@bendyline/gilde 0.1.51 → 0.1.52

package/data/craftbook-templates/id/idea-office-hours/versions/2.0.5/test.json

@@ -0,0 +1,141 @@
+{
+  "schemaVersion": 1,
+  "title": "Idea Office Hours — evidence-backed wedge decision",
+  "objective": "Exercise the Idea Office Hours craftbook end to end on a constrained product idea and require a grounded decision, explicit alternatives, and an auditable craftbook-task handoff.",
+  "tags": [
+    "workflow",
+    "product",
+    "ideation",
+    "decision"
+  ],
+  "prompt": "Use the Idea Office Hours craftbook to pressure-test the QuietQueue idea in `source/idea-context.md`. Do not jump straight to implementation. Work through the evidence, compare at least three materially different options (including no-build/manual), choose a narrow pilot wedge, and write the craftbook's decision artifacts. The final decision at `decisions/idea-office-hours.md` must cite the supplied source, state what remains assumed, name a concrete next real-world action with an owner and measurement, and avoid inventing customer evidence.",
+  "setup": {
+    "projectName": "QuietQueue idea review",
+    "about": "A hermetic product-decision exercise for a small clinic scheduling concept. Only the seeded evidence is authoritative.",
+    "missionObjectives": "Decide whether there is a narrow, testable pilot worth running without handling PHI or committing to a full scheduling product.",
+    "files": [
+      {
+        "path": "source/idea-context.md",
+        "content": "# QuietQueue idea context\n\n## Audience\nBoutique physical-therapy clinics with 3–12 practitioners. The immediate user is the front-desk coordinator; clinic owners approve spend.\n\n## Observed problem\nAcross four discovery calls, coordinators described reminder calling as repetitive and hard to finish during busy afternoons. A two-week manual tally recorded **31 no-shows across 420 appointments** and about **6 staff hours per week** spent on reminder calls. These are directional observations, not a statistically representative study.\n\n## Constraints\n- A pilot must launch within two weeks.\n- It must not ingest protected health information.\n- The clinic can export appointment first name, mobile number, and time into a temporary CSV only after its privacy lead approves the fields.\n- The team has one product engineer and no native-mobile capacity.\n- Budget for the pilot is $750.\n\n## Candidate ideas raised so far\n1. A full scheduling and messaging platform.\n2. A CSV-driven reminder assistant that drafts messages for staff approval.\n3. A better call-list spreadsheet and a scripted reminder process (no new product).\n\n## Unknowns\nWhether patients will opt into SMS, whether approval adds too much staff friction, and whether fewer no-shows would persist beyond the pilot.\n"
+      }
+    ]
+  },
+  "mocks": [],
+  "success": {
+    "summary": "The named craftbook produces a grounded wedge decision and records its terminal task handoff.",
+    "deliverables": [
+      {
+        "path": "decisions/idea-office-hours.md",
+        "kind": "markdown-report",
+        "minBytes": 1100,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "decisions/idea-office-hours.md",
+            "pattern": "^#{1,3}\\s+(Problem|Problem framing)\\b[\\s\\S]*^#{1,3}\\s+(User evidence|Evidence)\\b[\\s\\S]*^#{1,3}\\s+(Chosen wedge|Decision)\\b",
+            "flags": "im",
+            "label": "problem, evidence, and chosen-wedge sections"
+          },
+          {
+            "kind": "contains",
+            "file": "decisions/idea-office-hours.md",
+            "pattern": "^#{1,3}\\s+Alternatives considered\\b[\\s\\S]*(manual|no[- ]build)[\\s\\S]*^#{1,3}\\s+Next real-world action\\b",
+            "flags": "im",
+            "label": "manual alternative and next action"
+          },
+          {
+            "kind": "valueGrounding",
+            "file": "decisions/idea-office-hours.md",
+            "facts": [
+              {
+                "id": "observed-no-shows",
+                "label": "observed no-show evidence",
+                "required": [
+                  "31\\s+no-shows?"
+                ]
+              },
+              {
+                "id": "observed-appointments",
+                "label": "observed appointment denominator",
+                "required": [
+                  "420\\s+appointments?"
+                ]
+              },
+              {
+                "id": "staff-time",
+                "label": "weekly reminder effort",
+                "required": [
+                  "6\\s+(staff\\s+)?hours?\\s+per\\s+week"
+                ]
+              },
+              {
+                "id": "pilot-duration",
+                "label": "two-week pilot constraint",
+                "required": [
+                  "two[- ]week|2[- ]week"
+                ]
+              },
+              {
+                "id": "pilot-data-boundary",
+                "label": "no-PHI pilot constraint",
+                "required": [
+                  "(no|without|not)\\s+(handling|ingesting|using)?\\s*PHI|protected health information"
+                ]
+              }
+            ]
+          },
+          {
+            "kind": "citationsResolve",
+            "file": "decisions/idea-office-hours.md",
+            "minCitations": 1
+          }
+        ]
+      }
+    ],
+    "taskNotes": {
+      "minBytes": 160,
+      "checks": [
+        {
+          "kind": "contains",
+          "file": "task-notes.md",
+          "pattern": "\\bDONE\\b[\\s\\S]*decisions/idea-office-hours\\.md",
+          "label": "terminal craftbook note names the decision"
+        }
+      ],
+      "requireCraftbookTask": true
+    },
+    "taskGraph": {
+      "requireCraftbookTask": true,
+      "requireTerminalStep": true
+    },
+    "unchangedFixtures": [
+      "source/idea-context.md"
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "decisions/idea-office-hours.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "Diagnostic depth",
+        "description": "The decision separates observed evidence from assumptions and identifies the most consequential unknowns before proposing a solution."
+      },
+      {
+        "name": "Option quality",
+        "description": "Alternatives are genuinely different, fairly compared, and include a credible manual or no-build path."
+      },
+      {
+        "name": "Decision usefulness",
+        "description": "The chosen wedge is narrow, constraint-aware, measurable, and leads to a concrete owner-backed next action."
+      }
+    ],
+    "contextNote": "Judge only against `source/idea-context.md`; unsupported market or customer claims are defects."
+  },
+  "qualityFocus": [
+    "Evidence is clearly distinguished from assumption",
+    "The selected wedge is smaller than a full scheduling platform",
+    "The next action has an owner, measurement, and decision-useful outcome"
+  ]
+}

package/data/craftbook-templates/id/idle-clicker-game/versions/1.0.3/craftbook.json

@@ -0,0 +1,288 @@
+{
+  "id": "idle-clicker-game",
+  "name": "Idle / Incremental Game",
+  "description": "Build a single-file idle or incremental clicker game such as a cookie/factory clicker with upgrades, generators, and exponential growth. Designs the resource economy — base click yield, generator costs, cost-scaling factor, and per-second production — first, then the layout, then implements a tick loop with persistent-feeling progression. Idle games are an economy problem before a UI problem: if costs and yields are not tuned the game is boring in 10 seconds or unwinnable, so the economy phase locks the exact numbers and growth curve before any rendering.\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. Economy design (game-designer) — resources, generator costs, scaling, tick rate → gated on artifact `{{workPath}}/economy-design.md` (markdown-notes)\n2. Visual design (visual-designer) — big-click target, shop layout, number formatting → gated on artifact `{{workPath}}/visual-design.md` (markdown-notes)\n3. Build (developer) — implement the tick loop + shop in index.html → gated on `index.html` (html-game)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "economy-design",
+  "triggers": [
+    "idle game",
+    "clicker game",
+    "incremental game",
+    "cookie clicker",
+    "factory game",
+    "make an idle game"
+  ],
+  "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": "economy-design",
+      "name": "Economy design",
+      "description": "resources, generator costs, scaling, tick rate",
+      "prompt": "Design the ECONOMY with real numbers. (1) Name the primary resource and the base yield per manual click. (2) Define 3-5 generators: each with a base cost, a per-second production, and a cost-scaling factor applied per purchase (e.g. cost *= 1.15). (3) Set the tick rate (how often production is added, e.g. every 100ms) and ensure offline-free production accumulates while playing. (4) Add at least one upgrade that multiplies click or generator output. (5) Sanity-check the curve: roughly when can the player afford generator 1, 2, 3 — it should feel rewarding within the first minute and keep escalating. (6) Write an acceptance-criteria checklist of 5-8 items, e.g. 'clicking increases the resource', 'each generator costs more after each buy', 'production accrues per tick automatically', 'an upgrade visibly boosts output', 'buttons disable when unaffordable', 'no console errors'. Write to {{workPath}}/economy-design.md and via write_task_note. No code yet.\n\nThe deliverable `{{workPath}}/economy-design.md` lands in the project's artifacts drawer — write it with `write_artifact` and read it back with `read_artifact`; the shipped workspace stays untouched.",
+      "suggestedRole": "game-designer",
+      "advanceWhen": {
+        "file": "{{workPath}}/economy-design.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/economy-design.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/economy-design.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "economy-design",
+        "maxAttempts": 3
+      },
+      "next": "visual-design",
+      "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": "visual-design",
+      "name": "Visual design",
+      "description": "big-click target, shop layout, number formatting",
+      "prompt": "Design the layout from the locked economy. (1) Choose a palette (hex) and a prominent click target (a big button or icon). (2) Lay out the resource counter (with abbreviated large numbers like 1.2K, 3.4M), the per-second rate, and the generator/upgrade shop list with cost and owned-count. (3) Specify affordance feedback: unaffordable items dimmed/disabled, a small pop on click. (4) Keep numbers readable as they grow. (5) Self-contained CSS, no external assets. Write the visual spec to {{workPath}}/visual-design.md and via write_task_note. No game logic yet.\n\nThe deliverable `{{workPath}}/visual-design.md` lands in the project's artifacts drawer — write it with `write_artifact` and read it back with `read_artifact`; the shipped workspace stays untouched.",
+      "suggestedRole": "visual-designer",
+      "advanceWhen": {
+        "file": "{{workPath}}/visual-design.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/visual-design.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/visual-design.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "visual-design",
+        "maxAttempts": 3
+      },
+      "next": "build",
+      "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": "build",
+      "name": "Build",
+      "description": "implement the tick loop + shop in index.html",
+      "prompt": "Implement the idle game in a single index.html (inline CSS + JS) to the visual spec, satisfying every criterion. (1) Hold resource, generators (count, cost, rate), and upgrades in state. (2) On click, add the click yield. (3) On a setInterval/RAF tick, add total per-second production scaled by elapsed time. (4) Buying a generator deducts cost, increments count, and multiplies its cost by the scaling factor; disable buttons when unaffordable. (5) Apply upgrades as multipliers and format large numbers compactly. Vanilla JS, no CDN. On a loop-back, fix only the named gaps without regressing passing criteria. write_task_note the path and passing criteria.",
+      "suggestedRole": "developer",
+      "advanceWhen": {
+        "file": "index.html",
+        "minBytes": 1,
+        "sniff": "html-complete"
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "index.html",
+            "bytes": 1500
+          },
+          {
+            "kind": "htmlLint",
+            "file": "index.html"
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkHtmlGame",
+            "scope": "standard",
+            "inputs": {
+              "file": "index.html"
+            }
+          },
+          {
+            "name": "checkJsParses",
+            "scope": "standard",
+            "inputs": {
+              "file": "index.html"
+            }
+          }
+        ],
+        "onReject": "build",
+        "maxAttempts": 4
+      },
+      "next": "evaluate",
+      "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"
+        ],
+        "outputMedium": "workspace",
+        "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": "Play for a minute. Open index.html if possible, else trace the tick loop and cost-scaling math. Check EACH criterion from {{workPath}}/economy-design.md and write PASS/FAIL with a reason: does clicking add resource, does each purchase raise the next cost, does production accrue automatically per tick, does an upgrade boost output, do buttons disable when unaffordable, zero console errors? Confirm the curve feels rewarding-then-escalating, not instant-win or stuck. Any broken cost-scaling is a FAIL — loop back.\n\nThen route — this is the whole point of the loop:\n\n- **Every criterion PASSES →** call `advance_task_step({ ref, stepId: \"evaluate\", next: \"finish\" })`.\n- **Any criterion FAILS →** write the specific gaps to notes, then call `advance_task_step({ ref, stepId: \"evaluate\", next: \"build\" })` to loop back. The builder fixes exactly those gaps.\n\nNever route to `finish` while any criterion is unmet. The build phase's completion gate already blocked a grossly-incomplete deliverable; your job is the judgment an automated check cannot make (does it actually work, read well, look right). After ~3 unproductive loops, stop and report DONE_WITH_CONCERNS so the user can step in.",
+      "suggestedRole": "reviewer",
+      "consumes": [
+        {
+          "file": "index.html"
+        }
+      ],
+      "next": "build",
+      "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"
+      }
+    },
+    {
+      "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/id/idle-clicker-game/versions/1.0.3/test.json

@@ -0,0 +1,99 @@
+{
+  "schemaVersion": 1,
+  "title": "Idle / Incremental Game smoke eval",
+  "objective": "Self-contained smoke eval for the Idle / Incremental Game craftbook using the html-game generic harness.",
+  "tags": [
+    "html-game"
+  ],
+  "prompt": "Make us a fun litle browser game around the returns-desk theme — just one file, index.html, that we can open and play.",
+  "setup": {
+    "projectName": "Idle / Incremental Game Eval",
+    "about": "Self-contained eval project for idle-clicker-game. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/index.html.",
+    "missionObjectives": "Use the Idle / Incremental Game 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": "# Idle / Incremental Game 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: idle-clicker-game - Idle / Incremental Game.\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Developer"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "index.html is a complete self-contained browser game smoke artifact.",
+    "deliverables": [
+      {
+        "path": "index.html",
+        "kind": "html-game",
+        "minBytes": 3200,
+        "checks": [
+          {
+            "kind": "cssMinBytes",
+            "bytes": 600,
+            "file": "index.html"
+          },
+          {
+            "kind": "jsParses",
+            "file": "index.html"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "<canvas|<svg|requestAnimationFrame",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "score|state|level|turn",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "restart|play again|new game|game over|victory|you win|you lose",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "Boreal|returns|desk",
+            "flags": "i"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "index.html",
+      "kind": "html"
+    },
+    "axes": [
+      {
+        "name": "playability",
+        "description": "The game is actually playable: input works, state advances, and a session can be completed."
+      },
+      {
+        "name": "completeness",
+        "description": "Core loop, scoring/win-lose, and restart are all present rather than stubbed."
+      },
+      {
+        "name": "polish",
+        "description": "Visual design and feedback (motion, states, messages) feel deliberate, not default."
+      },
+      {
+        "name": "robustness",
+        "description": "No console errors, dead controls, or states the player can get stuck in."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "runtime surface",
+    "interaction loop",
+    "self-contained game"
+  ]
+}