lidge-jun/codexclaw / plugins/codexclaw/skills/dev-visualizer
cxc-dev-visualizer
VerifiedUse for visual explanations and documents. Triggers: diagrams, charts, interactive models, HTML reports, infographics, 시각화, 그려줘, 문서 만들어줘, 보고서, PDF 생성.
assets/report-examples/decision-en.json
View on GitHub{
"schemaVersion": 1,
"id": "decision-en",
"genre": "decision",
"language": "en",
"localeConfig": {
"sourceLanguages": ["ko"],
"outputLanguage": "en",
"locale": "en-US",
"paperSize": "Letter",
"formats": {
"date": { "dateStyle": "long", "timeZone": "UTC" },
"number": { "maximumFractionDigits": 1, "useGrouping": true },
"currency": { "currencyDisplay": "symbol", "minimumFractionDigits": 0, "maximumFractionDigits": 0, "useGrouping": true },
"unit": { "maximumFractionDigits": 1, "useGrouping": true, "separator": " " }
}
},
"title": "Expand first-month support only within a measured cohort",
"summary": "Thirty-day attrition was lower in the illustrative support cohort, at 80 versus 120 of every 1,000 subscribers, but assignment was not randomized. The operating decision is a limited expansion that tracks 90-day retention alongside cost per subscriber.",
"sections": [
{
"id": "decision",
"title": "A limited expansion fits the evidence available today",
"paragraphs": [
"In the support cohort, 80 of every 1,000 enrolled subscribers left within 30 days, compared with 120 in the comparison cohort. That is an observed attrition difference, not a causal estimate, because assignment was not randomized.",
"First-month cost per subscriber rose from KRW 18,400 to KRW 19,800. Expansion should therefore remain conditional on both 90-day retention and a defined cost ceiling."
],
"claimIds": ["C1", "C2"],
"factIds": ["F1", "F2", "F3", "F4"]
}
],
"sourceNotes": [
{ "id": "S1", "locator": "illustrative:decision/cohort", "text": "Illustrative 30-day cohort record with alternating assignment" },
{ "id": "S2", "locator": "illustrative:decision/cost", "text": "Illustrative first-month cost record per enrolled subscriber" }
],
"figures": [
{
"id": "decision-outcomes",
"sectionId": "decision",
"caption": "Figure 1. Thirty-day attrition was lower in the support cohort while cost per subscriber was higher.",
"accessibleDescription": "In the illustrative, nonrandomized 30-day cohorts, 120 of every 1,000 comparison-cohort subscribers and 80 of every 1,000 support-cohort subscribers left. Illustrative first-month cost was KRW 18,400 per comparison-cohort subscriber and KRW 19,800 per support-cohort subscriber.",
"factIds": ["F1", "F2", "F3", "F4"],
"sourceRefs": ["S1", "S2"]
}
],
"quotations": [
{
"id": "QTE1",
"sectionId": "decision",
"text": "Do not approve a full rollout before the 90-day result is available.",
"originalText": "90일 결과를 보기 전에는 전면 확대를 승인하지 않는다.",
"sourceLanguage": "ko",
"sourceRef": "S1",
"translated": true,
"translationMarker": "Translated from Korean"
}
],
"limitations": [
"All numbers are illustrative and exist only to exercise the report contract.",
"Assignment was not randomized, so the attrition difference is not a causal estimate of support.",
"Thirty-day observation cannot establish long-term retention or lifetime value."
],
"semantics": {
"questionIds": ["Q1"],
"sourceIds": ["S1", "S2"],
"claims": [
{ "id": "C1", "text": "Expand support only within a measured cohort.", "strength": "recommendation", "strengthLabel": "Recommendation", "qualification": "conditional", "qualificationText": "Expansion depends on 90-day retention and the cost ceiling" },
{ "id": "C2", "text": "Thirty-day attrition was lower in the support cohort.", "strength": "observation", "strengthLabel": "Observation", "qualification": "non-randomized-illustrative", "qualificationText": "Illustrative 30-day cohort; assignment was not randomized." }
],
"facts": [
{ "id": "F1", "claimId": "C2", "label": "Comparison-cohort 30-day attrition", "raw": 120, "kind": "unit", "unit": "subscriber", "displayUnit": "subscribers", "denominator": "1000-enrolled-subscribers", "denominatorText": "1,000 enrolled subscribers", "qualification": "illustrative-non-randomized-30-day", "qualificationText": "Illustrative 30-day cohort; assignment was not randomized." },
{ "id": "F2", "claimId": "C2", "label": "Support-cohort 30-day attrition", "raw": 80, "kind": "unit", "unit": "subscriber", "displayUnit": "subscribers", "denominator": "1000-enrolled-subscribers", "denominatorText": "1,000 enrolled subscribers", "qualification": "illustrative-non-randomized-30-day", "qualificationText": "Illustrative 30-day cohort; assignment was not randomized." },
{ "id": "F3", "claimId": "C1", "label": "Comparison-cohort first-month cost", "raw": 18400, "kind": "currency", "currency": "KRW", "unit": "KRW", "denominator": "per-enrolled-subscriber-first-month", "denominatorText": "per enrolled subscriber, first month", "qualification": "illustrative-cost", "qualificationText": "Illustrative direct cost" },
{ "id": "F4", "claimId": "C1", "label": "Support-cohort first-month cost", "raw": 19800, "kind": "currency", "currency": "KRW", "unit": "KRW", "denominator": "per-enrolled-subscriber-first-month", "denominatorText": "per enrolled subscriber, first month", "qualification": "illustrative-cost", "qualificationText": "Illustrative direct cost" }
]
}
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |