@bendyline/gilde 0.1.50 → 0.1.52

package/data/craftbook-templates/ma/market-scan/versions/1.0.3/test.json

@@ -0,0 +1,213 @@
+{
+  "schemaVersion": 1,
+  "title": "Market scan from seeded landscape facts",
+  "objective": "Measure whether the market-scan craftbook scopes a boundary and writes a sourced landscape report across size, segments, players, trends, risks, and takeaway.",
+  "tags": [
+    "data"
+  ],
+  "prompt": "In the `Market Scan Eval` project, read `source/market-sources.md` and write `tasks/eval/scan.md` about the US design-studio operations software market in 2026. State the market boundary and exclusions, cover size/growth, segments, players, drivers, trends, risks, and a so-what takeaway. Cite every sized figure with source id and year.",
+  "setup": {
+    "projectName": "Market Scan Eval",
+    "about": "Self-contained eval project for market-scan. The landscape facts are seeded in workspace/source/market-sources.md.",
+    "missionObjectives": "Write a boundary-scoped, source-cited market scan from seeded facts without live web access.",
+    "files": [
+      {
+        "path": "source/market-sources.md",
+        "content": "# Seeded market sources\n\n[1] Studio Ops Survey 2026: US independent design studios spent an estimated $420M on operations software in 2025, growing 12% year over year.\n[2] Buyer interviews 2026: key segments are solo studios, 2-20 person boutique firms, and multi-location design-build groups.\n[3] Vendor notes 2026: notable players include StudioBinder Ops, Ivy Workspace, DesignFiles, HoneyBook, and Boreal Desk; Boreal Desk is strongest in returns workflows.\n[4] Trend memo 2026: three trends are AI-assisted admin, client portal consolidation, and returns/refunds workflow automation.\n[5] Risk memo 2026: risks include low willingness to switch CRMs, privacy expectations, and fragmented warehouse integrations.\n[6] Boundary note 2026: market boundary is US independent design studios with 1-100 employees. Exclude general construction ERP and consumer furniture marketplaces.\n"
+      }
+    ],
+    "worker": {
+      "name": "Timo",
+      "role": "Market Researcher"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "workspace/scan.md scopes the market boundary, cites seeded figures, maps segments/players/trends/risks, and closes with a decision-ready takeaway.",
+    "deliverables": [
+      {
+        "path": "tasks/eval/scan.md",
+        "kind": "markdown-report",
+        "minBytes": 1500,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "tasks/eval/scan.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/scan.md",
+            "pattern": "boundary|exclude|US independent design studios|construction ERP|furniture marketplaces",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/scan.md",
+            "pattern": "\\$420M|12%|2025|2026|\\[1\\]",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/scan.md",
+            "pattern": "solo studios|boutique|multi-location|segments",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/scan.md",
+            "pattern": "StudioBinder|Ivy Workspace|DesignFiles|HoneyBook|Boreal Desk",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/scan.md",
+            "pattern": "AI-assisted admin|client portal|returns/refunds|risks|so what|takeaway",
+            "flags": "i"
+          },
+          {
+            "kind": "notContains",
+            "file": "tasks/eval/scan.md",
+            "pattern": "\\[(?:0|7|8|9|\\d{2,})\\]",
+            "flags": "i",
+            "label": "do not invent citation ids beyond the seeded [1]-[6] sources"
+          },
+          {
+            "kind": "notContains",
+            "file": "tasks/eval/scan.md",
+            "pattern": "projected|projection(?:s)?|expected to grow|forecast|CAGR|TAM|SAM|SOM|global|worldwide|robust|significant growth trajectory|mature enough|maturing past|core growth segment|large design-build|specialized tools|specialized solutions|seamless|best positioned|future market success|high-level operational efficiency|vendor lock-in|regulatory scrutiny|powerful drivers",
+            "flags": "i",
+            "label": "remove unsupported market-sizing, forecast, and maturity claims"
+          },
+          {
+            "kind": "unsupportedClaims",
+            "file": "tasks/eval/scan.md",
+            "sourceFiles": [
+              "source/market-sources.md"
+            ],
+            "patterns": [
+              {
+                "pattern": "projected|projection(?:s)?",
+                "label": "avoid invented forecasts"
+              },
+              {
+                "pattern": "expected to grow",
+                "label": "avoid invented forecasts"
+              },
+              {
+                "pattern": "forecast",
+                "label": "avoid invented forecasts"
+              },
+              {
+                "pattern": "CAGR",
+                "label": "avoid invented growth metrics"
+              },
+              {
+                "pattern": "TAM|SAM|SOM",
+                "label": "avoid invented market-sizing frames"
+              },
+              {
+                "pattern": "global|worldwide",
+                "label": "stay inside the US market boundary"
+              },
+              {
+                "pattern": "robust",
+                "label": "avoid unsupported market-strength claims"
+              },
+              {
+                "pattern": "significant",
+                "label": "avoid unsupported magnitude claims"
+              },
+              {
+                "pattern": "mature enough",
+                "label": "avoid invented market-maturity claims"
+              },
+              {
+                "pattern": "maturing past",
+                "label": "avoid invented market-maturity claims"
+              },
+              {
+                "pattern": "core growth segment",
+                "label": "avoid invented segment priority"
+              },
+              {
+                "pattern": "large design-build",
+                "label": "avoid invented segment scale"
+              },
+              {
+                "pattern": "specialized tools",
+                "label": "avoid invented buyer-needs claims"
+              },
+              {
+                "pattern": "specialized solutions",
+                "label": "avoid invented vendor-positioning claims"
+              },
+              {
+                "pattern": "seamless",
+                "label": "avoid unsupported ease claims"
+              },
+              {
+                "pattern": "best positioned",
+                "label": "avoid invented winner claims"
+              },
+              {
+                "pattern": "future market success",
+                "label": "avoid invented market-outcome claims"
+              },
+              {
+                "pattern": "high-level operational efficiency",
+                "label": "avoid invented efficiency framing"
+              },
+              {
+                "pattern": "vendor lock-in",
+                "label": "avoid invented risk mechanisms"
+              },
+              {
+                "pattern": "regulatory scrutiny",
+                "label": "avoid invented regulatory claims"
+              },
+              {
+                "pattern": "powerful drivers",
+                "label": "avoid unsupported market-force claims"
+              }
+            ],
+            "flags": "i"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "tasks/eval/scan.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": [
+    "market boundary",
+    "sourced figures",
+    "landscape structure"
+  ]
+}

package/data/craftbook-templates/me/meeting-minutes/versions/1.0.2/test.json

@@ -19,9 +19,6 @@
     "worker": {
       "name": "Jules",
       "role": "Writer"
-    },
-    "craftbookParams": {
-      "workPath": "tasks/eval"
     }
   },
   "mocks": [],

package/data/craftbook-templates/me/meeting-minutes/versions/1.0.3/craftbook.json

@@ -0,0 +1,220 @@
+{
+  "id": "meeting-minutes",
+  "name": "Meeting Minutes & Actions",
+  "description": "Turn a meeting transcript, recording notes, or rough scratch into clean, distributable meeting minutes — attendees, agenda topics discussed, decisions made, and (most importantly) action items with owners and due dates. Scopes the minutes structure and what counts as a decision vs an action FIRST, then writes accurate, neutral minutes where every decision is recorded and every action has an owner and a date — the action table is the part people actually use. Use for board/team meeting minutes, project status meetings, and decision logs.\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 minutes (planner) — structure, what counts as a decision vs action, owner/date rule → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. Write the minutes (copywriter) — neutral minutes with a decisions log and an owner/date action table → gated on `minutes.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": [
+    "meeting minutes",
+    "write up meeting notes",
+    "minutes from a meeting",
+    "decisions and action items",
+    "meeting recap doc",
+    "action items list"
+  ],
+  "paramSchema": {
+    "type": "object",
+    "properties": {
+      "workPath": {
+        "type": "string",
+        "title": "Working folder",
+        "description": "Per-task working folder in the artifacts drawer. Defaults to this task's own folder so runs never collide; override with a stable name when you deliberately want runs to share files.",
+        "default": "{{task.dir}}"
+      }
+    }
+  },
+  "steps": [
+    {
+      "id": "scope",
+      "name": "Scope the minutes",
+      "description": "structure, what counts as a decision vs action, owner/date rule",
+      "prompt": "Decide the structure and the rules before writing. Step 1: capture the meeting metadata to record — title, date/time, attendees (present + absent), and the agenda/topics. Step 2: define the crucial distinction the minutes must enforce: a DECISION is a settled outcome (record what was decided and by whom), whereas an ACTION is a future task that MUST have an owner and a due date. Step 3: decide the section order: header/metadata, agenda, discussion-by-topic, decisions log, and an action-items table (Action | Owner | Due | Status). Step 4: set the neutrality rule — minutes record what happened factually, not opinion or editorializing. Step 5: write an acceptance-criteria checklist ('header with date + attendees', 'each agenda topic summarized neutrally', 'a decisions section listing every decision', 'an action table where EVERY action has an owner and a due date', 'no editorializing'). Write the structure + rules + checklist via write_task_note AND to {{workPath}}/scope.md. No minutes prose yet.\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": "write",
+      "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": "write",
+      "name": "Write the minutes",
+      "description": "neutral minutes with a decisions log and an owner/date action table",
+      "prompt": "Write the minutes as minutes.md from the source material. Step 1: open with the header block — meeting title, date/time, attendees present and absent. Step 2: list the agenda, then write a neutral, concise summary per topic discussed (what was raised and the gist of the discussion) without editorializing or attributing motives. Step 3: write a Decisions section that records every decision reached, each as a clear statement of what was decided. Step 4: write the Action Items as a markdown TABLE with columns Action | Owner | Due Date | Status, and ensure EVERY action row has a named owner and a concrete due date — flag any item missing an owner/date as [OWNER?]/[DATE?] rather than leaving it blank. Step 5: note the next meeting / follow-up if mentioned. Pull only from the source; do not invent decisions or actions that were not discussed. On a loop-back, fix ONLY the named gaps. Write the path + counts of decisions and actions via write_task_note.",
+      "suggestedRole": "copywriter",
+      "advanceWhen": {
+        "file": "minutes.md",
+        "minBytes": 1,
+        "sniff": "nonempty"
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "minutes.md",
+            "bytes": 500
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkContains",
+            "scope": "standard",
+            "inputs": {
+              "file": "minutes.md",
+              "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+              "flags": "i"
+            }
+          }
+        ],
+        "onReject": "write",
+        "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": "QA the minutes against the locked criteria. Step 1: read minutes.md alongside the source. Step 2: check EACH acceptance criterion: header includes date + attendees, each agenda topic has a neutral summary, a decisions section captures every decision from the source, and an action-items TABLE exists where EVERY row has a named owner and a concrete due date (any [OWNER?]/[DATE?] placeholder or blank is a FAIL on that criterion). Step 3: confirm the tone is factual with no editorializing and that no decision or action was invented beyond the source. Write PASS/FAIL per criterion; on a missing owner/date, name the offending action row and 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: \"write\" })` 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": "minutes.md"
+        }
+      ],
+      "next": "write",
+      "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/me/meeting-minutes/versions/1.0.3/test.json

@@ -0,0 +1,110 @@
+{
+  "schemaVersion": 1,
+  "title": "Meeting Minutes & Actions smoke eval",
+  "objective": "Self-contained smoke eval for the Meeting Minutes & Actions craftbook using the corpus generic harness.",
+  "tags": [
+    "corpus"
+  ],
+  "prompt": "We need a meeting minutes & actions 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": "Meeting Minutes & Actions Eval",
+    "about": "Self-contained eval project for meeting-minutes. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/report.md.",
+    "missionObjectives": "Use the Meeting Minutes & Actions 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": "# Meeting Minutes & Actions 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: meeting-minutes - Meeting Minutes & Actions.\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/me/meeting-notes-to-actions/versions/1.0.2/test.json

@@ -19,9 +19,6 @@
     "worker": {
       "name": "Jules",
       "role": "Writer"
-    },
-    "craftbookParams": {
-      "workPath": "tasks/eval"
     }
   },
   "mocks": [],