@bendyline/gilde 0.1.2 → 0.1.4

package/data/craftbook-templates/ro/root-cause-investigation/versions/1.0.1/craftbook.json

@@ -0,0 +1,126 @@
+{
+  "id": "root-cause-investigation",
+  "name": "Root-Cause Investigation",
+  "description": "Debug systematically: reproduce the failure and find the true root cause before changing any code, then fix and verify. Enforces a no-fix-without-diagnosis discipline.",
+  "basedOn": {
+    "name": "gstack",
+    "url": "https://github.com/garrytan/gstack"
+  },
+  "plan": "## Iron Law\n\n**NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST.**\n\nFixing symptoms creates whack-a-mole debugging. Every fix that doesn't address root cause makes the next bug harder to find. Find the root cause, then fix it.\n\n---\n\n## Important Rules\n\n- **3+ failed fix attempts → STOP and question the architecture.** Wrong architecture, not failed hypothesis.\n- **Never apply a fix you cannot verify.** If you can't reproduce and confirm, don't ship it.\n- **Never say \"this should fix it.\"** Verify and prove it. Run the tests.\n- **If fix touches >5 files → AskUserQuestion** about blast radius before proceeding.\n- **Completion status:**\n  - DONE — root cause found, fix applied, regression test written, all tests pass\n  - DONE_WITH_CONCERNS — fixed but cannot fully verify (e.g., intermittent bug, requires staging)\n  - BLOCKED — root cause unclear after investigation, escalated",
+  "entryStepId": "phase-1",
+  "triggers": [
+    "debug this",
+    "fix this bug",
+    "why is this broken",
+    "root cause analysis",
+    "investigate this error"
+  ],
+  "command": "root-cause-investigation",
+  "steps": [
+    {
+      "id": "phase-1",
+      "name": "Phase 1: Root Cause Investigation",
+      "prompt": "> **Iron Law:**\n> **NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST.**\n> \n> Fixing symptoms creates whack-a-mole debugging. Every fix that doesn't address root cause makes the next bug harder to find. Find the root cause, then fix it.\n> \n> ---\n\nGather context before forming any hypothesis.\n\n1. **Collect symptoms:** Read the error messages, stack traces, and reproduction steps. If the user hasn't provided enough context, ask ONE question at a time via ask_user_question.\n\n2. **Read the code:** Trace the code path from the symptom back to potential causes. Use search_code to find all references, readFile to understand the logic.\n\n3. **Check recent changes:**\n   ```bash\n   git log --oneline -20 -- <affected-files>\n   ```\n   Was this working before? What changed? A regression means the root cause is in the diff.\n\n4. **Reproduce:** Can you trigger the bug deterministically? If not, gather more evidence before proceeding.\n\n5. **Check investigation history:** Search prior learnings for investigations on the same files. Recurring bugs in the same area are an architectural smell. If prior investigations exist, note patterns and check if the root cause was structural.\n\n### Scope Lock\n\nAfter forming your root cause hypothesis, lock edits to the affected module to prevent scope creep.\n\n**If FREEZE_AVAILABLE:** Identify the narrowest directory containing the affected files. Write it to the freeze state file:\n\nSubstitute `<detected-directory>` with the actual directory path (e.g., `src/auth/`). Tell the user: \"Edits restricted to `<dir>/` for this debug session. This prevents changes to unrelated code. Run `/unfreeze` to remove the restriction.\"\n\nIf the bug spans the entire repo or the scope is genuinely unclear, skip the lock and note why.\n\n**If FREEZE_UNAVAILABLE:** Skip scope lock. Edits are unrestricted.\n\n---\n\nKeep a running record in notes/investigation.md: symptoms, the traced code path, and candidate causes.",
+      "next": "phase-2",
+      "suggestedRole": "developer",
+      "gate": {
+        "maxAttempts": 3,
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "notes/investigation.md",
+            "bytes": 300
+          }
+        ]
+      }
+    },
+    {
+      "id": "phase-2",
