@bendyline/gilde 0.1.38 → 0.1.40

package/data/craftbook-templates/ex/expense-categorize/versions/1.0.2/craftbook.json

@@ -0,0 +1,152 @@
+{
+  "id": "expense-categorize",
+  "name": "Categorize Transactions",
+  "description": "Classify a list of bank/card transactions into a fixed chart-of-accounts category set, with confidence and a review queue for the uncertain ones, producing a clean categorized ledger ready for bookkeeping or tax. Locks the category taxonomy and the matching rules (merchant patterns, amount/sign heuristics) FIRST, then categorizes every transaction deterministically-first then by inference, then reviews that the taxonomy is closed, low-confidence rows are queued not force-fit, and totals reconcile to the input. Rules-before-categorize is the wisdom: a defined taxonomy plus rule precedence makes results auditable and repeatable, not a one-off guess.\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 rules (planner) — category taxonomy + matching rules + precedence → gated on artifact `{{workPath}}/rules-scope.md` (markdown-notes)\n2. Categorize transactions (developer) — apply rules, assign category + confidence, queue doubts → gated on `ledger.json` (json)\n3. Review the ledger (reviewer) — closed taxonomy, reconciliation, review queue → gated on artifact `{{workPath}}/review.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": "rules-scope",
+  "triggers": [
+    "categorize my transactions",
+    "sort expenses by category",
+    "clean up bank transactions",
+    "bookkeeping categorization",
+    "tag spending"
+  ],
+  "steps": [
+    {
+      "id": "rules-scope",
+      "name": "Scope the rules",
+      "description": "category taxonomy + matching rules + precedence",
+      "prompt": "Define the taxonomy and rules before categorizing. Step 1: load the transactions (date, description/merchant, amount, sign) and list the columns. Step 2: define the closed category set (the chart of accounts, e.g. Income, Office, Software, Travel, Meals, Utilities, Transfers, Uncategorized) — every transaction must land in exactly one. Step 3: define matching rules with precedence: explicit merchant→category patterns first, then heuristics (sign for income vs expense, amount bands, recurring-amount detection), and an Uncategorized fallback. Step 4: define the confidence rule and the review threshold (below which a row goes to a review queue rather than being force-categorized). Step 5: write an acceptance-criteria checklist ('every transaction categorized into exactly one in-set category', 'rule precedence applied deterministically', 'low-confidence rows queued for review', 'per-category totals reconcile to the input sum', 'no category invented outside the taxonomy'). Call write_task_note with taxonomy + rules + checklist and write {{workPath}}/rules-scope.md. No categorizing yet.\n\nThe deliverable `{{workPath}}/rules-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}}/rules-scope.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/rules-scope.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/rules-scope.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "rules-scope",
+        "maxAttempts": 3
+      },
+      "next": "categorize"
+    },
+    {
+      "id": "categorize",
+      "name": "Categorize transactions",
+      "description": "apply rules, assign category + confidence, queue doubts",
+      "prompt": "Categorize every transaction to the locked taxonomy. Step 1: for each transaction, apply the rules in precedence order — explicit merchant match first, then heuristics, then Uncategorized. Step 2: assign exactly one in-set category plus a confidence and a short reason (which rule fired). Step 3: route rows below the review threshold to a review queue flag rather than forcing a category. Step 4: produce the categorized ledger (the input columns plus category, confidence, reason, needs_review) in the chosen format. Step 5: compute per-category totals and a grand total and confirm the grand total equals the sum of the input amounts. Call write_task_note with the output path, the per-category totals, and the count of rows queued for review.",
+      "suggestedRole": "developer",
+      "advanceWhen": {
+        "file": "ledger.json",
+        "minBytes": 1,
+        "sniff": "json-valid"
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "ledger.json",
+            "bytes": 2
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkJsonValid",
+            "scope": "standard",
+            "inputs": {
+              "file": "ledger.json"
+            }
+          }
+        ],
+        "onReject": "categorize",
+        "maxAttempts": 3
+      },
+      "next": "review"
+    },
+    {
+      "id": "review",
+      "name": "Review the ledger",
+      "description": "closed taxonomy, reconciliation, review queue",
+      "prompt": "Review the categorized ledger against the rules scope. Step 1: confirm the file parses and every transaction has exactly one category drawn only from the closed taxonomy — no invented categories. Step 2: confirm rule precedence was applied — spot-check that explicit merchant matches beat heuristics. Step 3: confirm low-confidence rows are flagged needs_review rather than force-fit, and that the queue is non-empty if genuinely ambiguous rows exist. Step 4: confirm reconciliation — per-category totals sum to the grand total and the grand total equals the input sum (flag any penny drift). Step 5: spot-check 5 categorizations for correctness. Write PASS/FAIL per criterion to {{workPath}}/review.md and task notes; on failure, name the rows and loop back to categorize.\n\nThe deliverable `{{workPath}}/review.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",
+      "advanceWhen": {
+        "file": "{{workPath}}/review.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "ledger.json",
+            "bytes": 2
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkJsonValid",
+            "scope": "standard",
+            "inputs": {
+              "file": "ledger.json"
+            }
+          }
+        ],
+        "onReject": "review",
+        "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 ledger.json and verify every criterion from {{workPath}}/rules-scope.md. Confirm it parses, every transaction has exactly one category from the closed taxonomy (none invented), rule precedence held (explicit merchant matches beat heuristics — spot-check), low-confidence rows are flagged for review rather than force-fit, and totals reconcile (per-category sums equal the grand total which equals the input sum). Write PASS/FAIL per criterion; on any failure, name the rows and loop back to categorize.\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: \"categorize\" })` 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": "ledger.json"
+        }
+      ],
+      "next": "categorize"
+    },
+    {
+      "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/ex/expense-categorize/versions/1.0.2/test.json

