@bendyline/gilde 0.1.37 → 0.1.39

package/data/craftbook-templates/ty/type-safety-pass/versions/1.0.2/test.json

@@ -0,0 +1,95 @@
+{
+  "schemaVersion": 1,
+  "title": "Type-Safety Pass smoke eval",
+  "objective": "Self-contained smoke eval for the Type-Safety Pass craftbook using the code generic harness.",
+  "tags": [
+    "code"
+  ],
+  "prompt": "We need a small Node helper for this — the requirments are in source/requirements.md. Put it in src/solution.mjs.",
+  "setup": {
+    "projectName": "Type-Safety Pass Eval",
+    "about": "Self-contained eval project for type-safety-pass. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/src/solution.mjs.",
+    "missionObjectives": "Use the Type-Safety Pass craftbook/template, read the seeded local fixtures, and write src/solution.mjs without network calls, real credentials, or live services.",
+    "files": [
+      {
+        "path": "source/brief.md",
+        "content": "# Type-Safety Pass 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: type-safety-pass - Type-Safety Pass.\n"
+      },
+      {
+        "path": "source/requirements.md",
+        "content": "# Runner Requirements\n\nBuild a dependency-free Node ESM helper for Boreal Desk support operations. Export at least one function. Include a tiny self-test section using node:assert or an equivalent assertion helper. Use fixture values for 18 -> 6 hour response time and 14.2 -> 8.9 refund leakage.\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Developer"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "src/solution.mjs is a local ESM module with basic self-test scaffolding.",
+    "deliverables": [
+      {
+        "path": "src/solution.mjs",
+        "kind": "code-with-tests",
+        "minBytes": 1500,
+        "checks": [
+          {
+            "kind": "esmImports",
+            "file": "src/solution.mjs"
+          },
+          {
+            "kind": "contains",
+            "file": "src/solution.mjs",
+            "pattern": "export\\s+(function|const|class)|export\\s*\\{",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "src/solution.mjs",
+            "pattern": "assert|test|describe|it|expect",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "src/solution.mjs",
+            "pattern": "18|6|14\\.2|8\\.9|Boreal",
+            "flags": "i"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "src/solution.mjs",
+      "kind": "typescript"
+    },
+    "axes": [
+      {
+        "name": "correctness",
+        "description": "The module does what the requirements ask, with sensible edge handling."
+      },
+      {
+        "name": "verification",
+        "description": "Self-tests exercise real behavior, not trivial truths."
+      },
+      {
+        "name": "clarity",
+        "description": "Exports, naming, and structure make the module usable without reading every line."
+      },
+      {
+        "name": "robustness",
+        "description": "Invalid input and boundary cases fail loudly rather than silently."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "runnable ESM",
+    "test scaffolding",
+    "local fixtures"
+  ]
+}

package/data/craftbook-templates/ve/version-bump/versions/1.0.2/craftbook.json

@@ -0,0 +1,167 @@
+{
+  "id": "version-bump",
+  "name": "Version Bump",
+  "description": "Perform a coordinated, semver-correct version bump across a project — deciding MAJOR/MINOR/PATCH from the actual change set, then updating every place the version is stamped in lockstep (package manifest(s), version constant, lockfile, badges, docs) plus the changelog header, so nothing drifts out of sync. A planner determines the correct semver level and enumerates every file that carries the version, a developer applies the bump everywhere consistently, and a reviewer verifies no location was missed and the new version is internally consistent. Use this when 'bumping the version', preparing a tag, or releasing a new package version where a half-applied bump (manifest says 2.0.0 but the constant says 1.9.0) is a classic ship bug.\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 bump (planner) — pick the semver level and enumerate every version-bearing file → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. Apply the bump (developer) — update every version location in lockstep → gated on `version-bump.json` (json)\n3. Verify consistency (reviewer) — confirm no location drifted and the bump is consistent → gated on artifact `{{workPath}}/verify.md` (markdown-notes)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "scope",
+  "triggers": [
+    "bump the version",
+    "release a new version",
+    "set version to 2.0.0",
+    "prepare a version tag",
+    "semver bump"
+  ],
+  "steps": [
+    {
+      "id": "scope",
+      "name": "Scope the bump",
+      "description": "pick the semver level and enumerate every version-bearing file",
+      "prompt": "1. Read the change set since the last release (changelog Unreleased, merged PRs, git log) and decide the semver level: MAJOR for any breaking/incompatible change, MINOR for new backward-compatible functionality, PATCH for backward-compatible fixes only — state the deciding change. 2. Compute the exact new version string from the current one (find the current version first; respect any pre-release/build suffix convention). 3. Enumerate EVERY location that stamps the version: package manifest(s) (and workspace members if a monorepo), any VERSION constant in source, the lockfile, README/docs badges, and the changelog header. 4. Note any inter-package version constraints that must move together. 5. Good looks like: the chosen new version with a one-line semver justification and a complete, file-by-file list of every place that must change with its current and target value. Write this as an acceptance-criteria checklist ('semver level matches the change set', 'every version-bearing file is listed with old→new', 'monorepo/peer constraints accounted for', 'changelog header updated to the new version') plus the analysis to the notes file via write_task_note AND 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": "bump"
+    },
+    {
+      "id": "bump",
+      "name": "Apply the bump",
+      "description": "update every version location in lockstep",
+      "prompt": "1. Open {{workPath}}/scope.md and update the version string in EVERY enumerated location to the exact target value — do not eyeball one and miss another. 2. Update package manifest(s) and any workspace members, the source VERSION constant, the lockfile (regenerate if the tooling requires it), docs/badges, and the changelog header. 3. Keep any pre-release/build suffix convention intact. 4. Do not change anything unrelated to the version stamp. 5. After editing, grep the repo for the OLD version string to confirm no stray occurrence remains (except historical changelog entries, which are correct to leave). 6. Produce a manifest of what changed: for each file, the path and the old→new version, plus the result of the stale-version grep. 7. Good looks like: every location from scope.md now reads the new version, the old version survives only in historical changelog entries, and the manifest records each edit. Write the change manifest (JSON with one entry per file) to version-bump.json.\n\nBefore working, open the artifact input `{{workPath}}/scope.md` with `read_artifact`; do not look for it in the workspace.",
+      "suggestedRole": "developer",
+      "consumes": [
+        {
+          "file": "{{workPath}}/scope.md",
+          "artifact": true
+        }
+      ],
+      "advanceWhen": {
+        "file": "version-bump.json",
+        "minBytes": 1,
+        "sniff": "json-valid"
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "version-bump.json",
+            "bytes": 2
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkJsonValid",
+            "scope": "standard",
+            "inputs": {
+              "file": "version-bump.json"
+            }
+          }
+        ],
+        "onReject": "bump",
+        "maxAttempts": 3
+      },
+      "next": "verify"
+    },
+    {
+      "id": "verify",
+      "name": "Verify consistency",
+      "description": "confirm no location drifted and the bump is consistent",
+      "prompt": "1. Open version-bump.json and confirm every file from {{workPath}}/scope.md was bumped to the SAME target version — no drift between manifest, constant, lockfile, and docs. 2. Independently grep the repo for both the old and the new version strings: the new version should appear in every expected place; the old version should remain only in historical changelog entries. 3. Verify the semver level still matches the change set described in scope.md. 4. Confirm the changelog header was updated and nothing unrelated changed. 5. Write a PASS/FAIL per acceptance criterion with the grep evidence, and list any missed or inconsistent location. 6. Any failure routes back to the bump phase. Write findings to {{workPath}}/verify.md.\n\nBefore working, open the artifact input `{{workPath}}/scope.md` with `read_artifact`; do not look for it in the workspace.\n\nThe deliverable `{{workPath}}/verify.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": "reviewer",
+      "consumes": [
+        {
+          "file": "{{workPath}}/scope.md",
+          "artifact": true
+        },
+        {
+          "file": "version-bump.json"
+        }
+      ],
+      "advanceWhen": {
+        "file": "{{workPath}}/verify.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "version-bump.json",
+            "bytes": 2
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkJsonValid",
+            "scope": "standard",
+            "inputs": {
+              "file": "version-bump.json"
+            }
+          }
+        ],
+        "onReject": "verify",
+        "maxAttempts": 4
+      },
+      "next": "evaluate"
+    },
+    {
+      "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 version-bump.json and verify it against {{workPath}}/scope.md, PASS/FAIL each criterion. Confirm: (a) it is valid JSON listing every version-bearing file from scope.md with an old→new entry; (b) every listed location carries the SAME new version (no drift between manifest, source constant, lockfile, docs); (c) the new version is semver-correct for the change set; (d) the changelog header reflects the new version; (e) the old version string survives only in historical changelog entries (verify with a grep). Any missed or inconsistent location routes back to the bump phase.\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: \"bump\" })` 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": "version-bump.json"
+        }
+      ],
+      "next": "bump"
+    },
+    {
+      "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
+    }
+  ],
+  "version": "1.0.2",
+  "releasedAt": "2026-08-21T00:00:00Z",
+  "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}}"
+      }
+    }
+  },
+  "minGezelVersion": "1.26233"
+}