+      "name": "Phase 2: Pattern Analysis",
+      "prompt": "Check if this bug matches a known pattern:\n\n| Pattern | Signature | Where to look |\n|---------|-----------|---------------|\n| Race condition | Intermittent, timing-dependent | Concurrent access to shared state |\n| Nil/null propagation | NoMethodError, TypeError | Missing guards on optional values |\n| State corruption | Inconsistent data, partial updates | Transactions, callbacks, hooks |\n| Integration failure | Timeout, unexpected response | External API calls, service boundaries |\n| Configuration drift | Works locally, fails in staging/prod | Env vars, feature flags, DB state |\n| Stale cache | Shows old data, fixes on cache clear | Redis, CDN, browser cache, Turbo |\n\nAlso check:\n- `TODOS.md` for related known issues\n- `git log` for prior fixes in the same area — **recurring bugs in the same files are an architectural smell**, not a coincidence\n\n**External pattern search:** If the bug doesn't match a known pattern above, WebSearch for:\n- \"{framework} {generic error type}\" — **sanitize first:** strip hostnames, IPs, file paths, SQL, customer data. Search the error category, not the raw message.\n- \"{library} {component} known issues\"\n\nIf WebSearch is unavailable, skip this search and proceed with hypothesis testing. If a documented solution or known dependency bug surfaces, present it as a candidate hypothesis in Phase 3.\n\n---\n\nAppend a '## Pattern' section to notes/investigation.md naming the matched pattern (or 'novel — no known pattern').",
+      "next": "phase-3",
+      "suggestedRole": "developer",
+      "gate": {
+        "maxAttempts": 3,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "notes/investigation.md",
+            "pattern": "##\\s*Pattern",
+            "flags": "i"
+          }
+        ]
+      }
+    },
+    {
+      "id": "phase-3",
+      "name": "Phase 3: Hypothesis Testing",
+      "prompt": "Before writing ANY fix, verify your hypothesis.\n\n1. **Confirm the hypothesis:** Add a temporary log statement, assertion, or debug output at the suspected root cause. Run the reproduction. Does the evidence match?\n\n2. **If the hypothesis is wrong:** Before forming the next hypothesis, consider searching for the error. **Sanitize first** — strip hostnames, IPs, file paths, SQL fragments, customer identifiers, and any internal/proprietary data from the error message. Search only the generic error type and framework context: \"{component} {sanitized error type} {framework version}\". If the error message is too specific to sanitize safely, skip the search. If WebSearch is unavailable, skip and proceed. Then return to Phase 1. Gather more evidence. Do not guess.\n\n3. **3-strike rule:** If 3 hypotheses fail, **STOP**. Use ask_user_question:\n   ```\n   3 hypotheses tested, none match. This may be an architectural issue\n   rather than a simple bug.\n\n   A) Continue investigating — I have a new hypothesis: [describe]\n   B) Escalate for human review — this needs someone who knows the system\n   C) Add logging and wait — instrument the area and catch it next time\n   ```\n\n**Red flags** — if you see any of these, slow down:\n- \"Quick fix for now\" — there is no \"for now.\" Fix it right or escalate.\n- Proposing a fix before tracing data flow — you're guessing.\n- Each fix reveals a new problem elsewhere — wrong layer, not wrong code.\n\n---\n\nAppend a '## Hypothesis' section to notes/investigation.md: the confirmed root cause plus the one line of evidence that confirmed it.",
+      "next": "phase-4",
+      "suggestedRole": "developer",
+      "gate": {
+        "maxAttempts": 4,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "notes/investigation.md",
+            "pattern": "##\\s*Hypothesis",
+            "flags": "i"
+          }
+        ]
+      }
+    },
+    {
+      "id": "phase-4",
+      "name": "Phase 4: Implementation",
