@bendyline/gilde 0.1.50 → 0.1.52

package/data/craftbook-templates/da/data-to-report/versions/1.0.3/craftbook.json

@@ -0,0 +1,277 @@
+{
+  "id": "data-to-report",
+  "name": "Dataset to Narrative Report",
+  "description": "Turn a dataset into a written, evidence-backed analytical report that a non-technical reader can act on. Analyzes the data FIRST to surface the real findings (key metrics, segments, trends, surprises) with supporting numbers, then writes a narrative that leads with the takeaway and traces every claim to a figure, then builds the polished report document with sections, a summary table, and an explicit limitations note. Use this for turning raw numbers into an insights report, executive summary, data storytelling, or a findings write-up stakeholders will read.\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. Analyze the data (data-analyst) — extract the real findings with supporting numbers → gated on artifact `{{workPath}}/analyze.md` (markdown-notes)\n2. Write the narrative (copywriter) — draft a takeaway-led narrative grounded in the figures → gated on artifact `{{workPath}}/write.md` (markdown-notes)\n3. Build the report (developer) — assemble the polished {{workPath}}/report.md with sections and a summary table → gated on artifact `{{workPath}}/report.md` (markdown-report)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "analyze",
+  "triggers": [
+    "turn data into a report",
+    "analyze this dataset",
+    "write a findings report",
+    "data insights writeup",
+    "executive summary from data"
+  ],
+  "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": "analyze",
+      "name": "Analyze the data",
+      "description": "extract the real findings with supporting numbers",
+      "prompt": "Interrogate the dataset to find what actually matters — do not write prose yet. Step 1: state the 3-5 questions the report should answer (totals, trends over time, top/bottom segments, notable correlations or anomalies). Step 2: compute the answer to each with concrete numbers (counts, means, %, deltas, top-N) and record the exact figure plus how you derived it. Step 3: identify the single most important takeaway and 2-3 supporting findings, each tied to a number. Step 4: note data caveats (sample size, missing periods, definitions). Step 5: write an acceptance-criteria checklist for the report ('leads with the headline finding', 'every claim cites a number', 'includes a summary table', 'states limitations'). Call write_task_note and write the findings + figures + checklist to {{workPath}}/analyze.md. No narrative prose yet.\n\nThe deliverable `{{workPath}}/analyze.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": "data-analyst",
+      "advanceWhen": {
+        "file": "{{workPath}}/analyze.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/analyze.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/analyze.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "analyze",
+        "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 narrative",
+      "description": "draft a takeaway-led narrative grounded in the figures",
+      "prompt": "Write the report narrative using ONLY the figures from the analysis note — invent no numbers. Step 1: open with a 2-3 sentence executive summary that states the headline finding and its 'so what'. Step 2: write one short section per supporting finding; each paragraph states the insight, then the number that proves it, then the implication. Step 3: keep it scannable — short paragraphs, plain language, no jargon a manager wouldn't use. Step 4: end with a clearly labeled 'Limitations' paragraph from the caveats. Call write_task_note with the draft keyed by section so the build phase drops it straight in.\n\nThe deliverable `{{workPath}}/write.md` lands in the project's artifacts drawer — write it with `write_artifact` and read it back with `read_artifact`; the shipped workspace stays untouched.",
+      "suggestedRole": "copywriter",
+      "advanceWhen": {
+        "file": "{{workPath}}/write.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/write.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/write.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "write",
+        "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 the report",
+      "description": "assemble the polished {{workPath}}/report.md with sections and a summary table",
+      "prompt": "Assemble the final report as {{workPath}}/report.md. Step 1: add a title, a date, and an Executive Summary section from the approved narrative. Step 2: add one ## section per finding with the prose and inline figures. Step 3: include a Markdown summary table of the key metrics (metric, value, change). Step 4: add a Methodology / Data notes section and a Limitations section. Step 5: ensure every numeric claim in the prose matches the analysis note. On a loop-back, fix only the named gaps. Call write_task_note with the report path and section list.\n\nThe deliverable `{{workPath}}/report.md` lands in the project's artifacts drawer — write it with `write_artifact` and read it back with `read_artifact`; the shipped workspace stays untouched.",
+      "suggestedRole": "developer",
+      "advanceWhen": {
+        "file": "{{workPath}}/report.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/report.md",
+            "bytes": 1500,
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "{{workPath}}/report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i",
+            "label": "at least one markdown heading",
+            "artifact": true
+          }
+        ],
+        "onReject": "build",
+        "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": "Read {{workPath}}/report.md as a stakeholder would. Verify: it opens with a takeaway-led executive summary; every numeric claim matches a figure in the analysis note (re-check at least three); it contains a summary table of key metrics; section headers organize it; and a Limitations section is present and honest. Confirm no fabricated numbers and no claim without a supporting figure. Write PASS/FAIL per acceptance criterion; any FAIL loops back to build.\n\nThe deliverable lives in the project's artifacts drawer — open `{{workPath}}/report.md` with `read_artifact`, not `read_file`.\n\nThen route — this is the whole point of the loop:\n\n- **Every criterion PASSES →** call `advance_task_step({ ref, stepId: \"evaluate\", next: \"finish\" })`.\n- **Any criterion FAILS →** write the specific gaps to notes, then call `advance_task_step({ ref, stepId: \"evaluate\", next: \"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": "{{workPath}}/report.md",
+          "artifact": true
+        }
+      ],
+      "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": "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/da/data-to-report/versions/1.0.3/test.json

@@ -0,0 +1,98 @@
+{
+  "schemaVersion": 1,
+  "title": "Executive report from seeded data",
+  "objective": "Measure whether the data-to-report craftbook analyzes seeded data first and produces a narrative report grounded in computed figures.",
+  "tags": [
+    "data"
+  ],
+  "prompt": "In the `Data to Report Eval` project, read `data/returns-summary.csv` and write `tasks/eval/report.md`: an executive report for support leadership. Include an executive summary, key metrics table, findings, segment trends, recommendations, and limitations. Ground every claim in the seeded figures.",
+  "setup": {
+    "projectName": "Data to Report Eval",
+    "about": "Self-contained eval project for the data-to-report craftbook. The dataset is workspace/data/returns-summary.csv.",
+    "missionObjectives": "Write an executive analytical report from seeded data with summary, metrics table, findings, recommendations, and limitations.",
+    "files": [
+      {
+        "path": "data/returns-summary.csv",
+        "content": "month,region,return_rate,refund_leakage,response_hours,escalations\nMarch,West,0.112,0.142,18,44\nApril,West,0.108,0.101,9,31\nMay,West,0.099,0.089,6,25\nMarch,East,0.087,0.096,15,21\nApril,East,0.091,0.094,13,24\nMay,East,0.088,0.092,12,22\n"
+      }
+    ],
+    "worker": {
+      "name": "Mats",
+      "role": "Data Analyst"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "workspace/report.md is a narrative analytical report with metrics table, findings, recommendations, and limitations grounded in seeded data.",
+    "deliverables": [
+      {
+        "path": "tasks/eval/report.md",
+        "kind": "markdown-report",
+        "minBytes": 2200,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "Executive summary|Key metrics|Findings|Recommendations|Limitations",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "March|April|May|West|East"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "14\\.2%|8\\.9%|18|6|44|25",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "refund leakage|response hours|escalations|return rate",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "table|\\|",
+            "flags": "i"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "tasks/eval/report.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": [
+    "analysis before narrative",
+    "source-grounded figures",
+    "limitations"
+  ]
+}

