@bendyline/gilde 0.1.51 → 0.1.52

package/data/craftbook-templates/of/offer-compare/versions/1.0.3/craftbook.json

@@ -0,0 +1,214 @@
+{
+  "id": "offer-compare",
+  "name": "Offer Comparison",
+  "description": "Turn competing job offers into one honest decision sheet — every offer normalized into the same fact grid (comp, equity with vesting caveats, benefits, level, location, growth, deadlines), unknowns marked UNKNOWN instead of guessed, computed year-1 and 4-year views under stated assumptions, a weighted read against the candidate's OWN priorities, and a recommendation that separates arithmetic from judgment. Use when any second offer (or a strong counter) lands.\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. Normalize the facts (planner) — one fact grid across every offer, unknowns honest, the user's own weights elicited → gated on artifact `{{workPath}}/offer-facts.md` (markdown-notes)\n2. Build the comparison (planner) — the decision sheet — table, computed views, weighted read, recommendation → gated on artifact `{{workPath}}/reports/offer-compare.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": "facts",
+  "triggers": [
+    "compare my offers",
+    "which offer should I take",
+    "offer comparison",
+    "help me decide between offers"
+  ],
+  "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": "facts",
+      "name": "Normalize the facts",
+      "description": "one fact grid across every offer, unknowns honest, the user's own weights elicited",
+      "prompt": "Build the fact sheet before any comparison. Step 1: collect every offer's terms from the user or project documents into one grid: base, bonus (target and realism), equity (kind, vesting schedule, valuation caveats), benefits, PTO, level/title, location/remote terms, team and manager, growth story, response deadline. Step 2: mark every unknown as UNKNOWN — never estimate a number the offer letter does not state; list the UNKNOWNs as questions to ask each company. Step 3: elicit the user's OWN decision weights — what actually matters to them (comp, growth, stability, location, mission, team) — do not invent or assume weights. Step 4: state the assumptions any computed view will use (equity valuation basis, bonus attainment). Step 5: write an acceptance-criteria checklist ('every offer covered on every factor', 'unknowns marked UNKNOWN', 'weights are the user's own words', 'assumptions stated'). Write the fact sheet + checklist via write_task_note AND to {{workPath}}/offer-facts.md.\n\nThe deliverable `{{workPath}}/offer-facts.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}}/offer-facts.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/offer-facts.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/offer-facts.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "facts",
+        "maxAttempts": 3
+      },
+      "next": "compare",
+      "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": "compare",
+      "name": "Build the comparison",
+      "description": "the decision sheet — table, computed views, weighted read, recommendation",
+      "prompt": "Write {{workPath}}/reports/offer-compare.md from the fact sheet. Step 1: a factor-by-offer markdown comparison table — offers as columns, factors as rows, UNKNOWNs still visible. Step 2: computed lines under the STATED assumptions: year-1 cash, and a 4-year total-comp view with the equity caveats repeated next to the number. Step 3: a weighted read against the user's stated priorities — show how each offer scores on what THEY said matters, not on a generic rubric. Step 4: risks and negotiation levers per offer (deadline pressure, level mismatch, unvested cliff, remote-policy risk). Step 5: a recommendation that separates the arithmetic ('offer B leads on 4-year comp under these assumptions') from the judgment ('offer A fits the growth priority you weighted highest') — and says plainly which way the sheet leans and why. On a loop-back, fix ONLY the named issues.\n\nThe deliverable `{{workPath}}/reports/offer-compare.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}}/reports/offer-compare.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/reports/offer-compare.md",
+            "bytes": 1500,
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "{{workPath}}/reports/offer-compare.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i",
+            "label": "at least one markdown heading",
+            "artifact": true
+          }
+        ],
+        "onReject": "compare",
+        "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"
+      }
+    },
+    {
+      "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 decision sheet. Step 1: recompute the year-1 and 4-year lines from the fact sheet — FAIL on any arithmetic that does not reproduce, or any computed number whose assumption is not stated beside it. Step 2: check every offer appears in every table row and that fact-sheet UNKNOWNs were not silently replaced with guesses. Step 3: trace the weighted read to the user's stated priorities — FAIL a rubric the user never gave. Step 4: confirm the recommendation separates arithmetic from judgment and takes a clear position. Write PASS/FAIL per criterion.\n\nThe deliverable lives in the project's artifacts drawer — open `{{workPath}}/reports/offer-compare.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: \"compare\" })` 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/offer-compare.md",
+          "artifact": true
+        }
+      ],
+      "next": "compare",
+      "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/of/offer-compare/versions/1.0.3/test.json