+      "prompt": "Once root cause is confirmed:\n\n1. **Fix the root cause, not the symptom.** The smallest change that eliminates the actual problem.\n\n2. **Minimal diff:** Fewest files touched, fewest lines changed. Resist the urge to refactor adjacent code.\n\n3. **Write a regression test** that:\n   - **Fails** without the fix (proves the test is meaningful)\n   - **Passes** with the fix (proves the fix works)\n\n4. **Run the full test suite.** Paste the output. No regressions allowed.\n\n5. **If the fix touches >5 files:** Use ask_user_question to flag the blast radius:\n   ```\n   This fix touches N files. That's a large blast radius for a bug fix.\n   A) Proceed — the root cause genuinely spans these files\n   B) Split — fix the critical path now, defer the rest\n   C) Rethink — maybe there's a more targeted approach\n   ```\n\n---",
+      "next": "phase-5",
+      "suggestedRole": "developer"
+    },
+    {
+      "id": "phase-5",
+      "name": "Phase 5: Verification & Report",
+      "prompt": "**Fresh verification:** Reproduce the original bug scenario and confirm it's fixed. This is not optional.\n\nRun the test suite and paste the output.\n\nOutput a structured debug report:\n```\nDEBUG REPORT\n════════════════════════════════════════\nSymptom:         [what the user observed]\nRoot cause:      [what was actually wrong]\nFix:             [what was changed, with file:line references]\nEvidence:        [test output, reproduction attempt showing fix works]\nRegression test: [file:line of the new test]\nRelated:         [TODOS.md items, prior bugs in same area, architectural notes]\nStatus:          DONE | DONE_WITH_CONCERNS | BLOCKED\n════════════════════════════════════════\n```\n\nLog the investigation as a learning for future sessions. Use `type: \"investigation\"` and include the affected files so future investigations on the same area can find this:\n\n### Important Rules\n\n- **3+ failed fix attempts → STOP and question the architecture.** Wrong architecture, not failed hypothesis.\n- **Never apply a fix you cannot verify.** If you can't reproduce and confirm, don't ship it.\n- **Never say \"this should fix it.\"** Verify and prove it. Run the tests.\n- **If fix touches >5 files → ask_user_question** about blast radius before proceeding.\n- **Completion status:**\n  - DONE — root cause found, fix applied, regression test written, all tests pass\n  - DONE_WITH_CONCERNS — fixed but cannot fully verify (e.g., intermittent bug, requires staging)\n  - BLOCKED — root cause unclear after investigation, escalated\n\nWrite the structured debug report to debug-report.md using the block above.",
+      "suggestedRole": "reviewer",
+      "gate": {
+        "maxAttempts": 4,
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "debug-report.md",
+            "bytes": 400
+          },
+          {
+            "kind": "contains",
+            "file": "debug-report.md",
+            "pattern": "Root cause",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "debug-report.md",
+            "pattern": "Regression test",
+            "flags": "i"
+          }
+        ]
+      },
+      "next": "evaluate"
+    },
+    {
+      "id": "evaluate",
+      "name": "Evaluate",
+      "suggestedRole": "reviewer",
+      "next": "phase-4",
+      "prompt": "Re-read debug-report.md against the fresh verification: does the evidence actually show the original symptom is gone, and does the regression test fail without the fix? If a gap remains, loop back to Phase 4 and close it. If everything holds, advance to Finish. Routing: ALL criteria pass → advance to finish; ANY criterion fails → loop back to phase-4 with a note naming the exact gap."
+    },
+    {
+      "id": "finish",
+      "name": "Finish",
+      "suggestedRole": "developer",
+      "prompt": "Summarize the root cause, the fix, and where the debug report lives. Hand the thread back to the user. Write a one-paragraph DONE summary to task notes via `write_task_note`, then report DONE.",
+      "terminal": true
+    }
+  ],
+  "version": "1.0.1",
+  "releasedAt": "2026-07-25T22:45:00.000Z"
+}