@@ -0,0 +1,107 @@
+{
+  "schemaVersion": 1,
+  "title": "Categorize Transactions smoke eval",
+  "objective": "Self-contained smoke eval for the Categorize Transactions craftbook using the data generic harness.",
+  "tags": [
+    "data"
+  ],
+  "prompt": "I dropped our numbers in source/records.csv. Can you look at the data, analyze it, and put togehter some results in analysis.md?",
+  "setup": {
+    "projectName": "Categorize Transactions Eval",
+    "about": "Self-contained eval project for expense-categorize. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/analysis.md.",
+    "missionObjectives": "Use the Categorize Transactions craftbook/template, read the seeded local fixtures, and write analysis.md without network calls, real credentials, or live services.",
+    "files": [
+      {
+        "path": "source/brief.md",
+        "content": "# Categorize Transactions 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: expense-categorize - Categorize Transactions.\n"
+      },
+      {
+        "path": "source/records.csv",
+        "content": "customer,region,orders,revenue_usd,churn_risk\nAster,North,12,1440,low\nBoreal,South,8,720,medium\nCedar,West,15,2100,high\nDune,North,5,500,low\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Data Analyst"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "analysis.md is a seeded-data analysis with deterministic computed facts.",
+    "deliverables": [
+      {
+        "path": "analysis.md",
+        "kind": "markdown-report",
+        "minBytes": 900,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "analysis.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "analysis.md",
+            "pattern": "40\\b",
+            "flags": "i",
+            "label": "include total orders of 40"
+          },
+          {
+            "kind": "contains",
+            "file": "analysis.md",
+            "pattern": "\\$?4,?760\\b",
+            "flags": "i",
+            "label": "include total revenue of 4760"
+          },
+          {
+            "kind": "contains",
+            "file": "analysis.md",
+            "pattern": "Cedar",
+            "flags": "i",
+            "label": "identify Cedar as top revenue and high risk"
+          },
+          {
+            "kind": "contains",
+            "file": "analysis.md",
+            "pattern": "high",
+            "flags": "i",
+            "label": "include churn-risk finding"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "analysis.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": [
+    "seeded data reading",
+    "computed facts",
+    "recommendation grounding"
+  ]
+}

