@bendyline/gilde 0.1.39 → 0.1.41

package/data/craftbook-templates/re/release-readiness-review/manifest.json

@@ -3,6 +3,7 @@
   "kind": "craftbook-template",
   "id": "release-readiness-review",
   "role": "maintenance-review",
+  "category": "code-release",
   "name": "Release Readiness Review",
   "description": "Run a go/no-go release readiness review against a structured pre-launch checklist and produce a sign-off report with a clear ship decision. First scopes the release and locks a readiness checklist (acceptance criteria met, tests and CI green, no open blockers, migrations and rollback ready, monitoring and alerts in place, docs and changelog updated, feature flags and config set, and on-call/comms prepared), then verifies each item by inspecting the actual state rather than assuming, then writes a go/no-go report listing every blocker that must clear before ship and the residual risks. Use this for a release readiness review, a go/no-go decision, a pre-launch checklist, a ship-readiness gate, a launch review, or deciding if a change is safe to deploy — it produces an evidence-backed ship decision rather than a gut-feel 'looks good'.",
   "tags": [

package/data/craftbook-templates/re/release-readiness-review/versions/1.1.0/craftbook.json

@@ -0,0 +1,192 @@
+{
+  "id": "release-readiness-review",
+  "name": "Release Readiness Review",
+  "description": "Run a go/no-go release readiness review against a structured pre-launch checklist and produce a sign-off report with a clear ship decision. First scopes the release and locks a readiness checklist (acceptance criteria met, tests and CI green, no open blockers, migrations and rollback ready, monitoring and alerts in place, docs and changelog updated, feature flags and config set, and on-call/comms prepared), then verifies each item by inspecting the actual state rather than assuming, then writes a go/no-go report listing every blocker that must clear before ship and the residual risks. Use this for a release readiness review, a go/no-go decision, a pre-launch checklist, a ship-readiness gate, a launch review, or deciding if a change is safe to deploy — it produces an evidence-backed ship decision rather than a gut-feel 'looks good'.\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 readiness checklist (reviewer) — lock the release scope + a go/no-go checklist → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. Verify readiness (developer) — check each item against the real state → gated on artifact `{{workPath}}/verify.md` (markdown-notes)\n3. Write the go/no-go report (reviewer) — ship decision + blockers + residual risk → gated on artifact `{{workPath}}/release-readiness.md` (markdown-report)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "scope",
+  "triggers": [
+    "release readiness review",
+    "are we ready to ship",
+    "go no go decision",
+    "pre-launch checklist",
+    "is this safe to deploy",
+    "ship readiness review"
+  ],
+  "steps": [
+    {
+      "id": "scope",
+      "name": "Scope the readiness checklist",
+      "description": "lock the release scope + a go/no-go checklist",
+      "prompt": "Step 1: Define the release: what is shipping (features/changes), to whom, and the rollout mechanism (full deploy / staged / flagged). Step 2: Write a readiness acceptance-criteria checklist covering: the feature's own acceptance criteria are met; the test suite and CI are green; there are no open blocking bugs or unresolved review comments; database migrations are reversible and a rollback path exists; monitoring, logging, and alerts cover the new code; user-facing docs, release notes, and changelog are updated; feature flags and config/secrets are set correctly for the target env; and on-call ownership and a comms/rollback plan are ready. Step 3: For each item, state the concrete pass condition and HOW it will be verified (where to look). Step 4: Mark which items are hard blockers vs advisory. Write the release definition + checklist to `write_task_note` AND `{{workPath}}/scope.md`. No verification yet.\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": "reviewer",
+      "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": "verify"
+    },
+    {
+      "id": "verify",
+      "name": "Verify readiness",
+      "description": "check each item against the real state",
+      "prompt": "Step 1: For EACH checklist item, VERIFY the actual state — do not assume. Run/inspect the tests and CI status; search for open issues/TODOs/blocking review comments; check that the migration has a down path and that a rollback is documented; confirm alerts/dashboards reference the new code paths; open the docs/changelog/release notes to confirm they are updated; check the flag and config/secret values for the target environment; confirm on-call and the rollback/comms plan exist. Step 2: For each item record PASS/FAIL/NA with the EVIDENCE (the command output, the file, the config value, the issue link) — a claim without evidence is not a pass. Step 3: Classify every FAIL as a hard blocker or an accepted risk. Step 4: Note residual risks even where items pass (e.g. 'migration is reversible but locks the table for ~30s'). Good looks like: every item backed by an observation, not 'should be fine'. Stage the verification log to `write_task_note`. Do not write the report yet.\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": "developer",
+      "advanceWhen": {
+        "file": "{{workPath}}/verify.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/verify.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/verify.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "verify",
+        "maxAttempts": 3
+      },
+      "next": "report"
+    },
+    {
+      "id": "report",
+      "name": "Write the go/no-go report",
+      "description": "ship decision + blockers + residual risk",
+      "prompt": "Step 1: Open `{{workPath}}/release-readiness.md` and write the DECISION at the top: GO / NO-GO / GO-WITH-CONDITIONS, in one sentence with the deciding factor. Step 2: Add a '## Checklist' table: each item with PASS/FAIL/NA and its evidence. Step 3: Add a '## Blockers' section listing every must-clear item before ship, with the concrete action to clear it and an owner. Step 4: Add a '## Residual risks' section (accepted risks and watch-items for after deploy) and a '## Rollback' note summarizing how to back out. Step 5: If GO-WITH-CONDITIONS, list the exact conditions. The decision must follow from the evidence — no GO with an open hard blocker. On a loop-back, fix only the named gaps. `write_task_note` the report path, the decision, and the count of open blockers.\n\nThe deliverable `{{workPath}}/release-readiness.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}}/release-readiness.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true,
+        "requireChange": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/release-readiness.md",
+            "bytes": 1500,
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "{{workPath}}/release-readiness.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i",
+            "label": "at least one markdown heading",
+            "artifact": true
+          },
+          {
+            "kind": "citationsResolve",
+            "file": "{{workPath}}/release-readiness.md",
+            "minCitations": 2,
+            "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}}/release-readiness.md` with `read_artifact` first, then review it against the original scope: every claim cites a real path, the severities and priorities are defensible, and nothing important in scope was skipped. Open the underlying files for at least the top findings; do not grade from the report's own summary. If a finding cannot be verified, say so explicitly.\n\nWrite your review to the artifact `{{workPath}}/review.md` with one `write_artifact` call: what you checked, what held, what did not (as a findings table with columns `| Severity | File | Line | Problem | Fix |` when anything needs fixing), ending with exactly `Verdict: PASS` or `Verdict: REVISE`. The gate enforces the verdict: a well-formed REVISE is routed back to the `report` step automatically with your findings. On PASS, `advance_task_step` to `finish`.",
+      "suggestedRole": "reviewer",
+      "consumes": [
+        {
+          "file": "{{workPath}}/release-readiness.md",
+          "artifact": true
+        }
+      ],
+      "next": "finish",
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/review.md",
+            "bytes": 300,
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "{{workPath}}/review.md",
+            "pattern": "Verdict:\\s*(?:PASS|REVISE)",
+            "flags": "i",
+            "label": "explicit PASS or REVISE verdict",
+            "artifact": true
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkFixReview",
+            "scope": "standard",
+            "inputs": {
+              "taskRef": "{{task.ref}}",
+              "reviewPath": "{{workPath}}/review.md",
+              "fixStepId": "report"
+            }
+          }
+        ],
+        "onReject": "evaluate",
+        "maxAttempts": 4
+      }
+    },
+    {
+      "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": "1.1.0",
+  "releasedAt": "2026-08-24T00:00:00.000Z",
+  "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": "1.26236"
+}

package/data/craftbook-templates/re/release-readiness-review/versions/1.1.0/test.json

@@ -0,0 +1,113 @@
+{
+  "schemaVersion": 1,
+  "title": "Release Readiness Review smoke eval",
+  "objective": "Self-contained smoke eval for the Release Readiness Review craftbook using the corpus generic harness.",
+  "tags": [
+    "corpus"
+  ],
+  "prompt": "We need a release readiness review 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": "Release Readiness Review Eval",
+    "about": "Self-contained eval project for release-readiness-review. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/report.md.",
+    "missionObjectives": "Use the Release Readiness Review 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": "# Release Readiness Review 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: release-readiness-review - Release Readiness Review.\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/re/reliability-review/manifest.json

@@ -3,6 +3,7 @@
   "kind": "craftbook-template",
   "id": "reliability-review",
   "role": "maintenance-review",
+  "category": "code-ops",
   "name": "Reliability & Resilience Review",
   "description": "Review a codebase for production reliability and resilience risks across asynchronous work, external dependencies, state transitions, resource lifecycles, and recovery paths. Uses the repository and per-file indexes to map failure domains, verifies likely issues in source and tests, and leaves a prioritized morning report covering timeouts, retries, idempotency, cancellation, concurrency, backpressure, cleanup, graceful shutdown, observability, and disaster recovery. Use for a weekly reliability sweep, resilience review, failure-mode audit, or pre-production hardening review.",
   "tags": [

package/data/craftbook-templates/re/report-pdf/manifest.json

@@ -3,6 +3,7 @@
   "kind": "craftbook-template",
   "id": "report-pdf",
   "role": "general",
+  "category": "writing",
   "name": "Formatted Report",
   "description": "Produce a polished, print-ready PDF report from Markdown with DocBlocks — no hand-built HTML or browser print translator. Locks the audience, source facts, structure, and acceptance criteria first; writes the complete report as report.md; then converts, previews, and saves report.pdf in the project's artifacts drawer.",
   "tags": [

package/data/craftbook-templates/re/research-report/manifest.json

@@ -3,6 +3,7 @@
   "kind": "craftbook-template",
   "id": "research-report",
   "role": "general",
+  "category": "research",
   "name": "Cited Research Report",
   "description": "Produce a rigorously cited research report that answers a specific question end to end: a planner first decomposes the question into sub-questions and locks the scope, then a researcher gathers and logs primary and secondary sources with inline citations, then a copywriter writes a structured markdown report (executive summary, findings, evidence, limitations, references). The ordering matters because a small model that writes before scoping rambles and a model that writes without a source log fabricates citations; locking sub-questions and a source table first turns the report into a fill-in-the-evidence exercise. Use this for literature-backed analysis, deep dives, investigative write-ups, background research, and any 'find out and write it up with sources' task where every claim must trace to a citation.",
   "tags": [

package/data/craftbook-templates/re/research-to-document/manifest.json

@@ -3,6 +3,7 @@
   "kind": "craftbook-template",
   "id": "research-to-document",
   "role": "general",
+  "category": "writing",
   "name": "Word Document from Content or Research",
   "description": "Turn supplied content or a researched question into a real Word document (.docx, plus PDF on request) with DocBlocks. The workflow inventories sources, writes the reviewed source as Markdown, then converts, previews, and saves the finished file without hand-built document XML or an HTML intermediary.",
   "tags": [

package/data/craftbook-templates/re/rest-api/manifest.json

@@ -3,6 +3,7 @@
   "kind": "craftbook-template",
   "id": "rest-api",
   "role": "project-starter",
+  "category": "code-data",
   "name": "REST API Service",
   "description": "Build a RESTful HTTP API service with resource endpoints, JSON request/response bodies, status codes, validation, and error handling. Locks the contract FIRST — resources, routes, verbs, request/response shapes, status-code map, auth, and pagination — so the implementation has a fixed target, then builds the server, then writes endpoint tests that exercise every route and error case. Covers CRUD endpoints, RESTful routing, OpenAPI-style contract, HTTP status codes, input validation, JSON serialization, and integration tests against the running handler.",
   "tags": [

package/data/craftbook-templates/re/resume-cv/manifest.json

@@ -3,6 +3,7 @@
   "kind": "craftbook-template",
   "id": "resume-cv",
   "role": "general",
+  "category": "business",
   "name": "Résumé / CV",
   "description": "Build a clean, ATS-friendly résumé or CV from a person's background, tailored to a target role. Scopes the target role and the highlight reel of achievements FIRST (so the résumé is targeted, not a life history), then designs a single-column, parser-safe layout, then writes impact-led bullets with metrics that fit one to two pages. Use for job applications, LinkedIn-to-résumé conversions, and role-targeted CV rewrites.",
   "tags": [

package/data/craftbook-templates/re/reviewer-loop/manifest.json

@@ -3,6 +3,7 @@
   "kind": "craftbook-template",
   "id": "reviewer-loop",
   "role": "maintenance-review",
+  "category": "practice",
   "name": "Reviewer Loop",
   "description": "Draft → critique → revise (looped until approved) → publish. A repeatable critique-and-revise pattern with explicit branching.",
   "tags": [

package/data/craftbook-templates/ro/rollback-plan/manifest.json

@@ -3,6 +3,7 @@
   "kind": "craftbook-template",
   "id": "rollback-plan",
   "role": "general",
+  "category": "code-release",
   "name": "Rollback Plan",
   "description": "Author a concrete, tested rollback plan for a release so that when a deploy goes wrong the team can revert FAST and safely without improvising under pressure — covering the trigger conditions that mean 'roll back', the exact reversal steps (redeploy previous artifact, down-migrations, flag flips, cache/CDN invalidation), data-safety and forward/backward-compatibility considerations, the recovery-time estimate, and a post-rollback verification. A planner scopes the failure modes and triggers, a developer writes the precise step-by-step runbook with real commands, and a reviewer dry-runs it for correctness and irreversible-data hazards. Use this alongside any risky deploy, migration, or feature launch where 'how do we undo this' must be answered before, not during, an incident.",
   "tags": [

package/data/craftbook-templates/ro/root-cause-investigation/manifest.json

@@ -3,11 +3,18 @@
   "kind": "craftbook-template",
   "id": "root-cause-investigation",
   "role": "maintenance-review",
+  "category": "code-quality",
   "name": "Root-Cause Investigation",
   "description": "Debug systematically: reproduce the failure and find the true root cause before changing any code, then fix and verify.",
   "tags": [
     "debugging",
-    "engineering"
+    "engineering",
+    "investigation",
+    "root-cause",
+    "incident",
+    "diagnosis",
+    "debug",
+    "memory"
   ],
   "maintainer": {
     "name": "Gezel"