@bendyline/gilde 0.1.51 → 0.1.52

package/data/craftbook-templates/en/engineering-retrospective/versions/2.0.5/test.json

@@ -0,0 +1,191 @@
+{
+  "schemaVersion": 1,
+  "title": "Engineering Retrospective — queue reliability window",
+  "objective": "Exercise the Engineering Retrospective craftbook on a fixed exported history and require reconciled metrics, contextual interpretation, balanced growth notes, and owned experiments.",
+  "tags": [
+    "workflow",
+    "retrospective",
+    "engineering",
+    "corpus"
+  ],
+  "prompt": "Use the Engineering Retrospective craftbook for the fixed 2026-07-01 through 2026-07-14 window. This evaluation has no live git repository: `source/git-log.txt` and `source/numstat.tsv` are the authoritative read-only exports, and `source/team-events.md` supplies context. Do not treat unavailable live history as zero or ask for another window. Reconcile human activity, exclude the release bot, identify evidence-backed hotspots and quality/collaboration signals, and write the workflow artifacts ending at `retro/engineering-retrospective.md`. Include constructive notes for Alex Kim and Priya Shah without rankings or volume-as-productivity claims, then propose three to five owner-backed experiments with measurable outcomes and a review date.",
+  "setup": {
+    "projectName": "Queue reliability engineering retrospective",
+    "about": "A self-contained retrospective over exported repository evidence. The export and context files are complete; no network, live git repository, or personnel system is available.",
+    "missionObjectives": "Run the Engineering Retrospective craftbook as a real task, reconcile the fixed history, preserve evidence limits, and produce an actionable, fair retrospective.",
+    "files": [
+      {
+        "path": "source/git-log.txt",
+        "content": "# sha|date|author|email|subject\na1c001|2026-07-02|Alex Kim|alex@example.test|fix queue timeout classification\na1c002|2026-07-03|Priya Shah|priya@example.test|add queue retry metrics\na1c003|2026-07-06|Priya Shah|priya@example.test|document on-call queue recovery\na1c004|2026-07-09|Alex Kim|alex@example.test|cover refresh-token expiry\na1c005|2026-07-10|Alex Kim|alex@example.test|add queue timeout regression fixture\na1c006|2026-07-12|Priya Shah|priya@example.test|pin parser dependency after advisory review\na1c007|2026-07-14|release-bot|bot@example.test|release 2.8.0\n"
+      },
+      {
+        "path": "source/numstat.tsv",
+        "content": "sha\tadded\tdeleted\tpath\na1c001\t34\t12\tsrc/queue.ts\na1c001\t22\t0\ttests/queue.test.ts\na1c002\t28\t4\tsrc/queue.ts\na1c002\t40\t2\tsrc/metrics.ts\na1c003\t55\t3\tdocs/oncall.md\na1c004\t18\t7\tsrc/auth.ts\na1c004\t26\t0\ttests/auth.test.ts\na1c005\t12\t6\tsrc/queue.ts\na1c005\t31\t2\ttests/queue.test.ts\na1c006\t3\t3\tpackage.json\na1c006\t14\t14\tpnpm-lock.yaml\na1c007\t2\t2\tCHANGELOG.md\n"
+      },
+      {
+        "path": "source/team-events.md",
+        "content": "# Team context\n\n- Window: 2026-07-01 through 2026-07-14, UTC. Compare only within this window; no prior baseline export is available.\n- Queue retry incident on 2026-07-02 caused delayed job status for 41 minutes. Priya Shah was primary responder; Alex Kim traced the timeout classification the next morning.\n- Alex was on planned leave July 4-5.\n- Priya paired with Alex on the queue regression fixture; pairing is mentioned in commit a1c005 but the export cannot attribute line-level co-authorship.\n- Release-bot is automation and must not be included in human activity or growth notes.\n- Review comments, meetings, and off-repository operational work are not present in this export.\n- Experiments should be reviewed on 2026-07-28.\n"
+      }
+    ]
+  },
+  "mocks": [],
+  "success": {
+    "summary": "The real craftbook reconciles the exported history into a contextual, non-ranking retrospective with balanced growth notes and measurable experiments.",
+    "deliverables": [
+      {
+        "path": "retro/scope.md",
+        "kind": "markdown-notes",
+        "minBytes": 600,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "retro/scope.md",
+            "pattern": "2026-07-01[\\s\\S]*2026-07-14[\\s\\S]*(Alex Kim|alex@example\\.test)[\\s\\S]*(Priya Shah|priya@example\\.test)[\\s\\S]*(release-bot|automation)",
+            "flags": "i",
+            "label": "window, identity map, and bot exclusion"
+          }
+        ]
+      },
+      {
+        "path": "retro/evidence.md",
+        "kind": "markdown-report",
+        "minBytes": 1100,
+        "checks": [
+          {
+            "kind": "valueGrounding",
+            "file": "retro/evidence.md",
+            "facts": [
+              {
+                "id": "human-commits",
+                "label": "six human commits",
+                "required": [
+                  "6\\s+human\\s+commits?|six\\s+human\\s+commits?"