package/data/craftbook-templates/fa/fact-check/manifest.json

@@ -3,6 +3,7 @@
   "kind": "craftbook-template",
   "id": "fact-check",
   "role": "maintenance-review",
+  "category": "research",
   "name": "Fact-Check a Set of Claims",
   "description": "Verify a set of claims one by one and produce a verdict report: a planner extracts and itemizes every checkable claim and locks the rating scale, a researcher independently verifies each claim against primary sources and logs the evidence, and a reviewer compiles a per-claim verdict report with ratings and corrections. The ordering matters because verifying before itemizing lets claims slip through unchecked, and a report without a fixed rating scale gives inconsistent verdicts; isolating each atomic claim and locking the scale first makes the check exhaustive and auditable. Use this for fact-checking articles or statements, verifying claims, debunking, accuracy passes, and 'is this true' / 'check these facts' requests.",
   "tags": [

package/data/craftbook-templates/fa/fact-check/versions/1.0.2/craftbook.json

@@ -0,0 +1,158 @@
+{
+  "id": "fact-check",
+  "name": "Fact-Check a Set of Claims",
+  "description": "Verify a set of claims one by one and produce a verdict report: a planner extracts and itemizes every checkable claim and locks the rating scale, a researcher independently verifies each claim against primary sources and logs the evidence, and a reviewer compiles a per-claim verdict report with ratings and corrections. The ordering matters because verifying before itemizing lets claims slip through unchecked, and a report without a fixed rating scale gives inconsistent verdicts; isolating each atomic claim and locking the scale first makes the check exhaustive and auditable. Use this for fact-checking articles or statements, verifying claims, debunking, accuracy passes, and 'is this true' / 'check these facts' 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. Claim scope (planner) — itemize every checkable claim + lock the rating scale → gated on artifact `{{workPath}}/claim-scope.md` (markdown-notes)\n2. Verify each claim (researcher) — independently check each claim against primary sources → gated on artifact `{{workPath}}/evidence.md` (markdown-notes)\n3. Compile the verdict report (reviewer) — per-claim ratings, evidence, and corrections → gated on artifact `{{workPath}}/factcheck.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": "claim-scope",
+  "triggers": [
+    "fact-check this",
+    "verify these claims",
+    "is this true",
+    "check these facts",
+    "debunk or confirm"
+  ],
+  "steps": [
+    {
+      "id": "claim-scope",
+      "name": "Claim scope",
+      "description": "itemize every checkable claim + lock the rating scale",
+      "prompt": "1. Read the source material and extract EVERY discrete, checkable factual claim into {{workPath}}/claim-scope.md, each as one atomic statement with an id (C1, C2, ...) — split compound sentences into separate claims and quote the original wording. 2. Mark each claim's type (statistic, attribution, event, causal, definitional) since that drives how it is verified. 3. Lock the rating scale exactly (e.g. True / Mostly True / Mixed / Mostly False / False / Unverifiable) and define each rating. 4. Write an acceptance-criteria checklist (e.g. 'every claim from the source is itemized with an id', 'each claim gets exactly one rating from the locked scale', 'each rating cites at least one independent source', 'false/mixed claims include a correction'). 5. Record decisions. Call write_task_note with the claim list + scale + checklist; write the same to {{workPath}}/claim-scope.md.\n\nThe deliverable `{{workPath}}/claim-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}}/claim-scope.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/claim-scope.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/claim-scope.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "claim-scope",
+        "maxAttempts": 3
+      },
+      "next": "verify"
+    },
+    {
+      "id": "verify",
+      "name": "Verify each claim",
+      "description": "independently check each claim against primary sources",
