@bendyline/gilde 0.1.50 → 0.1.52

package/data/craftbook-templates/da/data-quality-audit/versions/1.0.3/craftbook.json

@@ -0,0 +1,277 @@
+{
+  "id": "data-quality-audit",
+  "name": "Data Quality Audit",
+  "description": "Audit a dataset against explicit data-quality rules and produce a scorecard of where it passes and fails across completeness, validity, consistency, uniqueness, and timeliness. Defines the quality rules and dimensions FIRST (so 'quality' is measurable, not a vibe), then runs the audit to measure each rule with pass rates and failing examples, then writes a prioritized report with an overall score and remediation steps. Use this for a data quality audit, data health check, validation report, data-quality scorecard, or assessing whether a dataset is trustworthy.\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. Define quality rules (data-analyst) — lock the dimensions, rules, and thresholds for 'good' → gated on artifact `{{workPath}}/rules.md` (markdown-notes)\n2. Run the audit (developer) — measure every rule and emit pass rates with failing examples → gated on `data/audit.json` (json)\n3. Report the audit (copywriter) — write a prioritized scorecard with remediation steps → 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": "rules",
+  "triggers": [
+    "audit data quality",
+    "data health check",
+    "is this data trustworthy",
+    "data quality scorecard",
+    "validate a dataset"
+  ],
+  "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": "rules",
+      "name": "Define quality rules",
+      "description": "lock the dimensions, rules, and thresholds for 'good'",
+      "prompt": "Make data quality measurable before auditing. Step 1: choose the quality dimensions in scope — completeness (no missing required fields), validity (values match type/format/domain), consistency (cross-field logic, e.g. end_date >= start_date), uniqueness (no dupes on the key), timeliness (recency), and accuracy/referential integrity where checkable. Step 2: write concrete, testable rules per dimension naming the exact columns ('email matches an email regex', 'status in {active,churned,trial}', 'no duplicate customer_id'). Step 3: set a pass-rate threshold per rule (e.g. >= 99% non-null) and a weighting for the overall score. Step 4: write an acceptance-criteria checklist ('every dimension has at least one testable rule', 'each rule names its columns and threshold', 'audit reports a pass rate + failing examples per rule', 'an overall weighted score is produced'). Call write_task_note and write the rules + thresholds + weights + checklist to {{workPath}}/rules.md. No auditing yet.\n\nThe deliverable `{{workPath}}/rules.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}}/rules.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/rules.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/rules.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "rules",
+        "maxAttempts": 3
+      },
+      "next": "audit",
+      "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": "audit",
+      "name": "Run the audit",
+      "description": "measure every rule and emit pass rates with failing examples",
+      "prompt": "Run every quality rule against the full dataset deterministically. Step 1: for each rule, evaluate all rows and compute the pass rate (rows passing / total) and the count of failures. Step 2: capture up to 5 concrete failing examples per rule (the row id + the offending value) so the report can show evidence. Step 3: compare each pass rate to its threshold and mark the rule pass/fail. Step 4: compute the overall weighted quality score from the rule results and the weights. Step 5: emit data/audit.json — per-rule { dimension, rule, pass_rate, threshold, status, failing_examples } plus the overall score and a per-dimension rollup. Call write_task_note with the overall score and the worst rules.",
+      "suggestedRole": "developer",
+      "advanceWhen": {
+        "file": "data/audit.json",
+        "minBytes": 1,
+        "sniff": "json-valid"
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "data/audit.json",
+            "bytes": 2
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkJsonValid",
+            "scope": "standard",
+            "inputs": {
+              "file": "data/audit.json"
+            }
+          }
+        ],
+        "onReject": "audit",
+        "maxAttempts": 3
+      },
+      "next": "report",
+      "toolPolicy": {
+        "disallowBuiltinToolsets": [
+          "ai-apps",
+          "archives",
+          "artifacts",
+          "audio",
+          "browser-automation",
+          "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": "report",
+      "name": "Report the audit",
+      "description": "write a prioritized scorecard with remediation steps",
+      "prompt": "Write the data-quality report from the audit results — use only measured numbers. Step 1: open with the overall score and a one-line verdict on trustworthiness. Step 2: show a scorecard table: dimension, rule, pass rate, threshold, pass/fail. Step 3: detail the failing rules worst-first, each with its pass rate and 1-2 failing examples as evidence. Step 4: give a prioritized remediation list (fix the highest-impact, lowest-effort failures first) with a concrete action per failing rule. Step 5: note any rule that couldn't be evaluated and why. Write the report to {{workPath}}/report.md and call write_task_note with the path and overall score. On a loop-back, fix only the named gaps.\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": "copywriter",