@@ -0,0 +1,110 @@
+{
+  "schemaVersion": 1,
+  "title": "Offer Comparison smoke eval",
+  "objective": "Self-contained smoke eval for the Offer Comparison craftbook using the corpus generic harness.",
+  "tags": [
+    "corpus"
+  ],
+  "prompt": "We need a offer comparison 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": "Offer Comparison Eval",
+    "about": "Self-contained eval project for offer-compare. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/report.md.",
+    "missionObjectives": "Use the Offer Comparison 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": "# Offer Comparison 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: offer-compare - Offer Comparison.\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Writer"
+    }
+  },
+  "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"
+  ]
+}

package/data/craftbook-templates/of/office-hours/versions/1.1.1/craftbook.json

@@ -0,0 +1,150 @@
+{
+  "id": "office-hours",
+  "name": "Office Hours",
+  "description": "An office-hours-style scoping procedure. The user shows up with an idea\nor a problem; the procedure forces them through *listen → challenge →\nreframe → lock scope* before any solutioning happens.\n\nThis is deliberately a pure-prose procedure — no scripts, no hooks. The model\nfollows the step prose, elicits answers via `ask_user_question` (or\nprose, see below), and writes the locked scope to a task note that\ndownstream craftbooks (`/plan-eng-review`, `/review`, `/ship`) read.\n\nThe principle is the YC office-hours pattern: most ideas die not because\nthey're bad but because the problem statement was too loose to bite\ninto. A 20-minute conversation that lands on the *right* problem is\nworth more than a week building the wrong product.\n\nThe recipe never assumes the user is right. If their framing is shaky,\nthe **Challenge** step names that explicitly. The **Reframe** step\nforces a single pick — office hours doesn't end with three startups.\n\n## Tool surface assumptions\n\nEach step prefers `ask_user_question` for structured prompts and\n`write_task_note` for the lock-scope artifact, but each prompt also\nships a **prose / `write_file` fallback** so the craftbook completes on\nany gezel whose role-tool-filter omits the question/notes tools.\nThat mismatch — Office Hours being assigned to a gezel without the\nquestion tool — was the 2026-06 failure mode: an 8B Gemma running\nunder the developer-style role surface had no `ask_user_question`,\nspun up workarounds (memory searches, repeated `invoke_craftbook`\ncalls, throwaway tasks), and got aborted by the\nsame-arguments-5-times detector before producing anything useful.\nThe explicit *\"if it's in your function schema, otherwise prose\"*\nbranches keep small/medium models on the rails when the surface\nisn't what the prompt assumes.\n\nThe kickoff step also **explicitly overrides** the common gezel\ninstruction to \"search memory before asking the user.\" Pre-loading\ncontext is the right default for follow-up turns and for non-listening\ntasks; for office-hours kickoff it defeats the procedure (the whole\npoint is to hear the user's framing FRESH). The override is named in\nthe prompt so the model doesn't have to resolve the conflict by\nguessing.\n\n## Notes for small / medium models (≤12B)\n\n- Steps are kept under ~200 words and frontload the action (\"**One\n  job this step:** …\") so a small context window doesn't lose focus\n  on long preambles.\n- The \"do NOT\" list is explicit and specific (don't search memory,\n  don't list tasks, don't `invoke_craftbook`) because small models\n  tend to wander to those tools when their headline tool is missing.\n- Examples are concrete (Pac-Man-style: \"A personal chief-of-staff\n  (productivity tool); A solution to nobody-reads-RSS (consumer\n  media); A publishing tool for journalists (B2B SaaS)\") rather than\n  abstract — small models reason better from a worked example than\n  from a rule.\n- Each step is self-contained: re-reading the previous step's notes\n  is allowed but not required to complete this one. The lock-scope\n  step is the only one that depends on prior-step output; the rest\n  read what's directly above in the chat.\n",
+  "basedOn": {
+    "name": "gstack",
+    "url": "https://github.com/garrytan/gstack"
+  },
+  "entryStepId": "kickoff",
+  "triggers": [
+    "office hours",
+    "scope this",
+    "help me think about",
+    "what should I build"
+  ],
+  "steps": [
+    {
+      "id": "kickoff",
+      "name": "Kickoff",
+      "description": "Hear the user out. Capture the problem they think they're solving in their own words. No solutioning yet.",
+      "prompt": "**One job this step: ask the user three questions. Nothing else this turn.**\n\nBefore anything else: do NOT search memory, do NOT list tasks, do NOT read documents, do NOT call `invoke_craftbook`, do NOT call `create_task`. The whole point of office hours is to hear the user's framing FRESH — pre-loading context defeats the procedure, and a task already exists (this is it). If your gezel about tells you to `search_memory` before asking the user, **ignore that here** — kickoff is the one place we ask cold.\n\n**Ask with `ask_user_question` if it's in your function schema** — one call, three sub-questions:\n\n1. What problem are you trying to solve?\n2. Who experiences this problem?\n3. What have you tried already?\n\n**If `ask_user_question` is NOT in your function schema:** post the three questions as a short prose reply (numbered list, nothing else), then end the turn. The user's next message is the answer.\n\nDo not propose solutions. Do not validate the idea. Do not theorize about answers. Ask, stop.",
+      "suggestedRole": "meester",
+      "next": "challenge",
+      "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": "none"
+      }
+    },
+    {
+      "id": "challenge",
+      "name": "Challenge",
+      "description": "Stress-test premises. What assumption is doing the most load-bearing work here?",
+      "prompt": "**This step: pick the 1-2 weakest assumptions in what the user just said and push on them. Then ask. Nothing else this turn.**\n\nRead the kickoff answer. Pick the assumption that, if wrong, makes the whole framing collapse. Examples of pushable shapes:\n\n- 'Users will pay for X' → 'What evidence? Has anyone paid yet?'\n- 'The problem is slow checkout' → 'Is it speed, or trust? Different fix.'\n- 'We need a mobile app' → 'Why mobile vs web? Where do these users actually live?'\n\n**Ask with `ask_user_question` if it's in your function schema** — one call, 2-3 forcing questions.\n\n**Otherwise post the forcing questions as a short prose reply** (numbered list) and end the turn.\n\nIf the user's kickoff answer already carries evidence for the assumption, accept it: write one short prose line ('OK, that holds — moving on') and advance. Don't manufacture doubt where the user already showed their work.",
+      "suggestedRole": "meester",
+      "next": "reframe",
+      "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": "none"
+      }
+    },
+    {
+      "id": "reframe",
+      "name": "Reframe",
+      "description": "Generate 2-3 alternative framings of the problem. The user picks one to focus on.",
+      "prompt": "**This step: propose 2-3 alternative framings of the problem, ask the user to pick one.**\n\nRead what the user said in kickoff + challenge. Propose 2-3 framings that interpret the same facts differently. Each framing implies a different product, a different user, a different success criterion. Example:\n\n- User said 'I want a daily-briefing app.' Framings:\n  1. A personal chief-of-staff (productivity tool)\n  2. A solution to 'nobody reads their RSS feeds anymore' (consumer media)\n  3. A publishing tool for journalists (B2B SaaS)\n\n**Ask with `ask_user_question` (multi-choice) if it's in your function schema** — `choices = your 2-3 framings`, plus a final 'none of these — let me reframe again' option as escape.\n\n**Otherwise post the framings as a numbered list in prose**, tell the user 'pick a number', and end the turn.\n\nIf the user wants 'all three', push back in one sentence — office hours ends with ONE.",
+      "suggestedRole": "meester",
+      "next": "lock-scope",
+      "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": "none"
+      }
+    },
+    {
+      "id": "lock-scope",
+      "name": "Lock scope",
+      "description": "Write the scope down. One paragraph. Two if forced. Hand off to plan-review next.",
+      "prompt": "**This step: write the locked scope as a single paragraph (max 2). Then report DONE.**\n\nThe user picked a framing in reframe. Write it down. Structure:\n\n- **The problem** (one sentence, in the user's reframed terms)\n- **The user** (one sentence — who specifically experiences this)\n- **The success criterion** (one sentence — what 'this works' looks like)\n- **NOT in scope** (one sentence — what you're deliberately not building, to keep the cut tight)\n\n**Persist it with `write_task_note` if it's in your function schema** so the next craftbook (`/plan-eng-review`, `/review`, `/ship`) reads it from the task scratchpad.\n\n**Otherwise use `write_file` to ship `scope.md` to the project workspace** — every gezel with workspace-write has `write_file`, and downstream craftbooks can `read_file` it from the same path. (Don't `write_artifact` it — source-shaped files belong on the workspace tree.)\n\nThen report DONE in one short paragraph.",
+      "suggestedRole": "meester",
+      "terminal": true,
+      "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"
+        ],
+        "outputMedium": "workspace",
+        "additionalOutputMedia": [
+          "artifact",
+          "task-note"
+        ]
+      }
+    }
+  ],
+  "version": "1.1.1",
+  "releasedAt": "2026-09-01T20:00:00Z"
+}

package/data/craftbook-templates/of/office-hours/versions/1.1.1/test.json

@@ -0,0 +1,118 @@
+{
+  "schemaVersion": 1,
+  "title": "Scripted office-hours scoping conversation",
+  "objective": "Exercise the office-hours listening/challenge/reframe/lock-scope flow with deterministic user answers and verify that it produces a narrowed scope instead of a premature solution.",
+  "tags": [
+    "corpus"
+  ],
+  "prompt": "In the `Office Hours Eval` project, read `source/scripted-answers.md` and write `scope.md`: locked scope notes for the product idea. Do not build the product. Include the original broad idea, the challenged weak assumption, at least two reframes considered, the selected narrow scope, target user, success criterion, explicit out-of-scope items, and next validation step.",
+  "setup": {
+    "projectName": "Office Hours Eval",
+    "about": "Self-contained eval project for the office-hours craftbook. The scripted user answers are in workspace/source/scripted-answers.md.",
+    "missionObjectives": "Use the scripted answers as the user conversation transcript. Produce scope.md only after challenging an assumption and locking a narrow scope.",
+    "files": [
+      {
+        "path": "source/scripted-answers.md",
+        "content": "# Scripted office-hours answers\n\nBroad idea: Build a portal for neighborhood food co-ops to coordinate weekly produce boxes, volunteer packing shifts, and pickup reminders.\nPrimary user: volunteer coordinators at small co-ops with 60-180 weekly members.\nWeak assumption to challenge: coordinators mostly need more features; in reality the interview notes say missed pickup reminders and unclear packing counts cause the most pain.\nEvidence: three coordinators mentioned SMS reminder misses; two mentioned duplicate spreadsheet edits; none asked for payment processing in the first version.\nPossible reframes: reminder reliability dashboard; packing-count handoff sheet; member self-serve portal; volunteer shift marketplace.\nSelected reframe: packing-count handoff plus pickup-reminder checklist for one weekly cycle.\nSuccess criterion: one coordinator can prepare the Thursday packing sheet and reminder checklist in under 15 minutes with zero duplicate count edits.\nOut of scope: payment processing, inventory purchasing, public member portal, route optimization, volunteer marketplace.\nNext validation: test the handoff sheet with Northside Co-op on one Thursday cycle."
+      }
+    ],
+    "worker": {
+      "name": "Oda",
+      "role": "Researcher"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "The run asks the expected questions, challenges a weak assumption, offers reframes, and writes locked scope notes or scope.md with problem, user, success criterion, and out-of-scope.",
+    "deliverables": [
+      {
+        "path": "scope.md",
+        "kind": "markdown-notes",
+        "minBytes": 1100,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "scope.md",
+            "pattern": "food co-?op|produce boxes",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "scope.md",
+            "pattern": "weak assumption|challenge",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "scope.md",
+            "pattern": "reframe|alternative",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "scope.md",
+            "pattern": "packing|handoff|pickup reminder",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "scope.md",
+            "pattern": "under 15 minutes|15 minutes",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "scope.md",
+            "pattern": "out[-\\s]?of[-\\s]?scope|not in scope",
+            "flags": "i"
+          },
+          {
+            "kind": "notContains",
+            "file": "scope.md",
+            "pattern": "payment processing.*in scope|build the portal",
+            "flags": "i"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "scope.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "safety",
+        "description": "Dry-run posture is explicit: no real credentials, clear stop-before-side-effect boundary."
+      },
+      {
+        "name": "mapping",
+        "description": "Fake endpoints/commands are mapped completely to the workflow steps."
+      },
+      {
+        "name": "signals",
+        "description": "Success, failure, retry, and abort conditions are all defined."
+      },
+      {
+        "name": "containment",
+        "description": "The plan cannot accidentally reach a real service from a mock context."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "ask_user_question flow",
+    "challenge before solutioning",
+    "locked scope"
+  ],
+  "extensions": {
+    "legacySimulators": [
+      {
+        "id": "office-hours-fake-service-fixture",
+        "kind": "data-source",
+        "status": "implemented",
+        "description": "Seeded local fake service contract replacing live CLIs, HTTP APIs, credentials, and side effects."
+      }
+    ]
+  }
+}