SI

savvides/idstack

开发工具

本页由 AI 翻译,技术细节请以原文为准。 查看原文

27 stars 质量 60 趋势 31MIT

基于证据的Claude Code教学设计技能。11项AI技能,用于检查对齐性、可及性、认知负荷和证据强度。可从任何LMS或创作工具导入。

概览

技能是端到端的,并支持版本化插件,但在小版本之间会遇到粗糙的边缘和破坏性变更,同时我们会与真正的教学设计师一起梳理其他工作流程。请参见 CHANGELOG.md 当前版本的新内容。告诉我们哪些地方有缺陷或缺失。 数十年研究表明,详细的反馈能提升学习效果。认知负荷理论已被复制了30年。建设性对齐能显著提升成绩。证据很充分,但大多数课程设计工具并不容易应用。 idstack 是一套开源的循证教学设计技能集,将同行评审的研究引入你的工作流程。运行于 Claude 代码。idstack 审计对齐矩阵,标记认知负荷问题,根据 Bloom 分类法对目标进行分类,并引用每项建议背后的实证证据,而非仅仅摘要论文。 涵盖整个生命周期的技能:分析、设计、制造、导出。

概述(AI 翻译)

状态:测试版(v3.7.0.0) 技能端到端运行,并支持版本化插件,但预计在次要版本之间会有粗糙和破坏性变更,同时我们会与真正的教学设计师一起梳理其他工作流程。请参见 CHANGELOG.md 当前版本的新内容。告诉我们有哪些缺陷或缺失。

数十年研究表明,详细的反馈能提升学习效果。认知负荷理论已被复制了30年。建设性对齐能显著提升成绩。证据很充分,但大多数课程设计工具并不容易应用。

idstack 是一套开源的循证教学设计技能集,将同行评审的研究引入你的工作流程。运行于 Claude 代码。idstack 审计对齐矩阵,标记认知负荷问题,根据 Bloom 分类法对目标进行分类,并引用每项建议背后的实证证据,而非仅仅摘要论文。

涵盖整个生命周期的技能:分析、设计、构建、导出。一个共享的项目清单,能在各会话中记住你的课程。

本页由 AI 翻译,技术细节请以原文为准。

README

以下为原文 README 节选,完整内容请查看原文。

idstack

Status: beta (v3.10.0.0). Skills work end-to-end and ship behind a versioned plugin, but expect rough edges and breaking changes between minor versions while we shake out the rest of the workflow with real instructional designers. See CHANGELOG.md for what’s new in the current release. Tell us what’s broken or missing.

Decades of research say elaborated feedback improves learning. Cognitive load theory has been replicated for 30 years. Constructive alignment measurably raises grades. The evidence is strong, but most course design tools don’t make it easy to apply.

idstack is an open source set of skills for evidence-based instructional design that brings peer-reviewed research into your workflow. Runs in Claude Code. Rather than summarizing papers, idstack audits alignment matrices, flags cognitive load issues, classifies objectives against Bloom’s taxonomy, and references the empirical evidence behind every recommendation.

Skills covering the full lifecycle: analyze, design, build, export. One shared project manifest that remembers your course across sessions. Every recommendation tagged with its evidence tier, from T1 (meta-analyses) to T5 (expert opinion), so you always know how strong the backing is.

Free, MIT licensed, open source. Available as a Claude Code plugin and a Chrome Extension. Have feedback or a feature request?

Quick start

  1. Install idstack (30 seconds, see below). No terminal? Use the Claude desktop app.
  2. Run /idstack:start in a folder for your course. It checks your setup and starts the correct skill.
  3. If you imported a course, run /idstack:course-quality-review to see what the evidence says.
  4. Stop there. You’ll know if this is for you.

See it work

You:    /idstack:course-import

idstack: How do you want to import your course?
         A) IMS Common Cartridge file (.imscc)
         B) Paste course documents
         C) Canvas API
         D) PDF or document file
         E) SCORM package (.zip)

You:    C — here's my Canvas URL and access token.

idstack: Connected. Pulling course data...
         Found: 12 modules, 8 assignments, 4 discussions, 6 outcomes.

         ## Import Quality Triage

         Found 4 flags during import:
         ⚠ 12 modules, only 4 have stated learning objectives
         ⚠ All 8 assessments are auto-graded quizzes (no rubrics)
           [Assessment-8] [T1] — elaborated feedback produces larger
           learning gains than correctness-only
         ⚠ No collaborative activities beyond discussion forums
           [Online-15] [T4] — low social presence predicts weaker outcomes
         ⚠ No accessibility information for video content

         6 objectives pre-classified with Bloom's taxonomy.
在 GitHub 查看完整 README

推荐工具

换一个关键词,或者移除筛选条件。

安装

npx skillfish add savvides/idstack
新手?先看 mcpskill.org 教程 →