+      "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": "report",
+        "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 and cross-check against {{workPath}}/rules.md and data/audit.json. Verify: every quality dimension has at least one testable rule; each rule reports a pass rate against its threshold with a pass/fail; failing rules show concrete failing examples as evidence; an overall weighted score is reported; and remediation steps are prioritized and concrete. Re-compute one rule's pass rate against the audit data to confirm. Confirm no rule is marked passing while its examples show failures. Write PASS/FAIL per criterion; any FAIL loops back to report.\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: \"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}}/report.md",
+          "artifact": true
+        }
+      ],
+      "next": "report",
+      "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-quality-audit/versions/1.0.3/test.json

@@ -0,0 +1,329 @@
+{
+  "schemaVersion": 1,
+  "title": "Data quality scorecard over seeded customer CSV",
+  "objective": "Measure whether the data-quality-audit craftbook defines measurable rules, emits audit JSON, and reports score/remediation with examples.",
+  "tags": [
+    "data"
+  ],
+  "prompt": "In the `Data Quality Audit Eval` project, read `data/customers.csv` and `data/quality-rules.md`, then write `data/audit.json` and `tasks/eval/report.md`. Apply the seeded rules exactly: audit date, required fields, allowed statuses, email format, date consistency, duplicate customer IDs, and stale last_seen threshold. The JSON must include summary.total_records equal to the CSV data row count, per-dimension pass_rate values, failing_examples, and overall_score. The report must cover completeness, validity, consistency, uniqueness, timeliness, overall score, failing examples, and prioritized remediation.",
+  "setup": {
+    "projectName": "Data Quality Audit Eval",
+    "about": "Self-contained eval project for data-quality-audit. Source data is workspace/data/customers.csv and deterministic audit rules are in workspace/data/quality-rules.md.",
+    "missionObjectives": "Produce a measured data-quality scorecard using the seeded rule file, with JSON audit data, per-dimension pass rates, failing examples, overall score, and remediation plan.",
+    "files": [
+      {
+        "path": "data/customers.csv",
+        "content": "customer_id,email,status,start_date,end_date,last_seen\nC-001,ana@example.com,active,2026-01-10,,2026-06-20\nC-002,,trial,2026-02-02,,2026-02-02\nC-003,bad-email,active,2026-03-01,,2026-06-18\nC-004,lee@example.com,churned,2026-01-15,2025-12-31,2026-01-20\nC-004,lee.dup@example.com,active,2026-01-15,,2026-06-12\nC-005,maya@example.com,pending,2026-04-01,,2026-04-02\n"
+      },
+      {
+        "path": "data/quality-rules.md",
+        "content": "# Data quality rules\n\nAudit as of: 2026-06-28.\n\nRequired fields: customer_id, email, status, start_date, last_seen.\nAllowed status values: active, trial, churned. Treat any other status as invalid.\nEmail validity: an email must contain exactly one @ and a dotted domain.\nDate consistency: if end_date is present, it must be on or after start_date.\nUniqueness: customer_id must be unique across rows.\nTimeliness: active or trial records are stale when last_seen is more than 60 days before the audit date. Invalid-status records should still be assessed for timeliness.\nOverall score: report the percentage of rule checks that passed and name it overall_score in data/audit.json.\n\nExpected minimum failing examples to find: C-002 missing email and stale last_seen; C-003 invalid email; C-004 duplicate customer_id and impossible end_date; C-005 invalid status and stale last_seen.\n"
+      }
+    ],
+    "worker": {
+      "name": "Oda",
+      "role": "Data Analyst"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "workspace/report.md and data/audit.json apply the seeded audit rules with per-dimension pass rates, failing examples, overall score, and remediation.",
+    "deliverables": [
+      {
+        "path": "tasks/eval/report.md",
+        "kind": "markdown-report",
+        "minBytes": 2200,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "completeness",
+            "flags": "i",
+            "label": "include a completeness section/result"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "validity",
+            "flags": "i",
+            "label": "include a validity section/result"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "consistency",
+            "flags": "i",
+            "label": "include a consistency section/result"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "uniqueness",
+            "flags": "i",
+            "label": "include a uniqueness section/result"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "timeliness|stale|last_seen",
+            "flags": "i",
+            "label": "include timeliness results"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "2026-06-28",
+            "flags": "i",
+            "label": "include the seeded audit date"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "6\\s+records|Total Records\\s*\\|\\s*6",
+            "flags": "i",
+            "label": "use the six CSV rows"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "C-002",
+            "flags": "i",
+            "label": "include C-002 as a failing example"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "C-003",
+            "flags": "i",
+            "label": "include C-003 as a failing example"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "C-004",
