Token导航 LogoToken导航TokenDH.com
研究检索需要联网github未标认证来源可访问许可证需确认审计提醒

canva-classroom-helperCanva classroom 助手

Agent Skill

canva-classroom-helper 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

412

周安装

17

GitHub Stars

28

下载量

135
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:canva-classroom-helper(Canva classroom 助手)
来源仓库:https://github.com/canva-sdks/canva-claude-skills
仓库路径:skills/canva-classroom-helper
安装命令:
npx skills add https://github.com/canva-sdks/canva-claude-skills --skill canva-classroom-helper
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/canva-sdks/canva-claude-skills --skill canva-classroom-helper

简介

canva-classroom-helper 将教案转化为教学演示文稿,配备逐页讲稿与时间分配建议。

  • 支持学习目标可视化、逻辑流梳理,便于教师课堂控场使用。
  • 优先读取原始教案内容,避免重复提问,确保转化保真度。
  • 需人工核对知识点覆盖完整性,关键结论建议标注重点提示。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Canva Classroom Helper — Lesson Plan to Deck

Transform a lesson plan into a clear, teachable presentation: learning goals on screen, logical flow, and slide-by-speaker-notes so the teacher can run the class from one deck.

Workflow

  1. Get the lesson plan source (always do this first — no substitute checklist)

- Do not open with a generic two-part prompt (e.g. “paste the plan” *and then* “describe the topic and key points”). The lesson plan already carries topic and key points; asking twice is redundant and skips this step’s real work (text vs Canva link vs search). - If the user has not yet given a source, ask one short question that matches this step only, for example: *Paste your full lesson plan here, or give a Canva design link or design ID, or the exact title to search in Canva; if the plan is in a file, paste the contents or give a path you can read.* Then proceed along the branch below. - If the user provides the lesson plan as text in chat, use that as the full source - If the user provides a Canva design ID directly (the identifier from a design URL—typically starts with D, e.g. DABcd1234ef), use that value as design_id with Canva:start-editing-transaction to read its text content (same as reading from a link, without URL parsing) - If the user provides a Canva design link (e.g., https://www.canva.com/design/DAG.../...), extract the design ID from the path and use Canva:start-editing-transaction to read its text content - If the user references a Canva doc or design by name, use Canva:search-designs to find it, then Canva:start-editing-transaction to read its contents

  1. List available brand kits

- Call Canva:list-brand-kits to retrieve the user's brand kits - If only one brand kit exists, use it automatically without asking - If multiple brand kits exist, present the options and ask the user to select one (school or district brand, if relevant)

  1. Generate the presentation

- Call Canva:generate-design with: - design_type: "presentation" - brand_kit_id: the selected brand kit ID - query: follow the Lesson plan → deck query format below (always a multi-slide deck—see opening lines of that format) - Show the generated candidates (thumbnails/previews as returned) to the user

  1. Finalize

- Ask the user which candidate they prefer - Call Canva:create-design-from-candidate to create the editable design - Provide the link to the new presentation and a one-line reminder of slide order vs. lesson phases (e.g., "Opening → Instruction → Practice → Check → Close")

Lesson plan → deck query format

Structure the query for Canva:generate-design so the model in Canva receives pedagogy-first instructions. This skill only targets multi-slide presentations (design_type is always "presentation"). Open the query with one line: the total slide count and that the output must be a standard multi-slide deck (one slide per item in the slide plan below)—never a poster, flyer, or single-page layout.

Include these sections (omit only if the lesson plan truly has no data for that section):

Lesson brief

  • Subject / unit / grade level (infer from context if missing)
  • Lesson title and duration (e.g., 45 min, double period)
  • Learning objective(s) — what students will know or be able to do (verbatim from the plan when provided)
  • Standards (e.g., CCSS, state, or district) — only if the user included them

Classroom arc One short paragraph: how the lesson flows for students (e.g., Engage → Explore → Explain → Elaborate → Evaluate; or I Do / We Do / You Do). Match the teacher's structure from the lesson plan when possible.

Slide plan (teaching deck) For each slide, include:

  • Slide N — Exact title (short, student-facing where appropriate)
  • Teaching goal: one sentence — what this slide does for the lesson
  • On-slide content: bullets (3–6) — key points, questions, or prompts; avoid walls of text; use age-appropriate language
  • Visuals: concrete but safe suggestions — prefer photos, simple icons, or abstract treatment; see Visuals — where they come from below (avoid asking the generator for dense labels, fine detail, or text inside images)
  • Speaker notes: 2–5 sentences — what the teacher says, facilitation tips, anticipated misconceptions, quick checks for understanding, timing hints

Materials & logistics (optional slide or final appendix slides)

  • List materials, tech, grouping, and safety notes if present in the lesson plan

Differentiation / extensions (if in the plan)

  • Brief bullets for support, challenge, or homework — can be one or two dedicated slides at the end

Pedagogical notes

  • Respect the lesson plan: Prefer the author's sequence, vocabulary, and activities; only reorganize for clarity or slide limits, and keep objectives aligned to the source
  • One main idea per slide where possible; split dense steps across multiple slides
  • Age-appropriate: Adjust reading level and examples to grade level stated or inferred
  • Sparse plans: If the plan is thin, expand with standard lesson structure (objectives, direct instruction, practice, assessment, closure) and flag assumptions briefly to the user before or after generation

Visuals — where they come from and how to avoid bad images

Why automated visuals often miss the lesson Across any subject (literacy, history, STEM, arts, SEL, etc.), AI-assisted and auto-picked images are unreliable for: readable text inside pictures; exact facts (dates, names, quotes, vocabulary); maps, timelines, or charts that must be precise; depictions of people, places, or events that must match the source material; and any slide where correct wording matters for assessment or standards alignment. Models may garble language, mix languages, invent labels, or choose plausible but wrong imagery.

What to put in the query (mitigations — any lesson plan) Include explicit global visual rules near the start of the generated query, for example:

  • Prefer simple photos, textures, icons, or abstract backgrounds; avoid asking the generator for dense infographics, labeled illustrations, or “posters with lots of text” in the image itself.
  • Do not rely on text baked into images — state that key terms, definitions, questions, numbers, and all curriculum-critical wording belong in on-slide text (in the lesson language, usually English), not inside pictures.
  • For slides where accuracy is essential (vocabulary, timelines, processes, data, primary sources, artwork titles, etc.): ask for minimal or decorative imagery and put the correct content in bullets/titles; remind that the teacher must verify on-slide text too.
  • Optionally ask for an overall image-light or clean-template feel so educators can swap in vetted Elements, uploads, or screenshots from trusted sources after generation.

After the deck exists Advise a full pass in the Canva editor: replace misleading images, fix on-slide copy, and add or paste vetted media. The editing API (perform-editing-operations, etc.) can help with text and some media in follow-up workflows—see implement-feedback patterns—but curriculum-faithful visuals and wording are ultimately human-reviewed.

Set expectations when handing off Briefly warn that auto-generated lesson visuals are drafts, not guaranteed accurate for any topic—teachers should treat images and on-slide facts as unverified until reviewed.

Notes

  • Same tool chain as branded presentation skills: brand kit + generate-design + create-design-from-candidate
  • Autofill and advanced generation features may require a Canva Enterprise plan — if tools error, explain briefly and suggest manual edits in Canva

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

34.62%
按下载量换算47

Claude

31.76%
按下载量换算43

Cursor

19.15%
按下载量换算26

Gemini CLI

9.18%
按下载量换算12

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills