跳到正文
cccskills
免费在 GitHub 公开

cxc-dev-visualizer

Use for visual explanations and documents. Triggers: diagrams, charts, interactive models, HTML reports, infographics, 시각화, 그려줘, 문서 만들어줘, 보고서, PDF 생성.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(43)

  • SKILL.md3.7 KB
  • agents/openai.yaml179 B
  • assets/editorial-report.html17.4 KB
  • assets/exhibit-recipes.json26.7 KB
  • assets/paged-report.html24.5 KB
  • assets/report-examples/decision-en.json5.2 KB
  • assets/report-examples/decision-ko.json5.0 KB
  • assets/report-examples/reference-en.json4.8 KB
  • assets/report-examples/reference-ko.json4.8 KB
  • assets/report-examples/research-en.json4.2 KB
  • assets/report-examples/research-ko.json4.1 KB
  • assets/report-model.example.json1.6 KB
  • assets/research-handoff.example.json1.6 KB
  • reference/artifact-composition.md4.8 KB
  • reference/authoring-routes.md3.5 KB
  • reference/computed-verification.md2.7 KB
  • reference/delivery-and-provenance.md762 B
  • reference/document-pdf.md17.3 KB
  • reference/english-authoring.md3.6 KB
  • reference/environment-detection.md3.3 KB
  • reference/exhibit-recipes.md12.8 KB
  • reference/html-templates.md18.0 KB
  • reference/page-role-catalog.md2.5 KB
  • reference/port-maintenance.md3.0 KB
  • reference/print-provenance.md2.9 KB
  • reference/reader-documents.md3.9 KB
  • reference/report-pipeline.md12.7 KB
  • reference/report-writing.md15.2 KB
  • reference/scope-and-maintenance.md957 B
  • reference/source-patterns.md10.3 KB
  • reference/svg-and-interaction.md9.3 KB
  • reference/visual-design.md11.3 KB
  • reference/visualize-contract.md1.1 KB
  • scripts/diagram-to-html.sh8.2 KB
  • scripts/exhibit-contract.mjs24.9 KB
  • scripts/export-paged-report.mjs40.4 KB
  • scripts/quality-gate.mjs5.0 KB
  • scripts/report-contract.mjs18.1 KB
  • scripts/report-intake.mjs2.8 KB
  • scripts/report-locale.mjs27.0 KB
  • scripts/research-adapter.mjs8.7 KB
  • upstream/sync-check.sh3.6 KB
  • upstream/visualize-upstream.md1.0 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Visual documents — compose, render, deliver

Turn the reader's question and supplied facts into a useful visual artifact. Use dev for scope, work class and verification; a document request does not automatically require a development loop. This skill owns artifact composition and delivery. dev-uiux-design owns broader design judgment, dev-frontend owns frontend implementation, and available format-specific skills own document mechanics.

Select a route; read only what it needs

ConditionReference
Every artifact: caller scope and requested outcomeScope, authoring routes
Choosing HTML, SVG, inline output, PDF, document format or scientific plottingAuthoring routes
Before composing/styling/building any visualArtifact composition
Human-readable reports and documentsReader documents, report writing
Research reports, analytical exhibits or English/bilingual outputResearch/language/exhibit routes
Computed/exported tiers, or any artifact in doubtComputed verification
PDF/print/paged report assurance profileReport pipeline
Delivery, borrowing sources or refreshing the skillDelivery and provenance

Verify in proportion to what can break

VIZ-VERIFY-SCALE-01 — the proof matches the failure it would catch. Rendering an artifact and reading the result costs a round trip, and much of what this skill produces cannot fail out of sight: the reader sees an inline visual before a screenshot could reach you, and a static page in normal flow shows its own text. Spend the round trip where the visible result is computed rather than written.

DeliveringBefore delivery
An inline visual in this conversation, or a fenced diagram the host rendersReread the source once and send it. The reader's screen is the render.
A small static HTML/SVG page in ordinary flow — prose, tables, hand-placed shapes, no runtime data, no library, no exportReread the source, save it, return the link.
Anything whose visible result is computed — marks drawn from data, connector geometry derived from rendered bounds, a runtime library or webfont, an input that changes the outputDIAGRAM-RENDER-VERIFY-01 in full.
PDF, print output, or a multi-page paged reportDIAGRAM-RENDER-VERIFY-01 with a stated assurance profile. Merely saving or sharing a simple static HTML/SVG file does not promote it to this tier.

Two rules hold in every tier. An unrun check is never written up as a passed one: "not rendered — static HTML in normal flow" is honest, "verified" is not. And a defect promotes the artifact: once the reader reports something wrong, or a first render shows it, render each further fix before sending it. Nothing here is enforced by a hook, and the calling task's own verification gate still governs its work.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Use for AST search and codemods. Triggers: ast-grep, sg, function/call/class/import, empty catch, missing await, YAML rules.

中文简介正在准备中。当前显示原文说明。

lidge-jun/codexclaw472026年10月9日 更新

cxc-dev

免费

Use for coding, PR delivery, scaffolding and QA. Triggers: develop, fix, refactor, test, review, docs, browse, stacked PR, 개발, 수정, 검토, 스택 PR.

中文简介正在准备中。当前显示原文说明。

lidge-jun/codexclaw472026年10月9日 更新

Use for module boundaries and dependencies. Triggers: circular import, coupling, barrel, re-export, validation placement, 모듈 경계, 순환 참조.

中文简介正在准备中。当前显示原文说明。

lidge-jun/codexclaw472026年10月9日 更新

Use for APIs, servers and app databases. Triggers: REST, GraphQL, migration, query optimization, middleware, caching, queues, 백엔드, API 작업, 마이그레이션, 쿼리 최적화.

中文简介正在准备中。当前显示原文说明。

lidge-jun/codexclaw472026年10月9日 更新

Use for code/PR/diff review and refactor audits. Triggers: review this, before merge, antipattern, 리뷰, 코드 리뷰, 머지 전에 확인.

中文简介正在准备中。当前显示原文说明。

lidge-jun/codexclaw472026年10月9日 更新

Use for analytics and data pipelines. Triggers: ETL, ELT, data quality, SQL optimization, schema drift, backfill, 데이터 파이프라인, 데이터 품질, 백필.

中文简介正在准备中。当前显示原文说明。

lidge-jun/codexclaw472026年10月9日 更新

查看 lidge-jun 的全部技能

报告此技能的问题