package/data/craftbook-templates/ve/version-bump/versions/1.0.2/test.json

@@ -0,0 +1,95 @@
+{
+  "schemaVersion": 1,
+  "title": "Version Bump smoke eval",
+  "objective": "Self-contained smoke eval for the Version Bump craftbook using the code generic harness.",
+  "tags": [
+    "code"
+  ],
+  "prompt": "We need a small Node helper for this — the requirments are in source/requirements.md. Put it in src/solution.mjs.",
+  "setup": {
+    "projectName": "Version Bump Eval",
+    "about": "Self-contained eval project for version-bump. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/src/solution.mjs.",
+    "missionObjectives": "Use the Version Bump craftbook/template, read the seeded local fixtures, and write src/solution.mjs without network calls, real credentials, or live services.",
+    "files": [
+      {
+        "path": "source/brief.md",
+        "content": "# Version Bump 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: version-bump - Version Bump.\n"
+      },
+      {
+        "path": "source/requirements.md",
+        "content": "# Runner Requirements\n\nBuild a dependency-free Node ESM helper for Boreal Desk support operations. Export at least one function. Include a tiny self-test section using node:assert or an equivalent assertion helper. Use fixture values for 18 -> 6 hour response time and 14.2 -> 8.9 refund leakage.\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Developer"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "src/solution.mjs is a local ESM module with basic self-test scaffolding.",
+    "deliverables": [
+      {
+        "path": "src/solution.mjs",
+        "kind": "code-with-tests",
+        "minBytes": 1500,
+        "checks": [
+          {
+            "kind": "esmImports",
+            "file": "src/solution.mjs"
+          },
+          {
+            "kind": "contains",
+            "file": "src/solution.mjs",
+            "pattern": "export\\s+(function|const|class)|export\\s*\\{",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "src/solution.mjs",
+            "pattern": "assert|test|describe|it|expect",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "src/solution.mjs",
+            "pattern": "18|6|14\\.2|8\\.9|Boreal",
+            "flags": "i"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "src/solution.mjs",
+      "kind": "typescript"
+    },
+    "axes": [
+      {
+        "name": "correctness",
+        "description": "The module does what the requirements ask, with sensible edge handling."
+      },
+      {
+        "name": "verification",
+        "description": "Self-tests exercise real behavior, not trivial truths."
+      },
+      {
+        "name": "clarity",
+        "description": "Exports, naming, and structure make the module usable without reading every line."
+      },
+      {
+        "name": "robustness",
+        "description": "Invalid input and boundary cases fail loudly rather than silently."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "runnable ESM",
+    "test scaffolding",
+    "local fixtures"
+  ]
+}

package/data/craftbook-templates/vi/video-storyboard/versions/1.0.2/craftbook.json

@@ -0,0 +1,121 @@
+{
+  "id": "video-storyboard",
+  "name": "Video Storyboard from a Script",
+  "description": "Turn a video script into a shot-by-shot storyboard — each scene broken into shots with a framing sketch/description, camera direction, on-screen action, the matching script line, and timing — so a shoot or animation has a clear visual plan. Scopes the script into scenes and shot list FIRST, then designs each storyboard panel visually. The script-scope-then-storyboard ordering ensures every shot maps to a real script beat and the timing adds up to the script's runtime, instead of pretty panels that drift from the words.\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. Script scope & shot list (planner) — scenes, shot breakdown, timing, panel fields → gated on artifact `{{workPath}}/script-scope.md` (markdown-notes)\n2. Storyboard the shots (visual-designer) — render panels per shot: sketch/description + directions → gated on `storyboard.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": "script-scope",
+  "triggers": [
+    "storyboard my script",
+    "shot list from a script",
+    "video storyboard",
+    "plan the shots",
+    "visualize a video script"
+  ],
+  "steps": [
+    {
+      "id": "script-scope",
+      "name": "Script scope & shot list",
+      "description": "scenes, shot breakdown, timing, panel fields",
+      "prompt": "Break the script down BEFORE drawing. Step 1: read the script and segment it into scenes; record the script's total target runtime. Step 2: break each scene into shots, each mapped to specific script line(s) and an estimated duration so the shot durations sum to the runtime. Step 3: define the panel fields every storyboard cell must carry: shot number, framing (WS/MS/CU), camera move (static/pan/zoom), on-screen action, the script/VO line, and seconds. Step 4: number shots sequentially across scenes. Write an acceptance-criteria checklist (every script line maps to ≥1 shot, every shot has all panel fields, shot durations sum to ~the runtime, shots numbered sequentially, a clear opening and closing shot) and the shot list to `{{workPath}}/script-scope.md` via write_task_note AND the produces path.\n\nThe deliverable `{{workPath}}/script-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}}/script-scope.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/script-scope.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/script-scope.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "script-scope",
+        "maxAttempts": 3
+      },
+      "next": "storyboard"
+    },
+    {
+      "id": "storyboard",
+      "name": "Storyboard the shots",
+      "description": "render panels per shot: sketch/description + directions",
+      "prompt": "Produce the storyboard from the shot list as a single viewable `storyboard.html` (inline CSS). Step 1: render one panel per shot in script order, each panel showing a framing visual (an SVG/CSS sketch of the composition, or generate a thumbnail if image tools exist — show subject placement, headroom, rule-of-thirds) plus the shot number. Step 2: under each panel list the fields from scope: framing, camera move, on-screen action, the script/VO line, and the shot's seconds. Step 3: group panels by scene with scene headers, and show a running timecode. Step 4: keep a consistent panel template/aspect ratio across the whole board. Step 5: confirm it opens cleanly with no console error. write_task_note the path and panel count. On a loop-back, fix only the flagged panels (missing fields, wrong framing, timing that doesn't sum).",
+      "suggestedRole": "visual-designer",
+      "advanceWhen": {
+        "file": "storyboard.html",
+        "minBytes": 1,
+        "sniff": "html-complete"
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "storyboard.html",
+            "bytes": 1500
+          },
+          {
+            "kind": "htmlLint",
+            "file": "storyboard.html"
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkHtmlComplete",
+            "scope": "standard",
+            "inputs": {
+              "file": "storyboard.html"
+            }
+          }
+        ],
+        "onReject": "storyboard",
+        "maxAttempts": 4
+      },
+      "next": "evaluate"
+    },
+    {
+      "id": "evaluate",
+      "name": "Evaluate",
+      "description": "Grade the deliverable against every acceptance criterion. All pass → finish; any fail → loop back and fix the gap.",
+      "prompt": "Review the storyboard like a director. Step 1: open `storyboard.html` — it renders panels in order with no console error (PASS/FAIL). Step 2: confirm EVERY panel carries all fields (framing, camera move, action, script line, seconds) and a framing visual. Step 3: confirm every script line maps to at least one shot and shot durations sum to ~the script runtime. Step 4: confirm shots are numbered sequentially and grouped by scene with a running timecode. Step 5: confirm there is a clear opening and closing shot. Write PASS/FAIL per criterion.\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: \"storyboard\" })` 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": "storyboard.html"
+        }
+      ],
+      "next": "storyboard"
+    },
+    {
+      "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
+    }
+  ],
+  "version": "1.0.2",
+  "releasedAt": "2026-08-21T00:00:00Z",
+  "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}}"
+      }
+    }
+  },
+  "minGezelVersion": "1.26233"
+}

package/data/craftbook-templates/vi/video-storyboard/versions/1.0.2/test.json

@@ -0,0 +1,106 @@
+{
+  "schemaVersion": 1,
+  "title": "Video Storyboard from a Script smoke eval",
+  "objective": "Self-contained smoke eval for the Video Storyboard from a Script 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": "Video Storyboard from a Script Eval",
+    "about": "Self-contained eval project for video-storyboard. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/media-plan.json.",
+    "missionObjectives": "Use the Video Storyboard from a Script 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": "# Video Storyboard from a Script 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: video-storyboard - Video Storyboard from a Script.\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"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
+    }
+  },
+  "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": "video-storyboard-media-fixtures",
+        "kind": "data-source",
+        "status": "implemented",
+        "description": "Seeded local media index replacing real audio, video, image generation, and external media metadata services."
+      }
+    ]
+  }
+}