail on demand first.\n\nThe deliverable `{{workPath}}/reproduce.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": "reviewer",
+      "advanceWhen": {
+        "file": "{{workPath}}/reproduce.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/reproduce.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/reproduce.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "reproduce",
+        "maxAttempts": 3
+      },
+      "next": "narrow"
+    },
+    {
+      "id": "narrow",
+      "name": "Narrow the cause",
+      "description": "form + test hypotheses until one is proven",
+      "prompt": "Step 1: From the repro, list 2-4 concrete hypotheses for the cause, each falsifiable (e.g. 'the input is undefined here', 'the off-by-one is in this index', 'the race is between A and B'). Step 2: Test the cheapest hypothesis first — add logging/asserts, set a breakpoint, bisect the diff (`git bisect` or binary-search the change), or read the implicated code and trace the data path. Step 3: Record what each experiment PROVED or DISPROVED — do not move on from a hypothesis on a hunch; require evidence. Step 4: Iterate until exactly one hypothesis is proven: you can point to the precise line and explain the mechanism (why this input + this code produces this failure). Step 5: Confirm the root cause by predicting a NEW case it explains and verifying that prediction. Good looks like: an evidence chain from symptom → mechanism → root line, not 'I think it is the cache'. Stage the hypothesis log to `write_task_note`. Do not write the final report yet.\n\nThe deliverable `{{workPath}}/narrow.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": "reviewer",
+      "advanceWhen": {
+        "file": "{{workPath}}/narrow.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/narrow.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/narrow.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "narrow",
+        "maxAttempts": 3
+      },
+      "next": "report"
+    },
+    {
+      "id": "report",
+      "name": "Write the root-cause report",
+      "description": "diagnosis, evidence chain, smallest fix, prevention",
+      "prompt": "Step 1: Open `{{workPath}}/root-cause.md` and write a one-paragraph '## Summary' stating the root cause in plain language and where it lives (file:line). Step 2: Add '## Reproduction' with the deterministic repro steps. Step 3: Add '## Evidence' as an ordered chain: symptom → each experiment and its result → the proven mechanism. Step 4: Add '## Fix' describing the SMALLEST change that resolves the repro (and why a smaller/larger fix is wrong), with the diff or exact edit. Step 5: Add '## Prevention' — the test or guard that would have caught this and should be added. Every claim in the evidence chain must be backed by an experiment result, not assertion. On a loop-back, fix only the named gaps. `write_task_note` the report path and the proven root-cause location.\n\nThe deliverable `{{workPath}}/root-cause.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": "reviewer",
+      "advanceWhen": {
+        "file": "{{workPath}}/root-cause.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/root-cause.md",
+            "bytes": 1500,
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "{{workPath}}/root-cause.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}}/root-cause.md` and grade it against the reproduce checklist. Check EACH criterion and write PASS/FAIL with a one-line reason: (1) the reproduction is deterministic and documented; (2) the root cause is pinned to a specific file:line/mechanism, not a vague subsystem; (3) the evidence chain actually proves the cause (each link backed by an experiment result); (4) the proposed fix is the smallest change that addresses the cause and would resolve the repro; (5) a prevention test/guard is specified; (6) the diagnosis is a proven mechanism, not a guess. If any criterion fails, name the exact gap and loop back.\n\nThe deliverable lives in the project's artifacts drawer — open `{{workPath}}/root-cause.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: \"report\" })` 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}}/root-cause.md",
+          "artifact": true
+        }
+      ],
+      "next": "report"
+    },
+    {
+      "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/in/investigate-root-cause/versions/1.0.2/test.json

@@ -0,0 +1,113 @@
+{
+  "schemaVersion": 1,
+  "title": "Root-Cause Investigation smoke eval",
+  "objective": "Self-contained smoke eval for the Root-Cause Investigation craftbook using the corpus generic harness.",
+  "tags": [
+    "corpus"
+  ],
+  "prompt": "We need a root-cause investigation for the returns-desk work. The backgound info is in source/brief.md — have a look and write it up in report.md.",
+  "setup": {
+    "projectName": "Root-Cause Investigation Eval",
+    "about": "Self-contained eval project for investigate-root-cause. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/report.md.",
+    "missionObjectives": "Use the Root-Cause Investigation craftbook/template, read the seeded local fixtures, and write report.md without network calls, real credentials, or live services.",
+    "files": [
+      {
+        "path": "source/brief.md",
+        "content": "# Root-Cause Investigation 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: investigate-root-cause - Root-Cause Investigation.\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Writer"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "report.md is a source-grounded markdown artifact with required facts and actions.",
+    "deliverables": [
+      {
+        "path": "report.md",
+        "kind": "markdown-report",
+        "minBytes": 1000,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "source/brief\\.md|Brief",
+            "flags": "i",
+            "label": "cite or name the seeded source"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "18\\b[\\s\\S]{0,30}\\bSKUs",
+            "flags": "i",
+            "label": "include the 18-SKU pilot scope"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "18\\s*hours|6\\s*hours",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "14\\.2%|8\\.9%",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "status silence|photo submission",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "automated status emails|barcode|Finance",
+            "flags": "i"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "report.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "grounding",
+        "description": "Seeded facts appear faithfully and the source is cited."
+      },
+      {
+        "name": "structure",
+        "description": "Sections progress logically for the artifact class."
+      },
+      {
+        "name": "completeness",
+        "description": "Required elements (risks, next actions, scope) are all present."
+      },
+      {
+        "name": "tone",
+        "description": "The register fits the audience and artifact class."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "source-grounded prose",
+    "section structure",
+    "next-action clarity"
+  ]
+}