+                ]
+              },
+              {
+                "id": "bot-exclusion",
+                "label": "one excluded bot commit",
+                "required": [
+                  "1\\s+(?:bot|automated)|one\\s+(?:bot|automated)"
+                ]
+              },
+              {
+                "id": "alex-count",
+                "label": "three Alex commits",
+                "required": [
+                  "Alex(?: Kim)?[^\\n]{0,80}3"
+                ]
+              },
+              {
+                "id": "priya-count",
+                "label": "three Priya commits",
+                "required": [
+                  "Priya(?: Shah)?[^\\n]{0,80}3"
+                ]
+              },
+              {
+                "id": "hotspot",
+                "label": "queue file changed in three commits",
+                "required": [
+                  "src/queue\\.ts[^\\n]{0,100}3|3[^\\n]{0,100}src/queue\\.ts"
+                ]
+              }
+            ]
+          },
+          {
+            "kind": "citationsResolve",
+            "file": "retro/evidence.md",
+            "minCitations": 3
+          }
+        ]
+      },
+      {
+        "path": "retro/engineering-retrospective.md",
+        "kind": "markdown-report",
+        "minBytes": 1600,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "retro/engineering-retrospective.md",
+            "pattern": "^#{1,3}\\s+Period context\\b[\\s\\S]*^#{1,3}\\s+What went well\\b[\\s\\S]*^#{1,3}\\s+Friction and hotspots\\b[\\s\\S]*^#{1,3}\\s+Collaboration and growth\\b[\\s\\S]*^#{1,3}\\s+Experiments\\b[\\s\\S]*^#{1,3}\\s+Evidence limits\\b",
+            "flags": "im",
+            "label": "complete retrospective structure"
+          },
+          {
+            "kind": "contains",
+            "file": "retro/engineering-retrospective.md",
+            "pattern": "Alex Kim[\\s\\S]*Priya Shah|Priya Shah[\\s\\S]*Alex Kim",
+            "label": "balanced named growth notes"
+          },
+          {
+            "kind": "contains",
+            "file": "retro/engineering-retrospective.md",
+            "pattern": "2026-07-28[\\s\\S]*(owner|Alex|Priya)|(owner|Alex|Priya)[\\s\\S]*2026-07-28",
+            "flags": "i",
+            "label": "owned experiments with review date"
+          },
+          {
+            "kind": "notContains",
+            "file": "retro/engineering-retrospective.md",
+            "pattern": "top performer|bottom performer|most productive|least productive|performance score|rank(?:ed|ing)?\\s+(?:the\\s+)?(?:engineers|people|team)",
+            "flags": "i",
+            "label": "no personnel ranking or volume-as-productivity framing"
+          },
+          {
+            "kind": "citationsResolve",
+            "file": "retro/engineering-retrospective.md",
+            "minCitations": 3
+          }
+        ]
+      }
+    ],
+    "taskNotes": {
+      "minBytes": 180,
+      "checks": [
+        {
+          "kind": "contains",
+          "file": "task-notes.md",
+          "pattern": "\\bDONE\\b[\\s\\S]*retro/engineering-retrospective\\.md[\\s\\S]*(experiment|evidence)",
+          "flags": "i",
+          "label": "terminal note records the evidence-backed retrospective"
+        }
+      ],
+      "requireCraftbookTask": true
+    },
+    "taskGraph": {
+      "requireCraftbookTask": true,
+      "requireTerminalStep": true
+    },
+    "unchangedFixtures": [
+      "source/git-log.txt",
+      "source/numstat.tsv",
+      "source/team-events.md"
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "retro/engineering-retrospective.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "Evidence integrity",
+        "description": "Counts reconcile to the exports, bot activity is excluded, hotspots are traceable, and missing review or operational data is not treated as zero."