+      "prompt": "1. For each claim id, independently verify it against authoritative, primary sources — do NOT trust the source being checked. 2. Log to {{workPath}}/evidence.md per claim: the id, the source(s) [n] you checked, the exact figure/quote/fact found, whether it confirms, contradicts, or partially supports the claim, and a proposed rating from the locked scale. 3. For numeric or attribution claims, find the original record (the dataset, the filing, the transcript), not a secondary report. 4. If a claim cannot be verified after a genuine search, rate it Unverifiable and say what evidence would settle it. 5. Where a claim is false or mixed, capture the correct fact so the report can state the correction. Good looks like an evidence log where each claim's rating is already justified. Do not write the final report yet.\n\nThe deliverable `{{workPath}}/evidence.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}}/evidence.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/evidence.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/evidence.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "verify",
+        "maxAttempts": 3
+      },
+      "next": "report"
+    },
+    {
+      "id": "report",
+      "name": "Compile the verdict report",
+      "description": "per-claim ratings, evidence, and corrections",
+      "prompt": "1. Write {{workPath}}/factcheck.md with a short summary (counts per rating) then one entry per claim id, in order: the quoted claim, its rating from the locked scale, a one-to-three-sentence justification, the supporting source(s) [n], and — for any False/Mixed claim — the correct statement. 2. Use ONLY ratings from the locked scale and base each strictly on {{workPath}}/evidence.md; do not introduce new claims or change wordings. 3. Add a References list so every [n] resolves to a real, independent source. 4. Keep verdicts dispassionate and evidence-first. 5. On a loop-back, fix only the named gaps. 6. Call write_task_note with the report path and which criteria now pass.\n\nBefore working, open the artifact input `{{workPath}}/evidence.md` with `read_artifact`; do not look for it in the workspace.\n\nThe deliverable `{{workPath}}/factcheck.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}}/evidence.md",
+          "artifact": true
+        }
+      ],
+      "advanceWhen": {
+        "file": "{{workPath}}/factcheck.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/factcheck.md",
+            "bytes": 1500,
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "{{workPath}}/factcheck.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i",
+            "label": "at least one markdown heading",
+            "artifact": true
+          }
+        ],
+        "onReject": "report",
+        "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 {{workPath}}/factcheck.md and check EACH criterion PASS/FAIL: (1) every claim id from {{workPath}}/claim-scope.md has an entry — none dropped; (2) each entry has exactly one rating drawn from the locked scale; (3) each rating cites at least one independent source that is NOT the material being checked; (4) every False/Mixed claim includes a correction; (5) spot-check 3 verdicts against {{workPath}}/evidence.md to confirm the rating matches the logged evidence; (6) the summary counts match the entries. A report that rates a claim against the source it came from, or skips a claim, FAILS.\n\nThe deliverable lives in the project's artifacts drawer — open `{{workPath}}/factcheck.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: \"report\" })` 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}}/factcheck.md",
+          "artifact": true
+        }
+      ],
+      "next": "report"
+    },
+    {
+      "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/fa/fact-check/versions/1.0.2/test.json

@@ -0,0 +1,113 @@
+{
+  "schemaVersion": 1,
+  "title": "Fact-Check a Set of Claims smoke eval",
+  "objective": "Self-contained smoke eval for the Fact-Check a Set of Claims craftbook using the corpus generic harness.",
+  "tags": [
+    "corpus"
+  ],
+  "prompt": "We need a fact-check a set of claims 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": "Fact-Check a Set of Claims Eval",
+    "about": "Self-contained eval project for fact-check. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/report.md.",
+    "missionObjectives": "Use the Fact-Check a Set of Claims 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": "# Fact-Check a Set of Claims 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: fact-check - Fact-Check a Set of Claims.\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Writer"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
+    }
+  },
+  "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/fa/family-story-chapter/manifest.json

@@ -3,6 +3,7 @@
   "kind": "craftbook-template",
   "id": "family-story-chapter",
   "role": "general",
+  "category": "writing",
   "name": "Family Story Chapter",
   "description": "Write one chapter of the family story from the record you actually have — interviews and tree facts woven into narrative, speculation clearly dressed as speculation — the ritual that turns an archive into the book every family means to write. Locks the chapter's arc and the sourcing rules FIRST, then drafts from the record only, with a faithfulness pass that loops until every event traces. Use for drafting a family history chapter, writing up the emigration years, turning interviews into narrative, and 'write the family story'.",
   "tags": [

package/data/craftbook-templates/fa/family-story-chapter/versions/1.0.2/craftbook.json

@@ -0,0 +1,86 @@
+{
+  "id": "family-story-chapter",
+  "name": "Family Story Chapter",
+  "description": "Write one chapter of the family story from the record you actually have — interviews and tree facts woven into narrative, speculation clearly dressed as speculation — the ritual that turns an archive into the book every family means to write. Locks the chapter's arc and the sourcing rules FIRST, then drafts from the record only, with a faithfulness pass that loops until every event traces. Use for drafting a family history chapter, writing up the emigration years, turning interviews into narrative, and 'write the family story'.\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 chapter (editor) — arc from the interviews and tree, sourcing rules, target file → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. Draft the chapter (writer) — the chapter under chapters/, sourced material only\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "scope",
+  "triggers": [
+    "write the family story chapter",
+    "draft the emigration chapter",
+    "turn the interviews into narrative",
+    "family history chapter",
+    "write up the family story"
+  ],
+  "steps": [
+    {
+      "id": "scope",
+      "name": "Scope the chapter",
+      "description": "arc from the interviews and tree, sourcing rules, target file",
+      "prompt": "Choose the chapter's arc from the record you actually have. Step 1: read tree.json and every file under interviews/ (plus any photo caption notes) — where is the material thick enough to carry a chapter, and what does the owner want told first. Step 2: fix the arc — the years, the people, and the journey it covers, and where it opens and closes. Step 3: lock the writing rules: every concrete event traces to an interview or a tree fact; quotes from the tellers stay verbatim; speculation is allowed only when dressed as speculation ('family legend has it', 'she may have') and never load-bearing; where the record is silent, the silence is acknowledged. Step 4: write the acceptance-criteria checklist from those rules, name the chapter file under chapters/ (the path the owner asks for, or chapters/<slug>.md named for the arc), and call write_task_note with the arc. Write {{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": "editor",
+      "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": "draft"
+    },
+    {
+      "id": "draft",
+      "name": "Draft the chapter",
+      "description": "the chapter under chapters/, sourced material only",
+      "prompt": "Write the chapter from the record. Step 1: gather everything in the interviews and the tree that belongs to the locked arc — events, dates, places, and the tellers' own words. Step 2: write the chapter as narrative — real prose with warmth and momentum — but built only from sourced material; let the tellers' verbatim phrases carry the voice. Step 3: dress every speculation as speculation, in the phrasings locked in scope. Step 4: where the record has a hole the story needs, acknowledge it on the page — an honest 'no one now remembers' is part of a family story. Step 5: save the chapter under chapters/ at the path locked in scope, make it substantial (a real chapter, not an outline), and call write_task_note with the word count.",
+      "suggestedRole": "writer",
+      "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 the chapter beside the interviews and tree.json and verify every criterion from {{workPath}}/scope.md: pick five concrete events or dates in the chapter and trace each to an interview or the tree — anything untraceable is invented and fails the whole pass; quotes are verbatim (check two); every speculative line is explicitly dressed as speculation; holes in the record are acknowledged rather than filled. Write PASS/FAIL per criterion; on any failure, name the invented detail or missed criterion and loop back to draft.\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: \"draft\" })` to loop back. The builder fixes exactly those gaps.\n\nNever route to `finish` while any criterion is unmet. If you advance without a target, the loop sends you back by design. After ~3 unproductive loops, stop and report DONE_WITH_CONCERNS so the user can step in.",
+      "suggestedRole": "reviewer",
+      "next": "draft"
+    },
+    {
+      "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"
+}