@bendyline/gilde 0.1.38 → 0.1.40

package/data/craftbook-templates/we/weekly-menu-plan/versions/1.0.2/craftbook.json

@@ -0,0 +1,152 @@
+{
+  "id": "weekly-menu-plan",
+  "name": "Plan the Week's Dinners",
+  "description": "Turn the pantry's real state into a planned week of dinners and one grocery list: check what is stocked, low, and out, plan seven dinners that use what is on hand and fit the household's tastes and schedule, write the menu onto the week, and produce a grocery list that covers the gaps. Locks the household constraints and the pantry picture FIRST, then plans the menu, then writes the list — so the weekly food question is answered once, on purpose, instead of nightly at 5pm. Use for weekly meal planning, menu planning, grocery list making, and 'what are we eating this week'.\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 week (planner) — pantry picture, household constraints, week shape → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. Plan the menu (chef) — seven dinners against the pantry and the constraints → gated on artifact `{{workPath}}/menu.md` (markdown-notes)\n3. Write the grocery list (copywriter) — one gap-covering list, grouped for the store → 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 week's dinners",
+    "weekly meal plan",
+    "what are we eating this week",
+    "make a grocery list",
+    "menu for the week"
+  ],
+  "steps": [
+    {
+      "id": "scope",
+      "name": "Scope the week",
+      "description": "pantry picture, household constraints, week shape",
+      "prompt": "Define the week before planning a single meal. Step 1: read pantry.json and menu.json from the workspace — what is stocked, what is low or out, and whether any dinners are already set for the week. Step 2: confirm the household constraints with the owner — how many people, dietary lines that cannot be crossed, nights that need a fast meal or no meal (out, leftovers), and anything they are tired of. Step 3: set the planning rules — prefer meals that use stocked and low items before they turn, repeat no main protein two nights running, at most N new-recipe nights. Step 4: write an acceptance-criteria checklist ('all seven nights planned or explicitly marked out/leftovers', 'each dinner names its main ingredients', 'every ingredient not stocked appears on the grocery list', 'the list is grouped for one store walk', 'constraints respected on every night'). Call write_task_note with the pantry gap count + constraints + 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": "plan"
+    },
+    {
+      "id": "plan",
+      "name": "Plan the menu",
+      "description": "seven dinners against the pantry and the constraints",
+      "prompt": "Plan the seven dinners against the locked rules. Step 1: draft the week — a dinner per night, honoring the fast-night and out-night shape, using stocked and low pantry items first. Step 2: for each dinner, list the main ingredients and mark which are on hand versus needed. Step 3: sanity-check variety (proteins, cuisines, effort spread across the week) and swap where it clumps. Step 4: confirm the draft with the owner and adjust. Step 5: write the confirmed menu onto the week through the project's kitchen capabilities (set each day's dinner), write the per-dinner ingredient breakdown to {{workPath}}/menu.md, and call write_task_note with the seven dinners in one line each.\n\nThe deliverable `{{workPath}}/menu.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": "chef",
+      "advanceWhen": {
+        "file": "{{workPath}}/menu.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/menu.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/menu.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "plan",
+        "maxAttempts": 3
+      },
+      "next": "list"
+    },
+    {
+      "id": "list",
+      "name": "Write the grocery list",
+      "description": "one gap-covering list, grouped for the store",
+      "prompt": "Write the grocery list from the menu and the pantry. Step 1: collect every menu ingredient marked needed, plus every pantry item at low or out that the household actually uses. Step 2: dedupe and size the quantities to the week (and note which low staples are worth topping up while there). Step 3: group the list the way a store walks — produce, meat/fish, dairy, dry goods, frozen, household. Step 4: put the week's menu at the top of the page so the list explains itself at the store. Step 5: keep it one page. Write {{workPath}}/report.md and call write_task_note with the item count.\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": "list",
+        "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 and {{workPath}}/menu.md and verify every criterion from {{workPath}}/scope.md: all seven nights are planned or explicitly out/leftovers, each dinner names its main ingredients, every needed ingredient (and every low/out staple in use) appears exactly once on the grocery list, the list is store-grouped, and every night respects the household constraints. Cross-check the written week against the menu store — the days set through the kitchen capabilities must match the report. Write PASS/FAIL per criterion; on any failure, name the gap and loop back to list.\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: \"list\" })` 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": "list"
+    },
+    {
+      "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/we/weekly-menu-plan/versions/1.0.2/test.json