+            "flags": "i",
+            "label": "include C-004 as a failing example"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "C-005",
+            "flags": "i",
+            "label": "include C-005 as a failing example"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "C-005[\\s\\S]{0,220}(pending|invalid status|status)|pending[\\s\\S]{0,220}C-005",
+            "flags": "i",
+            "label": "include C-005 invalid pending status, not only stale last_seen"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "pass rate|pass_rate",
+            "flags": "i",
+            "label": "include pass rates"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "overall(?:\\s+data\\s+quality)?\\s+score|overall_score",
+            "flags": "i",
+            "label": "include an explicit overall score"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "failing examples?",
+            "flags": "i",
+            "label": "include a failing examples section"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "remediation|priority|fix",
+            "flags": "i"
+          },
+          {
+            "kind": "notContains",
+            "file": "tasks/eval/report.md",
+            "pattern": "first_name|last_name|john@doe|90[- ]day|90\\s+days|2024-\\d\\d-\\d\\d|\\b7\\s+records\\b|\\d\\s*/\\s*7\\b",
+            "flags": "i",
+            "label": "avoid invented columns, values, thresholds, and audit dates not in the seeded rules"
+          }
+        ]
+      },
+      {
+        "path": "data/audit.json",
+        "kind": "json",
+        "minBytes": 700,
+        "checks": [
+          {
+            "kind": "sniff",
+            "file": "data/audit.json",
+            "sniff": "json-valid"
+          },
+          {
+            "kind": "jsonPathEquals",
+            "file": "data/audit.json",
+            "path": "audit_date",
+            "value": "2026-06-28",
+            "label": "audit_date must equal the seeded audit date from quality-rules.md"
+          },
+          {
+            "kind": "jsonPathEquals",
+            "file": "data/audit.json",
+            "path": "summary.total_records",
+            "value": 6,
+            "label": "summary.total_records must equal the six CSV data rows"
+          },
+          {
+            "kind": "contains",
+            "file": "data/audit.json",
+            "pattern": "2026-06-28",
+            "flags": "i",
+            "label": "include the seeded audit date"
+          },
+          {
+            "kind": "contains",
+            "file": "data/audit.json",
+            "pattern": "overall_score|overallScore|overall[^\"]*score",
+            "flags": "i",
+            "label": "include overall_score"
+          },
+          {
+            "kind": "contains",
+            "file": "data/audit.json",
+            "pattern": "pass_rate|passRate",
+            "flags": "i",
+            "label": "include per-dimension pass rates"
+          },
+          {
+            "kind": "contains",
+            "file": "data/audit.json",
+            "pattern": "failing_examples|failingExamples",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "data/audit.json",
+            "pattern": "completeness",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "data/audit.json",
+            "pattern": "validity",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "data/audit.json",
+            "pattern": "consistency",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "data/audit.json",
+            "pattern": "uniqueness",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "data/audit.json",
+            "pattern": "timeliness|stale|last_seen",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "data/audit.json",
+            "pattern": "C-002",
+            "flags": "i",
+            "label": "include C-002 as a failing example"
+          },
+          {
+            "kind": "contains",
+            "file": "data/audit.json",
+            "pattern": "C-003",
+            "flags": "i",
+            "label": "include C-003 as a failing example"
+          },
+          {
+            "kind": "contains",
+            "file": "data/audit.json",
+            "pattern": "C-004",
+            "flags": "i",
+            "label": "include C-004 as a failing example"
+          },
+          {
+            "kind": "contains",
+            "file": "data/audit.json",
+            "pattern": "C-005",
+            "flags": "i",
+            "label": "include C-005 as a failing example"
+          },
+          {
+            "kind": "contains",
+            "file": "data/audit.json",
+            "pattern": "C-005[\\s\\S]{0,220}(pending|invalid status|status)|pending[\\s\\S]{0,220}C-005",
+            "flags": "i",
+            "label": "include C-005 invalid pending status, not only stale last_seen"
+          },
+          {
+            "kind": "notContains",
+            "file": "data/audit.json",
+            "pattern": "first_name|last_name|john@doe|90[- ]day|90\\s+days|\"overall_score\"\\s*:\\s*\"[A-F][+-]?\"",
+            "flags": "i",
+            "label": "avoid invented columns, values, thresholds, and letter-grade overall scores"
+          },
+          {
+            "kind": "notContains",
+            "file": "data/audit.json",
+            "pattern": "2024-\\d\\d-\\d\\d",
+            "flags": "i",
+            "label": "do not invent an unrelated audit timestamp"
+          }
+        ]
+      }
+    ]
+  },
+  "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": [
+    "measurable rules",
+    "failing examples",
+    "prioritized remediation"
+  ]
+}