@bendyline/gilde 0.1.51 → 0.1.52

package/data/craftbook-templates/lo/logo-set/versions/1.0.3/test.json

@@ -0,0 +1,103 @@
+{
+  "schemaVersion": 1,
+  "title": "Logo & Variant Set smoke eval",
+  "objective": "Self-contained smoke eval for the Logo & Variant Set craftbook using the media generic harness.",
+  "tags": [
+    "media"
+  ],
+  "prompt": "Our media files are all listd in source/media-index.csv. Can you put together the production plan for them as media-plan.json?",
+  "setup": {
+    "projectName": "Logo & Variant Set Eval",
+    "about": "Self-contained eval project for logo-set. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/media-plan.json.",
+    "missionObjectives": "Use the Logo & Variant Set craftbook/template, read the seeded local fixtures, and write media-plan.json without network calls, real credentials, or live services.",
+    "files": [
+      {
+        "path": "source/brief.md",
+        "content": "# Logo & Variant Set 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: logo-set - Logo & Variant Set.\n"
+      },
+      {
+        "path": "source/media-index.csv",
+        "content": "filename,type,duration_or_size,notes\npilot-interview.wav,audio,00:02:15,mentions response time and status silence\nreturns-desk.png,image,1600x900,shows intake form and photo evidence step\nlaunch-clip.mp4,video,00:01:05,shows barcode exception handling\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Producer"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "media-plan.json is a valid JSON media-production manifest grounded in seeded fixture metadata.",
+    "deliverables": [
+      {
+        "path": "media-plan.json",
+        "kind": "json",
+        "minBytes": 700,
+        "checks": [
+          {
+            "kind": "sniff",
+            "file": "media-plan.json",
+            "sniff": "json-valid"
+          },
+          {
+            "kind": "contains",
+            "file": "media-plan.json",
+            "pattern": "pilot-interview\\.wav|returns-desk\\.png|launch-clip\\.mp4",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "media-plan.json",
+            "pattern": "outputs|assets|steps|cues|verification",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "media-plan.json",
+            "pattern": "accessibility|alt|caption|transcript|metadata",
+            "flags": "i"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "media-plan.json",
+      "kind": "json"
+    },
+    "axes": [
+      {
+        "name": "completeness",
+        "description": "The manifest covers sources, outputs, and processing steps end to end."
+      },
+      {
+        "name": "grounding",
+        "description": "Only seeded media fixtures are referenced, with faithful metadata."
+      },
+      {
+        "name": "accessibility",
+        "description": "Alt text, captions, or transcripts are planned wherever the class requires."
+      },
+      {
+        "name": "precision",
+        "description": "Timestamps, crops, and cues are specific enough to execute."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "media fixture handling",
+    "structured manifest",
+    "verification metadata"
+  ],
+  "extensions": {
+    "legacySimulators": [
+      {
+        "id": "logo-set-media-fixtures",
+        "kind": "data-source",
+        "status": "implemented",
+        "description": "Seeded local media index replacing real audio, video, image generation, and external media metadata services."
+      }
+    ]
+  }
+}

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

@@ -0,0 +1,279 @@
+{
+  "id": "market-scan",
+  "name": "Market & Landscape Scan",
+  "description": "Survey a market or landscape and write a scan that sizes it, maps the players, and surfaces trends: a planner scopes the market boundary and the lenses (size, segments, players, trends, drivers, risks), a researcher gathers sized figures and landscape facts with sources, and a copywriter writes a structured landscape report. The ordering matters because a scan without a defined boundary mixes adjacent markets and inflates numbers, and one without locked lenses skips the dimensions a decision-maker needs; fixing boundary and lenses first keeps the scan focused and comparable. Use this for market landscape scans, industry overviews, TAM/segmentation reads, trend analyses, and 'give me the lay of the land in X' requests.\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 scan (planner) — define the market boundary + analysis lenses → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. Gather landscape facts (researcher) — sized figures, players, and trends with sources → gated on artifact `{{workPath}}/findings.md` (markdown-notes)\n3. Write the scan (copywriter) — structured landscape report from the findings → gated on artifact `{{workPath}}/scan.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": [
+    "market scan",
+    "landscape overview",
+    "lay of the land",
+    "industry analysis",
+    "market sizing and trends"
+  ],
+  "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 scan",
+      "description": "define the market boundary + analysis lenses",
+      "prompt": "1. Define the market boundary precisely: what product/service category, geography, and timeframe — and state explicitly what adjacent markets are excluded. 2. Lock the lenses the scan will cover (e.g. market size & growth, key segments, major players/share, demand drivers, trends, risks/headwinds) and what each must contain. 3. Decide the report structure and where sized figures come from (state that figures must cite a source and a date). 4. Write an acceptance-criteria checklist (e.g. 'market boundary is stated and exclusions named', 'each lens has its own section', 'every sized figure cites a source + date', 'at least N notable players are mapped', 'a trends section with 3+ named trends exists'). 5. Record decisions. Call write_task_note with the boundary, lenses, and checklist; write the same to {{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": "research",
+      "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": "research",
+      "name": "Gather landscape facts",
+      "description": "sized figures, players, and trends with sources",
+      "prompt": "1. For each locked lens, gather concrete facts into {{workPath}}/findings.md: market size/growth figures (with the figure, the year, and the source [n]), the key segments, the notable players with what each is known for, the demand drivers, and 3+ named trends with evidence. 2. Cite every sized figure to a dated source; prefer recent, reputable data and reconcile conflicting numbers by noting the range and which source you trust. 3. Map at least the required number of players, each with a one-line positioning. 4. Flag estimates vs hard figures, and mark anything unverifiable as UNVERIFIED. Good looks like a findings file where each lens already has its evidence. Do not write the narrative yet.\n\nThe deliverable `{{workPath}}/findings.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": "researcher",
+      "advanceWhen": {
+        "file": "{{workPath}}/findings.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/findings.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/findings.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "research",
+        "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",
+          "workspace-fs-write"
+        ],
+        "outputMedium": "artifact"
+      }
+    },
+    {
+      "id": "write",
+      "name": "Write the scan",
+      "description": "structured landscape report from the findings",
+      "prompt": "1. Write {{workPath}}/scan.md with a section per locked lens: an opening that states the market boundary and exclusions, then size & growth, segments, players (a short table or list), drivers, trends, and risks. 2. Every sized figure carries its citation [n] and year; never state a number without a source. 3. Lead with the headline read of the market, then the supporting detail. 4. Close with a short 'so what' takeaway. 5. Add a References list from {{workPath}}/findings.md so every [n] resolves. 6. On a loop-back, fix only the named gaps. 7. Call write_task_note with the scan path and which criteria now pass.\n\nBefore working, open the artifact input `{{workPath}}/findings.md` with `read_artifact`; do not look for it in the workspace.\n\nThe deliverable `{{workPath}}/scan.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",
+      "consumes": [
+        {
+          "file": "{{workPath}}/findings.md",
+          "artifact": true
+        }
+      ],
+      "advanceWhen": {
+        "file": "{{workPath}}/scan.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/scan.md",
+            "bytes": 1500,
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "{{workPath}}/scan.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i",
+            "label": "at least one markdown heading",
+            "artifact": true
+          }
+        ],
+        "onReject": "write",
+        "maxAttempts": 4
+      },
+      "next": "evaluate",
+      "toolPolicy": {
+        "disallowBuiltinToolsets": [
+          "ai-apps",
+          "archives",
+          "audio",
+          "browser-automation",
+          "code-execution",
+          "craftbooks",
+          "data-tables",
+          "entity-intel",
+          "git",
+          "image-intel",
+          "images",
+          "role-delegation",
+          "role-delegation-escalation",
+          "security-intel",
+          "team-management",
+          "videos",
+          "web",
+          "workspace-fs-write"
+        ],
+        "outputMedium": "artifact",
+        "additionalOutputMedia": [
+          "task-note"
+        ]
+      }
+    },
+    {
+      "id": "evaluate",
+      "name": "Evaluate",
+      "description": "Grade the deliverable against every acceptance criterion. All pass → finish; any fail → loop back and fix the gap.",
+      "prompt": "Open {{workPath}}/scan.md and check EACH criterion PASS/FAIL: (1) the market boundary and exclusions are stated; (2) every locked lens has its own section; (3) every sized figure carries a source and year (spot-check 3 against {{workPath}}/findings.md); (4) at least the required number of players are mapped with positioning; (5) a trends section names 3+ trends with evidence; (6) a 'so what' takeaway exists. A scan that mixes adjacent markets or states unsourced figures FAILS.\n\nThe deliverable lives in the project's artifacts drawer — open `{{workPath}}/scan.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: \"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": "{{workPath}}/scan.md",
+          "artifact": true
+        }
+      ],
+      "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": "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/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"
+  ]
+}