@@ -0,0 +1,100 @@
+{
+  "schemaVersion": 1,
+  "title": "Plan the Week's Dinners smoke eval",
+  "objective": "Self-contained smoke eval for the Plan the Week's Dinners craftbook using the html-page generic harness.",
+  "tags": [
+    "html-page"
+  ],
+  "prompt": "Can you biuld us a little page for this? The content notes are in source/page-content.md. Save it as index.html — one file, nothing fancy needed on our end.",
+  "setup": {
+    "projectName": "Plan the Week's Dinners Eval",
+    "about": "Self-contained eval project for weekly-menu-plan. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/index.html.",
+    "missionObjectives": "Use the Plan the Week's Dinners 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": "# Plan the Week's Dinners 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: weekly-menu-plan - Plan the Week's Dinners.\n"
+      },
+      {
+        "path": "source/page-content.md",
+        "content": "# Boreal Desk Support Board\n\nBuild content around a support operations board. Required labels: Open issues, Status silence, Response time, Refund leakage, Next action. Required metric text: 18 hours to 6 hours and 14.2% to 8.9%.\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Developer"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "index.html is a source-grounded self-contained HTML page/tool.",
+    "deliverables": [
+      {
+        "path": "index.html",
+        "kind": "html-page",
+        "minBytes": 3000,
+        "checks": [
+          {
+            "kind": "cssMinBytes",
+            "bytes": 650,
+            "file": "index.html"
+          },
+          {
+            "kind": "jsParses",
+            "file": "index.html"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "Boreal|Support Board|returns",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "18\\s*hours|6\\s*hours|14\\.2%|8\\.9%",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "button|input|filter|tab|card|section|nav",
+            "flags": "i"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "index.html",
+      "kind": "html"
+    },
+    "axes": [
+      {
+        "name": "structure",
+        "description": "Layout and hierarchy fit the content; sections are scannable and coherent."
+      },
+      {
+        "name": "grounding",
+        "description": "Seeded source content is used faithfully — no invented facts or dropped requirements."
+      },
+      {
+        "name": "interactivity",
+        "description": "Controls and states the page claims to offer actually work."
+      },
+      {
+        "name": "polish",
+        "description": "Styling is intentional and responsive rather than unstyled or broken."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "self-contained UI",
+    "source grounding",
+    "responsive structure"
+  ]
+}

package/data/craftbook-templates/we/weekly-pipeline-review/manifest.json

@@ -3,6 +3,7 @@
   "kind": "craftbook-template",
   "id": "weekly-pipeline-review",
   "role": "maintenance-review",
+  "category": "business",
   "name": "Weekly Pipeline Review",
   "description": "The weekly walk of a job-search pipeline — a grounded snapshot of every application (what moved in the last seven days, what went stale, which follow-ups are due), then a review that chases or consciously parks every stalled item and commits to exactly three concrete priorities for next week. Built for the Job Hunt project's weekly cadence; also runs on demand whenever the pipeline feels foggy.",
   "tags": [

package/data/craftbook-templates/we/weekly-pipeline-review/versions/1.0.2/craftbook.json