package/data/craftbook-templates/da/data-viz-page/versions/1.0.2/test.json

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

package/data/craftbook-templates/da/data-viz-page/versions/1.0.3/craftbook.json

@@ -0,0 +1,281 @@
+{
+  "id": "data-viz-page",
+  "name": "Data Visualization Explorer",
+  "description": "Build a single interactive chart or data explorer page — bar, line, scatter, or pie — driven by sample or provided data, with controls to filter, switch series, or change the dimension and a tooltip on hover. Scopes the dataset and the question the chart answers first, then the chart type and encodings, then implements a canvas or SVG chart with real interactivity. A chart that does not map data to pixels correctly is worse than a table, so the data and chart-design phases lock the encoding and the axes before any rendering code.\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. Data scope (planner) — dataset shape + the question the chart answers → gated on artifact `{{workPath}}/data-scope.md` (markdown-notes)\n2. Chart design (designer) — chart type, encodings, axes, legend, tooltip → gated on artifact `{{workPath}}/chart-design.md` (markdown-notes)\n3. Build (developer) — implement index.html with the interactive chart → gated on `index.html` (html-page)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "data-scope",
+  "triggers": [
+    "data visualization",
+    "interactive chart",
+    "data explorer",
+    "build a chart",
+    "visualize data",
+    "graph page"
+  ],
+  "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": "data-scope",
+      "name": "Data scope",
+      "description": "dataset shape + the question the chart answers",
+      "prompt": "Scope the data and the question. (1) Define the dataset shape (fields, types) and embed a realistic sample array if none is provided. (2) State the ONE question the chart answers (e.g. 'how do sales trend by month?'). (3) Identify the dimension(s) and measure(s) to plot and any aggregation. (4) Decide the interactive controls (filter, series toggle, dimension switch) and the hover tooltip content. (5) Write an acceptance-criteria checklist of 5-8 items, e.g. 'the chart renders from the data', 'axes are labeled with correct scales', 'a hover tooltip shows the underlying value', 'a control filters or switches the view and the chart updates', 'responsive', 'no console errors'. Write to {{workPath}}/data-scope.md and via write_task_note. No chart code yet.\n\nThe deliverable `{{workPath}}/data-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}}/data-scope.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/data-scope.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/data-scope.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "data-scope",
+        "maxAttempts": 3
+      },
+      "next": "chart-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": "chart-design",
+      "name": "Chart design",
+      "description": "chart type, encodings, axes, legend, tooltip",
+      "prompt": "Design the chart precisely. (1) Choose the chart type that fits the question and justify it in one line. (2) Map each variable to a visual channel (x, y, color, size) and define the axis scales and ranges. (3) Specify the legend, gridlines, color palette (hex), and the tooltip layout. (4) Design the control affordances (dropdown/buttons) and the empty/loading state. (5) Self-contained — canvas or inline SVG, no chart-library CDN. Write the visual spec to {{workPath}}/chart-design.md and via write_task_note. No HTML yet.\n\nThe deliverable `{{workPath}}/chart-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": "designer",
+      "advanceWhen": {
+        "file": "{{workPath}}/chart-design.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/chart-design.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/chart-design.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "chart-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 index.html with the interactive chart",
+      "prompt": "Implement index.html with inline CSS/JS to the chart and data scope. (1) Embed the data and compute scales mapping data values to pixel coordinates correctly (mind the inverted y-axis). (2) Render the chart with labeled axes, gridlines, and a legend via canvas or SVG. (3) Implement the hover tooltip showing the underlying value at the cursor's data point. (4) Wire the controls so changing them recomputes and re-renders the chart. (5) Make it responsive; vanilla JS, no CDN. Verify a couple of plotted points sit at the right coordinates. 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": 800
+          },
+          {
+            "kind": "htmlLint",
+            "file": "index.html"
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkHtmlComplete",
+            "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": "Evaluate the explorer. Open/render index.html, hover for tooltips, and operate every control. Check EACH criterion from {{workPath}}/data-scope.md and write PASS/FAIL with a reason: does the chart render from the data, are axes labeled with correct scales, does the tooltip show the right underlying value, does a control update the chart, is it responsive, zero console errors? Verify one data point's screen position against its value by hand — a mis-scaled axis is a FAIL, loop back to build.\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"
+}