Token导航 LogoToken导航TokenDH.com
研究检索external-servicegithub未标认证来源可访问许可证需确认审计通过

canvas-course-qc画布课程质量控制

Agent Skill

canvas-course-qc 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

954

周安装

41

GitHub Stars

115

下载量

335
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:canvas-course-qc(画布课程质量控制)
来源仓库:https://github.com/vishalsachdev/canvas-mcp
仓库路径:skills/canvas-course-qc
安装命令:
npx skills add https://github.com/vishalsachdev/canvas-mcp --skill canvas-course-qc
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/vishalsachdev/canvas-mcp --skill canvas-course-qc

简介

canvas-course-qc 提供自动化课程质量检查功能,可验证课程结构、内容完整性、发布状态并报告优先级问题。

  • 适合学习设计师或教师在学期开始前对 Canvas 课程进行合规性审查与准备工作。
  • 需连接 Canvas MCP 服务器,用户须具备 instructor、TA 或 designer 角色,建议在课程发布前运行。
  • 可通过环境变量启用 FERPA 数据匿名化以保护学生隐私,输出结果包含问题清单与修复建议。
  • 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

Canvas Course QC

Automated quality checklist for Learning Designers to verify a Canvas course is ready for students. Runs structure, content, publishing, and completeness checks — then reports issues by priority.

Prerequisites

  • Canvas MCP server must be running and connected.
  • Authenticated user must have instructor, TA, or designer role in the target course.
  • Best run before the semester starts or before publishing a course to students.

Steps

1. Identify Target Course

Ask the user which course to QC. Accept a course code, Canvas ID, or course name.

If not specified, prompt:

Which course would you like to quality-check?

Use list_courses to look up available courses if needed.

2. Retrieve Course Structure

Call get_course_structure(course_identifier) to get the full module-to-items tree in one call.

This returns all modules with their items, publishing states, and summary statistics.

3. Run Structure Checks

Analyze the module tree for structural issues:

CheckPriorityWhat to Look For
Empty modulesWarningModules with 0 items (confusing to students)
Naming consistencySuggestionDo all modules follow the same pattern? (e.g., "Week N:", "Unit N:")
Module countSuggestionDoes it match expected count for course length?
Item orderingSuggestionSubHeaders present for organization?

4. Run Content Checks

Call list_assignments(course_identifier) and check each assignment:

CheckPriorityWhat to Look For
Missing due datesBlockingGraded assignments without a due_at date
Missing descriptionsWarningAssignments with empty or null description
Missing pointsWarningAssignments without points_possible set
Date sequencingWarningDue dates that don't follow module order
Rubric coverageSuggestionGraded assignments without an associated rubric

For pages, check if any pages in modules have empty body content using get_page_content for pages flagged in the structure.

5. Run Publishing Checks

Using the structure data:

CheckPriorityWhat to Look For
Ghost itemsBlockingPublished items inside unpublished modules (invisible to students)
Unpublished modulesWarningModules that may need publishing before semester
No front pageWarningCourse has no front page set

Check for front page by calling list_pages(course_identifier) and looking for front_page: true.

6. Run Completeness Checks

Compare module structures to find inconsistencies:

CheckPriorityWhat to Look For
Inconsistent structureWarningMost modules have 4 items but some only have 1
Missing item typesSuggestionMost modules have an Assignment but some don't

Build a "typical module" profile from the most common item-type pattern, then flag modules that deviate.

7. Generate QC Report

Present results grouped by priority:

## Course QC Report: [Course Name]

### Summary
- Modules: 15 | Items: 67 | Assignments: 15 | Pages: 20
- Issues found: 3 blocking, 5 warnings, 2 suggestions

### Blocking Issues (fix before publishing)
1. Assignment "Final Project" has no due date
2. Published "Week 5 Quiz" is inside unpublished "Week 5" module (invisible to students)
3. Assignment "Midterm" has no due date

### Warnings (should fix)
1. 2 empty modules: "Week 14", "Week 15"
2. 3 assignments missing descriptions: HW 3, HW 7, HW 12
3. No front page set for course
4. Due dates out of order: Week 8 assignment due before Week 7
5. "Week 3" module has 1 item while typical modules have 4

### Suggestions (nice-to-have)
1. Module naming: 13/15 use "Week N:" pattern but "Midterm Review" and "Final Review" don't
2. 5 graded assignments have no rubric attached

8. Offer Follow-up Actions

After presenting the report, offer actionable next steps:

Would you like me to: 1. Auto-fix publishing -- Publish all unpublished modules (with confirmation) 2. Show details -- Expand on a specific issue 3. Run accessibility audit -- Check WCAG compliance (uses canvas-accessibility-auditor skill) 4. Check another course

For auto-fix, use update_module or bulk_update_pages with user confirmation before each batch.

MCP Tools Used

ToolPurpose
list_coursesFind available courses
get_course_structureFull module tree with items
list_assignmentsAssignment details for content checks
get_assignment_detailsDeep-dive on flagged assignments
list_pagesCheck for front page
get_page_contentVerify pages have content
list_all_rubricsCheck rubric coverage
update_moduleAuto-fix: publish modules
bulk_update_pagesAuto-fix: publish pages

Example

User: "QC check for BADM 350"

Agent: Runs all checks, outputs the prioritized report.

User: "Fix the publishing issues"

Agent: Publishes the 2 unpublished modules after confirmation.

Notes

  • This skill is designed for Learning Designers who manage course structure before students access it.
  • Run this before each semester or after major content updates.
  • Pairs well with canvas-accessibility-auditor for comprehensive course review.

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

35.54%
按下载量换算119

Claude

29.94%
按下载量换算100

Cursor

22.16%
按下载量换算74

Gemini CLI

10.08%
按下载量换算34

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

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。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