@@ -0,0 +1,118 @@
+{
+  "id": "weekly-pipeline-review",
+  "name": "Weekly Pipeline Review",
+  "description": "The weekly walk of a job-search pipeline — a grounded snapshot of every application (what moved in the last seven days, what went stale, which follow-ups are due), then a review that chases or consciously parks every stalled item and commits to exactly three concrete priorities for next week. Built for the Job Hunt project's weekly cadence; also runs on demand whenever the pipeline feels foggy.\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. Snapshot the pipeline (Loopbaancoach) — the grounded state: per-stage counts, movement, staleness, follow-ups due → gated on artifact `{{workPath}}/pipeline-snapshot.md` (markdown-notes)\n2. Write the weekly review (Loopbaancoach) — moved, stalled with unblocking actions, follow-ups, and exactly three priorities → gated on artifact `{{workPath}}/reports/weekly-pipeline-review.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": "snapshot",
+  "triggers": [
+    "weekly pipeline review",
+    "review my job pipeline",
+    "job search weekly review",
+    "where does my search stand"
+  ],
+  "steps": [
+    {
+      "id": "snapshot",
+      "name": "Snapshot the pipeline",
+      "description": "the grounded state: per-stage counts, movement, staleness, follow-ups due",
+      "prompt": "Ground the review in the real record — invent nothing. Step 1: read the live pipeline through the pipeline status capability on your current roster when available; otherwise read the workspace pipeline.json and activity.json records directly. Step 2: snapshot per-stage counts and list every application with its stage and last-touched date. Step 3: mark movement — anything whose stage changed in the last seven days. Step 4: mark staleness — any active application untouched for more than seven days. Step 5: list follow-ups due — logged follow-up events due within the next seven days or overdue. Step 6: note materials debt: serious applications missing a tailored résumé or company brief. Write the snapshot via write_task_note AND to {{workPath}}/pipeline-snapshot.md.\n\nThe deliverable `{{workPath}}/pipeline-snapshot.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": "Loopbaancoach",
+      "advanceWhen": {
+        "file": "{{workPath}}/pipeline-snapshot.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/pipeline-snapshot.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/pipeline-snapshot.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "snapshot",
+        "maxAttempts": 3
+      },
+      "next": "review"
+    },
+    {
+      "id": "review",
+      "name": "Write the weekly review",
+      "description": "moved, stalled with unblocking actions, follow-ups, and exactly three priorities",
+      "prompt": "Write {{workPath}}/reports/weekly-pipeline-review.md from the snapshot. Step 1: '## Moved this week' — each change in one line, celebrated where it deserves it. Step 2: '## Stalled' — every stale item with its unblocking action; the carry-over rule is absolute: each one is explicitly chased, consciously parked with a reason, or closed — nothing is silently dropped. Step 3: '## Follow-ups due' — who, about what, by when. Step 4: '## Materials debt' — tailoring and briefs owed for serious applications. Step 5: '## Next week' — EXACTLY three concrete priorities; three, not ten. Every line must trace to the snapshot. On a loop-back, fix ONLY the named issues.\n\nThe deliverable `{{workPath}}/reports/weekly-pipeline-review.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": "Loopbaancoach",
+      "advanceWhen": {
+        "file": "{{workPath}}/reports/weekly-pipeline-review.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/reports/weekly-pipeline-review.md",
+            "bytes": 1500,
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "{{workPath}}/reports/weekly-pipeline-review.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i",
+            "label": "at least one markdown heading",
+            "artifact": true
+          }
+        ],
+        "onReject": "review",
+        "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": "Audit the review against the snapshot. Step 1: cross-check — every application in the snapshot is accounted for in the review; FAIL any active application that appears in neither Moved, Stalled, nor Follow-ups. Step 2: check the carry-over rule — every stale item has an explicit chase, park-with-reason, or close. Step 3: count the next-week priorities — FAIL unless exactly three, each concrete enough to start tomorrow. Step 4: every follow-up line has a who, a what, and a when. Write PASS/FAIL per criterion.\n\nThe deliverable lives in the project's artifacts drawer — open `{{workPath}}/reports/weekly-pipeline-review.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: \"review\" })` 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}}/reports/weekly-pipeline-review.md",
+          "artifact": true
+        }
+      ],
+      "next": "review"
+    },
+    {
+      "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/we/weekly-pipeline-review/versions/1.0.2/test.json

