跳到正文
cccskills
免费在 GitHub 公开

template-render

Render a Template + data + Style into a final artifact in one of HTML, PDF, PNG, SVG or PPTX. Use whenever the user asks for a concrete deliverable like "make me a poster", "render a card", "give me a one-pager".

中文简介正在准备中。当前显示原文说明。

集成工具Playwright
查看安装方法

包含的文件(1)

  • SKILL.md1.9 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

template-render

The standard recipe for producing a deliverable from a Template and a Style.

Procedure

  1. Pick a Template:
    • If the user names a category ("a poster", "a card"), list candidates: claw template list --category <cat>.
    • If they describe a use-case, match by tags or name.
  2. Pick a Style:
    • If they reference a brand or saved style, use that.
    • Otherwise default to the workspace's primary Style (often the first non-builtin or claw).
  3. Compose data:
    • Read the template's slots from claw template get <id>.
    • For each slot, write a JSON field with id as the key.
    • Respect maxLength, maxItems, required.
  4. Render:
    claw template render <templateId> --style <styleId> --data data.json --format pdf,png --out ./deliverable
    
  5. Report back: the paths produced and a sentence describing what is in each.

Formats

FormatRendererNotes
htmldirectCanonical, fastest, no deps.
svgwraps html in <foreignObject>Use for scalable vector.
pdfPlaywright (Chromium)Falls back to a minimal Node PDF if Playwright is unavailable.
pngPlaywright (Chromium)2x deviceScaleFactor.
pptxOpenXML (Node only)Minimal one-slide PPTX. Best for presentation category.

Constraints

  • Never hard-code style values into the data. The Style is the source of truth for color and typography.
  • If the template declares outputs and the requested format is not in the list, fail with a clear error.
  • Generated outputs go under .claw/templates/<templateId>/outputs/ unless --out is specified.

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

Govern Clawix accessibility changes across screen reader behavior, keyboard navigation, focus order, contrast, reduced motion, text scaling, timed interactions, and agent-generated UI.

中文简介正在准备中。当前显示原文说明。

clawic/Clawix82026年6月6日 更新

Review or update stable, canonical, any-human, PMF, and adoption claims using adoption/canonicity governance packets.

中文简介正在准备中。当前显示原文说明。

clawic/Clawix82026年6月6日 更新

Turn a new or changed ADR into implemented behavior, routing docs, tests, and guardrails rather than leaving it as standalone prose.

中文简介正在准备中。当前显示原文说明。

clawic/Clawix82026年6月6日 更新

Repair confirmed architecture drift in small batches while preserving public canon and avoiding broad opportunistic refactors.

中文简介正在准备中。当前显示原文说明。

clawic/Clawix82026年6月6日 更新

Given an existing Style, generate a human-readable brand guidelines document covering colors, typography, voice, do/don't, imagery rules, and usage examples. Use when the user asks for a brand book, brand guide, or design system document.

中文简介正在准备中。当前显示原文说明。

clawic/Clawix82026年6月6日 更新

Add or improve canonical data catalog collections, fields, aliases, relations, evidence tags, docs, and tests.

中文简介正在准备中。当前显示原文说明。

clawic/Clawix82026年6月6日 更新

查看 clawic 的全部技能

报告此技能的问题