package/data/craftbook-templates/ro/root-cause-investigation/versions/1.0.1/test.json

@@ -0,0 +1,97 @@
+{
+  "schemaVersion": 1,
+  "title": "Root-Cause Investigation smoke eval",
+  "objective": "Self-contained smoke eval for the Root-Cause Investigation craftbook using the html-page generic harness.",
+  "tags": [
+    "html-page"
+  ],
+  "prompt": "Can you biuld us a little page for this? The content notes are in source/page-content.md. Save it as index.html — one file, nothing fancy needed on our end.",
+  "setup": {
+    "projectName": "Root-Cause Investigation Eval",
+    "about": "Self-contained eval project for root-cause-investigation. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/index.html.",
+    "missionObjectives": "Use the Root-Cause Investigation craftbook/template, read the seeded local fixtures, and write index.html without network calls, real credentials, or live services.",
+    "files": [
+      {
+        "path": "source/brief.md",
+        "content": "# Root-Cause Investigation 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: root-cause-investigation - Root-Cause Investigation.\n"
+      },
+      {
+        "path": "source/page-content.md",
+        "content": "# Boreal Desk Support Board\n\nBuild content around a support operations board. Required labels: Open issues, Status silence, Response time, Refund leakage, Next action. Required metric text: 18 hours to 6 hours and 14.2% to 8.9%.\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Developer"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "index.html is a source-grounded self-contained HTML page/tool.",
+    "deliverables": [
+      {
+        "path": "index.html",
+        "kind": "html-page",
+        "minBytes": 3000,
+        "checks": [
+          {
+            "kind": "cssMinBytes",
+            "bytes": 650,
+            "file": "index.html"
+          },
+          {
+            "kind": "jsParses",
+            "file": "index.html"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "Boreal|Support Board|returns",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "18\\s*hours|6\\s*hours|14\\.2%|8\\.9%",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "button|input|filter|tab|card|section|nav",
+            "flags": "i"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "index.html",
+      "kind": "html"
+    },
+    "axes": [
+      {
+        "name": "structure",
+        "description": "Layout and hierarchy fit the content; sections are scannable and coherent."
+      },
+      {
+        "name": "grounding",
+        "description": "Seeded source content is used faithfully — no invented facts or dropped requirements."
+      },
+      {
+        "name": "interactivity",
+        "description": "Controls and states the page claims to offer actually work."
+      },
+      {
+        "name": "polish",
+        "description": "Styling is intentional and responsive rather than unstyled or broken."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "self-contained UI",
+    "source grounding",
+    "responsive structure"
+  ]
+}

package/data/craftbook-templates/ro/rough-cut-assembly/art.json

@@ -0,0 +1,13 @@
+{
+  "schemaVersion": 1,
+  "promptVersion": "workshop-mark-1910-v2",
+  "periodCue": "circa-1910-subtle",
+  "family": "design-media",
+  "accents": [
+    "muted terracotta",
+    "sage",
+    "muted indigo"
+  ],
+  "sourceSummary": "Execute the cut list and prove it ran: every clip verified against the media index before anything renders, the assembly driven through the project's media pipeline with a run log, and the result checked against the expected duration — an assembly you can trust unwatched.",
+  "styleReference": "accessibility-audit-1910"
+}

package/data/craftbook-templates/ro/rough-cut-assembly/manifest.json

@@ -16,6 +16,7 @@
   "maintainer": {
     "name": "Gezel"
   },
+  "logo": "logo.webp",
   "license": "MIT",
   "yankedVersions": [],
   "workflow": "build-loop"

package/data/craftbook-templates/ru/runbook/art.json

@@ -0,0 +1,12 @@
+{
+  "schemaVersion": 1,
+  "promptVersion": "workshop-mark-1910-v2",
+  "periodCue": "circa-1910-subtle",
+  "family": "inspect-review",
+  "accents": [
+    "muted terracotta",
+    "sage"
+  ],
+  "sourceSummary": "Write an operational runbook or playbook a tired on-call engineer can follow at 3am without thinking — covering when to use it, prerequisites, numbered step-by-step procedures, verification, rollback, and escalation.",
+  "styleReference": "accessibility-audit-1910"
+}

package/data/craftbook-templates/ru/runbook/manifest.json

@@ -15,6 +15,7 @@
   "maintainer": {
     "name": "Gezel"
   },
+  "logo": "logo.webp",
   "license": "MIT",
   "yankedVersions": [],
   "workflow": "build-loop"

package/data/craftbook-templates/sc/schema-migration/art.json

@@ -0,0 +1,13 @@
+{
+  "schemaVersion": 1,
+  "promptVersion": "workshop-mark-1910-v2",
+  "periodCue": "circa-1910-subtle",
+  "family": "plan-coordinate",
+  "accents": [
+    "ochre",
+    "sage",
+    "muted indigo"
+  ],
+  "sourceSummary": "Plan and execute a multi-file schema or type migration safely — changing a data model, type definition, or interface across the codebase while keeping everything compiling and consistent.",
+  "styleReference": "accessibility-audit-1910"
+}

package/data/craftbook-templates/sc/schema-migration/manifest.json

@@ -15,6 +15,7 @@
   "maintainer": {
     "name": "Gezel"
   },
+  "logo": "logo.webp",
   "license": "MIT",
   "yankedVersions": [],
   "workflow": "build-loop"

package/data/craftbook-templates/sc/scrape-to-structured/art.json

@@ -0,0 +1,13 @@
+{
+  "schemaVersion": 1,
+  "promptVersion": "workshop-mark-1910-v2",
+  "periodCue": "circa-1910-subtle",
+  "family": "build-code",
+  "accents": [
+    "muted indigo",
+    "terracotta",
+    "sage"
+  ],
+  "sourceSummary": "Turn one or more web pages into a clean, structured dataset (JSON or CSV) with a fixed schema — product listings, directory entries, articles, tables, or job posts.",
+  "styleReference": "accessibility-audit-1910"
+}

package/data/craftbook-templates/sc/scrape-to-structured/manifest.json

@@ -15,6 +15,7 @@
   "maintainer": {
     "name": "Gezel"
   },
+  "logo": "logo.webp",
   "license": "MIT",
   "yankedVersions": [],
   "workflow": "build-loop"

package/data/craftbook-templates/sc/script-automation/art.json

@@ -0,0 +1,12 @@
+{
+  "schemaVersion": 1,
+  "promptVersion": "workshop-mark-1910-v2",
+  "periodCue": "circa-1910-subtle",
+  "family": "inspect-review",
+  "accents": [
+    "muted terracotta",
+    "sage"
+  ],
+  "sourceSummary": "Write a one-off automation script that reliably does a repetitive task — process files, call an API, transform data — with arguments, a dry-run, idempotency, and clear logging so it is safe to run.",
+  "styleReference": "accessibility-audit-1910"
+}

package/data/craftbook-templates/sc/script-automation/manifest.json

@@ -15,6 +15,7 @@
   "maintainer": {
     "name": "Gezel"
   },
+  "logo": "logo.webp",
   "license": "MIT",
   "yankedVersions": [],
   "workflow": "build-loop"

package/data/craftbook-templates/sd/sdk-wrapper/art.json

@@ -0,0 +1,13 @@
+{
+  "schemaVersion": 1,
+  "promptVersion": "workshop-mark-1910-v2",
+  "periodCue": "circa-1910-subtle",
+  "family": "build-code",
+  "accents": [
+    "muted indigo",
+    "terracotta",
+    "sage"
+  ],
+  "sourceSummary": "Wrap a third-party HTTP API as a clean, typed client library — studying the real API surface first so the wrapper matches reality, not guesses.",
+  "styleReference": "accessibility-audit-1910"
+}

package/data/craftbook-templates/sd/sdk-wrapper/manifest.json

@@ -15,6 +15,7 @@
   "maintainer": {
     "name": "Gezel"
   },
+  "logo": "logo.webp",
   "license": "MIT",
   "yankedVersions": [],
   "workflow": "build-loop"

package/data/craftbook-templates/sd/sdk-wrapper/versions/1.0.1/test.json

@@ -53,6 +53,11 @@
             "file": "src/solution.mjs",
             "pattern": "18|6|14\\.2|8\\.9|Boreal",
             "flags": "i"
+          },
+          {
+            "kind": "nodeScriptPasses",
+            "script": "src/solution.mjs",
+            "timeoutMs": 10000
           }
         ]
       }

package/data/craftbook-templates/se/seasonal-maintenance-sweep/art.json

@@ -0,0 +1,13 @@
+{
+  "schemaVersion": 1,
+  "promptVersion": "workshop-mark-1910-v2",
+  "periodCue": "circa-1910-subtle",
+  "family": "plan-coordinate",
+  "accents": [
+    "ochre",
+    "sage",
+    "muted indigo"
+  ],
+  "sourceSummary": "Run a season's home-care sweep against the project's systems roster: work out what care is due or overdue from each system's interval, plan the walkthrough in a sensible order with supplies, then log the completed care and flag what needs a professional — leaving the roster's due-tracking reset and a short sweep report.",
+  "styleReference": "accessibility-audit-1910"
+}

package/data/craftbook-templates/se/seasonal-maintenance-sweep/manifest.json

@@ -16,6 +16,7 @@
   "maintainer": {
     "name": "Gezel"
   },
+  "logo": "logo.webp",
   "license": "MIT",
   "yankedVersions": [],
   "workflow": "build-loop"

package/data/craftbook-templates/se/security-architecture-review/art.json

@@ -0,0 +1,12 @@
+{
+  "schemaVersion": 1,
+  "promptVersion": "workshop-mark-1910-v2",
+  "periodCue": "circa-1910-subtle",
+  "family": "inspect-review",
+  "accents": [
+    "muted terracotta",
+    "sage"
+  ],
+  "sourceSummary": "A structured security architecture review: walk the stack for secrets, dependencies, auth, and common vulnerability classes, then report findings ranked by severity and confidence.",
+  "styleReference": "accessibility-audit-1910"
+}

package/data/craftbook-templates/se/security-architecture-review/manifest.json

@@ -11,6 +11,7 @@
   "maintainer": {
     "name": "Gezel"
   },
+  "logo": "logo.webp",
   "license": "MIT",
   "yankedVersions": []
 }

package/data/craftbook-templates/se/seo-meta-pack/art.json

@@ -0,0 +1,13 @@
+{
+  "schemaVersion": 1,
+  "promptVersion": "workshop-mark-1910-v2",
+  "periodCue": "circa-1910-subtle",
+  "family": "analyze-measure",
+  "accents": [
+    "muted indigo",
+    "ochre",
+    "sage"
+  ],
+  "sourceSummary": "Generate a complete on-page SEO metadata pack for a set of pages: it first scopes each page's primary keyword and search intent and the length/format rules (title tag, meta description, Open Graph, Twitter card, slug), then writes optimized, unique metadata for every page that respects pixel/character limits and…",
+  "styleReference": "accessibility-audit-1910"
+}

package/data/craftbook-templates/se/seo-meta-pack/manifest.json

@@ -15,6 +15,7 @@
   "maintainer": {
     "name": "Gezel"
   },
+  "logo": "logo.webp",
   "license": "MIT",
   "yankedVersions": [],
   "workflow": "build-loop"

package/data/craftbook-templates/sh/ship/art.json

@@ -0,0 +1,12 @@
+{
+  "schemaVersion": 1,
+  "promptVersion": "workshop-mark-1910-v2",
+  "periodCue": "circa-1910-subtle",
+  "family": "inspect-review",
+  "accents": [
+    "muted terracotta",
+    "sage"
+  ],
+  "sourceSummary": "End-to-end release procedure: run tests, run a review pass, commit/push, open the PR, wait for CI to come back green, hand off for merge.",
+  "styleReference": "accessibility-audit-1910"
+}

package/data/craftbook-templates/sh/ship/manifest.json

@@ -11,6 +11,7 @@
   "maintainer": {
     "name": "Gezel"
   },
+  "logo": "logo.webp",
   "license": "MIT",
   "yankedVersions": [],
   "workflow": "release"

package/data/craftbook-templates/so/social-thread/art.json

@@ -0,0 +1,13 @@
+{
+  "schemaVersion": 1,
+  "promptVersion": "workshop-mark-1910-v2",
+  "periodCue": "circa-1910-subtle",
+  "family": "communicate-market",
+  "accents": [
+    "muted terracotta",
+    "dusty rose",
+    "sage"
+  ],
+  "sourceSummary": "Write a multi-post social thread (X/Twitter, LinkedIn, Threads) that hooks, delivers, and converts: it first locks the single angle/big idea, the platform and its character limits, the target reader, and the CTA, then drafts the thread as numbered posts with a scroll-stopping hook, one idea per post, and a clear close.",
+  "styleReference": "accessibility-audit-1910"
+}

package/data/craftbook-templates/so/social-thread/manifest.json

@@ -15,6 +15,7 @@
   "maintainer": {
     "name": "Gezel"
   },
+  "logo": "logo.webp",
   "license": "MIT",
   "yankedVersions": [],
   "workflow": "build-loop"

package/data/craftbook-templates/so/source-quality-audit/art.json

@@ -0,0 +1,12 @@
+{
+  "schemaVersion": 1,
+  "promptVersion": "workshop-mark-1910-v2",
+  "periodCue": "circa-1910-subtle",
+  "family": "inspect-review",
+  "accents": [
+    "muted terracotta",
+    "sage"
+  ],
+  "sourceSummary": "Once a month, make the reading list earn its place: score each source on what it actually delivered — accuracy, originality, noise — and keep, demote, or drop with evidence, so the brief stays sharp as the feeds drift.",
+  "styleReference": "accessibility-audit-1910"
+}

package/data/craftbook-templates/so/source-quality-audit/manifest.json

@@ -16,6 +16,7 @@
   "maintainer": {
     "name": "Gezel"
   },
+  "logo": "logo.webp",
   "license": "MIT",
   "yankedVersions": [],
   "workflow": "build-loop"

package/data/craftbook-templates/sp/spa-dashboard/art.json

@@ -0,0 +1,13 @@
+{
+  "schemaVersion": 1,
+  "promptVersion": "workshop-mark-1910-v2",
+  "periodCue": "circa-1910-subtle",
+  "family": "analyze-measure",
+  "accents": [
+    "muted indigo",
+    "ochre",
+    "sage"
+  ],
+  "sourceSummary": "Build a single-page metrics or admin dashboard with KPI summary cards, at least one chart, and a data table, rendered from sample or provided data.",
+  "styleReference": "accessibility-audit-1910"
+}

package/data/craftbook-templates/sp/spa-dashboard/manifest.json

@@ -16,6 +16,7 @@
   "maintainer": {
     "name": "Gezel"
   },
+  "logo": "logo.webp",
   "license": "MIT",
   "yankedVersions": [],
   "workflow": "build-loop"

package/data/craftbook-templates/sp/spec-authoring/art.json

@@ -0,0 +1,13 @@
+{
+  "schemaVersion": 1,
+  "promptVersion": "workshop-mark-1910-v2",
+  "periodCue": "circa-1910-subtle",
+  "family": "plan-coordinate",
+  "accents": [
+    "ochre",
+    "sage",
+    "muted indigo"
+  ],
+  "sourceSummary": "Turn a rough intent into a backlog-ready spec: interrogate scope and requirements against the real code, then file a well-formed, unambiguous issue.",
+  "styleReference": "accessibility-audit-1910"
+}

package/data/craftbook-templates/sp/spec-authoring/manifest.json

@@ -11,6 +11,7 @@
   "maintainer": {
     "name": "Gezel"
   },
+  "logo": "logo.webp",
   "license": "MIT",
   "yankedVersions": []
 }

package/data/craftbook-templates/sp/spec-doc/art.json

@@ -0,0 +1,13 @@
+{
+  "schemaVersion": 1,
+  "promptVersion": "workshop-mark-1910-v2",
+  "periodCue": "circa-1910-subtle",
+  "family": "plan-coordinate",
+  "accents": [
+    "ochre",
+    "sage",
+    "muted indigo"
+  ],
+  "sourceSummary": "Write a technical design document (RFC / engineering design doc) that gets a system change reviewed and approved — covering context and problem, goals and non-goals, the proposed design, alternatives considered, trade-offs, risks, and a rollout plan.",
+  "styleReference": "accessibility-audit-1910"
+}