@@ -0,0 +1,107 @@
+{
+  "schemaVersion": 1,
+  "title": "Weekly Pipeline Review smoke eval",
+  "objective": "Self-contained smoke eval for the Weekly Pipeline Review craftbook using the data generic harness.",
+  "tags": [
+    "data"
+  ],
+  "prompt": "I dropped our numbers in source/records.csv. Can you look at the data, analyze it, and put togehter some results in analysis.md?",
+  "setup": {
+    "projectName": "Weekly Pipeline Review Eval",
+    "about": "Self-contained eval project for weekly-pipeline-review. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/analysis.md.",
+    "missionObjectives": "Use the Weekly Pipeline Review craftbook/template, read the seeded local fixtures, and write analysis.md without network calls, real credentials, or live services.",
+    "files": [
+      {
+        "path": "source/brief.md",
+        "content": "# Weekly Pipeline Review 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: weekly-pipeline-review - Weekly Pipeline Review.\n"
+      },
+      {
+        "path": "source/records.csv",
+        "content": "customer,region,orders,revenue_usd,churn_risk\nAster,North,12,1440,low\nBoreal,South,8,720,medium\nCedar,West,15,2100,high\nDune,North,5,500,low\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Data Analyst"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "analysis.md is a seeded-data analysis with deterministic computed facts.",
+    "deliverables": [
+      {
+        "path": "analysis.md",
+        "kind": "markdown-report",
+        "minBytes": 900,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "analysis.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "analysis.md",
+            "pattern": "40\\b",
+            "flags": "i",
+            "label": "include total orders of 40"
+          },
+          {
+            "kind": "contains",
+            "file": "analysis.md",
+            "pattern": "\\$?4,?760\\b",
+            "flags": "i",
+            "label": "include total revenue of 4760"
+          },
+          {
+            "kind": "contains",
+            "file": "analysis.md",
+            "pattern": "Cedar",
+            "flags": "i",
+            "label": "identify Cedar as top revenue and high risk"
+          },
+          {
+            "kind": "contains",
+            "file": "analysis.md",
+            "pattern": "high",
+            "flags": "i",
+            "label": "include churn-risk finding"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "analysis.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "accuracy",
+        "description": "Computed figures are correct against the seeded records."
+      },
+      {
+        "name": "grounding",
+        "description": "Every claim traces to the seeded data — nothing invented."
+      },
+      {
+        "name": "structure",
+        "description": "Tables and sections make the analysis checkable at a glance."
+      },
+      {
+        "name": "actionability",
+        "description": "Recommendations follow from the findings and are concretely doable."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "seeded data reading",
+    "computed facts",
+    "recommendation grounding"
+  ]
+}

package/data/craftbook-templates/we/weekly-review/manifest.json

@@ -3,6 +3,7 @@
   "kind": "craftbook-template",
   "id": "weekly-review",
   "role": "maintenance-review",
+  "category": "business",
   "name": "Personal / Team Weekly Review",
   "description": "Assemble a reflective weekly review that pulls the week's done-list, metrics, and open loops into a structured retrospective with wins, misses, lessons, and next-week priorities. Scopes the review template and the inputs FIRST (the GTD-style sections, what data feeds each, the carry-over rule for unfinished items), then a copywriter writes the honest, concise review against that template. The scope-first ordering keeps the review consistent week over week and ensures open loops are carried forward rather than forgotten. Use for weekly reviews, personal retrospectives, GTD weekly review, end-of-week wrap-ups, and team retros.",
   "tags": [

package/data/craftbook-templates/we/weekly-review/versions/1.0.2/craftbook.json

@@ -0,0 +1,119 @@
+{
+  "id": "weekly-review",
+  "name": "Personal / Team Weekly Review",
+  "description": "Assemble a reflective weekly review that pulls the week's done-list, metrics, and open loops into a structured retrospective with wins, misses, lessons, and next-week priorities. Scopes the review template and the inputs FIRST (the GTD-style sections, what data feeds each, the carry-over rule for unfinished items), then a copywriter writes the honest, concise review against that template. The scope-first ordering keeps the review consistent week over week and ensures open loops are carried forward rather than forgotten. Use for weekly reviews, personal retrospectives, GTD weekly review, end-of-week wrap-ups, and team retros.\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 review (planner) — lock the template, inputs, and carry-over rule → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. Assemble the review (copywriter) — write the honest, grounded review to the template → gated on `review.md` (markdown-doc)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "scope",
+  "triggers": [
+    "weekly review",
+    "personal retro",
+    "end of week wrap-up",
+    "GTD weekly review",
+    "team retrospective"
+  ],
+  "steps": [
+    {
+      "id": "scope",
+      "name": "Scope the review",
+      "description": "lock the template, inputs, and carry-over rule",
+      "prompt": "Define the review structure before writing. (1) Lock the section template — This week's wins / Misses & what slipped / Metrics & progress / Lessons learned / Open loops carried forward / Next week's top 3 priorities. (2) Name the inputs feeding each section (completed tasks, the prior review's priorities, tracked metrics, {{workPath}}/journal). (3) Lock the carry-over rule: every item that was a priority last week and is still open MUST appear in Open loops and be explicitly resolved or re-prioritized — nothing silently dropped. (4) Set tone (honest, concise, first-person or team) and the reporting week. Write an acceptance-criteria checklist ('every template section present', 'wins and misses both populated honestly', 'last week\\'s open priorities each accounted for', 'next week is exactly three concrete priorities', 'grounded in real inputs, not generic') plus the template + input map to {{workPath}}/scope.md via write_task_note AND the produces path.\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": "assemble"
+    },
+    {
+      "id": "assemble",
+      "name": "Assemble the review",
+      "description": "write the honest, grounded review to the template",
+      "prompt": "Write review.md following the locked template, grounded in the named inputs. (1) Wins: specific, completed things — names and numbers, not vibes. (2) Misses & slipped: honest, with a one-line why each. (3) Metrics & progress: this-week values vs prior where available. (4) Lessons learned: 2-4 concrete takeaways tied to the wins/misses. (5) Open loops: apply the carry-over rule — list every still-open prior priority and mark it resolved, dropped (with reason), or carried. (6) Next week: EXACTLY three concrete, outcome-shaped priorities. Keep it tight and skimmable; invent no accomplishments. On a loop-back fix only the flagged sections. Write the path and a confirmation that all sections + the three priorities are present to notes via write_task_note.",
+      "suggestedRole": "copywriter",
+      "advanceWhen": {
+        "file": "review.md",
+        "minBytes": 1,
+        "sniff": "nonempty"
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "review.md",
+            "bytes": 500
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkContains",
+            "scope": "standard",
+            "inputs": {
+              "file": "review.md",
+              "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+              "flags": "i"
+            }
+          }
+        ],
+        "onReject": "assemble",
+        "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": "QA review.md against the locked criteria. (1) Confirm every template section is present and in order. (2) Confirm wins and misses are both populated with specific, non-generic items grounded in the inputs. (3) Apply the carry-over check: every open priority from last week's inputs is accounted for in Open loops (resolved/dropped/carried) — FAIL on any silent drop. (4) Confirm Next week is exactly three concrete priorities. (5) Spot-check 2-3 wins/metrics against the inputs for honesty. Write PASS/FAIL per criterion with specifics.\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: \"assemble\" })` 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": "review.md"
+        }
+      ],
+      "next": "assemble"
+    },
+    {
+      "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"
+}