+      },
+      {
+        "name": "Context and fairness",
+        "description": "The incident, leave, pairing, and evidence limits shape interpretation; individual notes are constructive and do not rank people by volume."
+      },
+      {
+        "name": "Actionability",
+        "description": "The retrospective turns patterns into a small set of owner-backed, measurable experiments with a fixed review date."
+      }
+    ],
+    "contextNote": "The three source exports are the complete evidence set. Do not reward invented review metrics, cycle time, or off-repository work."
+  },
+  "qualityFocus": [
+    "Reconcile six human commits and exclude release automation",
+    "Explain the queue hotspot in incident context without equating volume with value",
+    "Give Alex and Priya balanced growth notes and measurable experiments"
+  ]
+}

package/data/craftbook-templates/ep/episode-plan/versions/1.0.3/craftbook.json

@@ -0,0 +1,277 @@
+{
+  "id": "episode-plan",
+  "name": "Plan the Episode",
+  "description": "Turn the idea backlog and last episode's loose threads into a locked plan for the next episode: a rundown with timed segments, what to prep, and a record date — so the show ships on rhythm instead of on adrenaline. Locks the episode goal and the acceptance checklist FIRST, then builds the timed rundown, then writes the brief with prep owners and the record date. Use for planning the next episode, episode rundowns, show planning, and 'what's the next episode'.\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 episode (planner) — backlog picture, episode goal, plan rules → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. Build the rundown (producer) — timed segments, per-segment needs, open questions → gated on artifact `{{workPath}}/rundown.md` (markdown-notes)\n3. Write the episode brief (copywriter) — title options, final rundown, prep list with owners, record date → 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": [
+    "plan the next episode",
+    "episode plan",
+    "what's our next episode",
+    "plan next week's show",
+    "episode rundown"
+  ],
+  "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}}"
+      }
+    }
+  },
+  "steps": [
+    {
+      "id": "scope",
+      "name": "Scope the episode",
+      "description": "backlog picture, episode goal, plan rules",
+      "prompt": "Define the episode before anything gets produced. Step 1: read episodes.json from the workspace — the idea backlog, the publishing cadence, the last few shipped episodes and any loose threads or listener notes they left behind. Step 2: confirm with the owner which idea leads the next episode and what the episode is FOR — the one thing a listener should take away. Step 3: set the plan rules — target length, the segment shape the show uses, guests or clips that need lead time, and the record date that keeps the cadence. Step 4: write an acceptance-criteria checklist ('every segment has a minute mark and a purpose', 'segment minutes add up to the target length', 'every prep item has an owner and a by-date', 'the record date beats the publish date', 'loose threads from last episode are picked up or consciously dropped'). Call write_task_note with the chosen idea + record date + 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": "planner",
+      "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": "rundown",
+      "toolPolicy": {
+        "disallowBuiltinToolsets": [
+          "ai-apps",
+          "archives",
+          "audio",
+          "browser-automation",
+          "code-execution",
+          "craftbooks",
+          "data-tables",
+          "entity-intel",
+          "git",
+          "image-intel",
+          "images",
+          "role-delegation",
+          "role-delegation-escalation",
+          "security-intel",
+          "team-management",
+          "videos",
+          "web",
+          "workspace-fs-write"
+        ],
+        "outputMedium": "artifact",
+        "additionalOutputMedia": [
+          "task-note"
+        ]
+      }
+    },
+    {
+      "id": "rundown",
+      "name": "Build the rundown",
+      "description": "timed segments, per-segment needs, open questions",
+      "prompt": "Build the rundown against the locked goal. Step 1: draft the segment list — cold open to outro — with a minute mark and a one-line purpose per segment. Step 2: for each segment, note what it needs: a guest, a clip, research, an ad read, or nothing but the host. Step 3: check the math — segment minutes must add up to the target length, with the big segment where the energy belongs. Step 4: list the open questions the owner must answer before record day. Step 5: write the full rundown to {{workPath}}/rundown.md and call write_task_note with the segment count and the total minutes.\n\nThe deliverable `{{workPath}}/rundown.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": "producer",
+      "advanceWhen": {
+        "file": "{{workPath}}/rundown.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/rundown.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/rundown.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "rundown",
+        "maxAttempts": 3
+      },
+      "next": "report",
+      "toolPolicy": {
+        "disallowBuiltinToolsets": [
+          "ai-apps",
+          "archives",
+          "audio",
+          "browser-automation",
+          "code-execution",
+          "craftbooks",
+          "data-tables",
+          "entity-intel",
+          "git",
+          "image-intel",
+          "images",
+          "role-delegation",
+          "role-delegation-escalation",
+          "security-intel",
+          "team-management",
+          "videos",
+          "web",
+          "workspace-fs-write"
+        ],
+        "outputMedium": "artifact",
+        "additionalOutputMedia": [
+          "task-note"
+        ]
+      }
+    },
+    {
+      "id": "report",
+      "name": "Write the episode brief",
+      "description": "title options, final rundown, prep list with owners, record date",
+      "prompt": "Write the episode brief from the rundown. Step 1: open with the episode goal and two or three title options that would make the target listener stop scrolling. Step 2: lay out the final rundown — every segment with its minute mark and purpose. Step 3: write the prep list — each item with an owner and a by-date, ordered by lead time, longest first. Step 4: state the record date and the publish date it protects. Step 5: keep it one page, warm and specific — this is the sheet the host glances at before hitting record. Write {{workPath}}/report.md and call write_task_note with the report path and the record date.\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": 1500,
+            "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",
+      "toolPolicy": {
+        "disallowBuiltinToolsets": [
+          "ai-apps",
+          "archives",
+          "audio",
+          "browser-automation",
+          "code-execution",
+          "craftbooks",
+          "data-tables",
+          "entity-intel",
+          "git",
+          "image-intel",
+          "images",
+          "role-delegation",
+          "role-delegation-escalation",
+          "security-intel",
+          "team-management",
+          "videos",
+          "web",
+          "workspace-fs-write"
+        ],
+        "outputMedium": "artifact",
+        "additionalOutputMedia": [
+          "task-note"
+        ]
+      }
+    },
+    {
+      "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 and {{workPath}}/rundown.md and verify every criterion from {{workPath}}/scope.md: every segment carries a minute mark and a purpose, the minutes add up to the target length, every prep item names an owner and a by-date, the record date is set and beats the publish date, and last episode's loose threads are picked up or consciously dropped. Cross-check the brief against episodes.json — the chosen idea must come from the backlog or the owner, never from thin air. Write PASS/FAIL per criterion; on any failure, name the gap and loop back to report.\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: \"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}}/report.md",
+          "artifact": true
+        }
+      ],
+      "next": "report",
+      "toolPolicy": {
+        "disallowBuiltinToolsets": [
+          "ai-apps",
+          "archives",
+          "audio",
+          "browser-automation",
+          "code-execution",
+          "craftbooks",
+          "data-tables",
+          "entity-intel",
+          "git",
+          "image-intel",
+          "images",
+          "role-delegation",
+          "role-delegation-escalation",
+          "security-intel",
+          "team-management",
+          "videos",
+          "web",
+          "workspace-fs-write"
+        ],
+        "outputMedium": "task-note"
+      }
+    },
+    {
+      "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,
+      "toolPolicy": {
+        "disallowBuiltinToolsets": [
+          "ai-apps",
+          "archives",
+          "artifacts",
+          "audio",
+          "browser-automation",
+          "code-execution",
+          "craftbooks",
+          "data-tables",
+          "entity-intel",
+          "git",
+          "image-intel",
+          "images",
+          "role-delegation",
+          "role-delegation-escalation",
+          "security-intel",
+          "team-management",
+          "videos",
+          "web",
+          "workspace-fs-write"
+        ],
+        "outputMedium": "task-note"
+      }
+    }
+  ],
+  "version": "1.0.3",
+  "releasedAt": "2026-09-01T20:00:00Z",
+  "minGezelVersion": "1.26233"
+}

package/data/craftbook-templates/ep/episode-plan/versions/1.0.3/test.json

@@ -0,0 +1,100 @@
+{
+  "schemaVersion": 1,
+  "title": "Plan the Episode — backlog to locked rundown",
+  "objective": "Measure whether the episode-plan craftbook turns a seeded episode store and listener feedback into a locked episode brief with a timed rundown, prep owners, and a record date.",
+  "tags": [
+    "corpus"
+  ],
+  "prompt": "Can you plan next weeks episode? our running notes are in episodes.json and there's listener feedback in source/feedback.md — plan into tasks/eval/report.md",
+  "setup": {
+    "projectName": "Shelf Life Podcast",
+    "about": "Podcast studio project for Shelf Life, a weekly show about books and the people who make them. The episode store is workspace/episodes.json; listener feedback lands under workspace/source.",
+    "missionObjectives": "Keep the show shipping on its weekly rhythm. Plans are grounded in the episode store and listener feedback — no live services, no real credentials.",
+    "files": [
+      {
+        "path": "episodes.json",
+        "content": "{\n  \"show\": \"Shelf Life\",\n  \"cadence\": \"weekly — records Thursday, publishes Monday\",\n  \"targetMinutes\": 45,\n  \"episodes\": [\n    {\n      \"number\": 10,\n      \"title\": \"The Library Cart Economy\",\n      \"publishedAt\": \"2026-06-29\",\n      \"looseThreads\": [\"listener mail about mobile libraries never answered on air\"]\n    },\n    {\n      \"number\": 11,\n      \"title\": \"Why Paperbacks Survive\",\n      \"publishedAt\": \"2026-07-06\",\n      \"looseThreads\": [\"promised a follow-up on print-on-demand costs\"]\n    },\n    {\n      \"number\": 12,\n      \"title\": \"Interview: The Last Bookbinder\",\n      \"publishedAt\": \"2026-07-13\",\n      \"looseThreads\": [\"the bookbinder offered to come back with her apprentice\"]\n    }\n  ],\n  \"ideaBacklog\": [\n    {\n      \"idea\": \"Print-on-demand: the real costs\",\n      \"tasks/eval\": \"pairs with the episode 11 follow-up promise; host has the numbers already\"\n    },\n    {\n      \"idea\": \"School libraries after the budget cuts\",\n      \"tasks/eval\": \"needs a guest — two weeks lead time minimum\"\n    },\n    {\n      \"idea\": \"Audiobook narrators nobody credits\",\n      \"tasks/eval\": \"evergreen, no lead time, host can carry it solo\"\n    }\n  ]\n}\n"
+      },
+      {
+        "path": "source/feedback.md",
+        "content": "# Listener feedback — week of 2026-07-13\n\n- \"You promised the print-on-demand cost breakdown two episodes ago. Still waiting!\" — Sam R., email\n- \"The bookbinder interview was the best episode this year. More craftspeople please.\" — review\n- \"Episodes have been running long lately. 45 minutes is the sweet spot.\" — voicemail\n- \"Whatever happened to the mobile libraries question from the mailbag?\" — Discord\n"
+      }
+    ],
+    "worker": {
+      "name": "Fenna",
+      "role": "Producer"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "tasks/eval/report.md is a one-page episode brief: title options, a rundown with minute marks, a prep list with owners, and a record date — grounded in the backlog and the feedback.",
+    "deliverables": [
+      {
+        "path": "tasks/eval/report.md",
+        "kind": "markdown-report",
+        "minBytes": 1500,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "segment|rundown",
+            "flags": "i",
+            "label": "rundown present"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "\\d{1,2}\\s*(min|:)",
+            "flags": "i",
+            "label": "minute marks on segments"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "prep|before record",
+            "flags": "i",
+            "label": "prep list present"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "tasks/eval/report.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "structure",
+        "description": "The brief reads as one page a host can glance at before recording: goal, titles, timed rundown, prep list, record date."
+      },
+      {
+        "name": "grounding",
+        "description": "The chosen episode comes from the idea backlog and the loose threads; the listener feedback visibly shaped the plan."
+      },
+      {
+        "name": "actionability",
+        "description": "Prep items carry owners and by-dates; segment minutes add up to the target length."
+      },
+      {
+        "name": "tone",
+        "description": "Warm and specific — a producer's brief, not a form."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "backlog grounding",
+    "timed rundown",
+    "prep ownership"
+  ]
+}