[curriculum-eval] side-quest-11-06-anthropic-key.md: active_learning — setup page with 26 concepts and low command density

未关闭 适合新手
#5,713 0 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看

维护者通常 1 天内回复

还没有人认领这个 Issue。

评估

难度
2/5
预计耗时
1-3 小时
新手友好度
70/100
Issue 类型
文档
描述清晰度
基本清楚
活跃度
活跃
技术栈
github, markdown
领域
documentation

调研方向

从 workshop/side-quest-11-06-anthropic-key.md 开始,并与 workshop/side-quest-11-07-openai-key.md 对比,找出重复的背景文字。将外部链接精简为指向控制台的链接和一个文档链接,然后把每个 H2 改写为带编号的步骤,每步包含命令 gh secret set ANTHROPIC_API_KEY 和一行 "Expected result"。保留 Before You Start 和 Checkpoint 两个部分。页面变短、步骤可直接复制粘贴,并且 npx --yes markdownlint-cli2 "**/*.md" 通过,即为完成。

由索引模型根据 Issue 内容生成。

描述

curriculum documentation quality

File: workshop/side-quest-11-06-anthropic-key.md
Overall Score: 5.37 / 10.0 (corpus mean: 6.06)

Flagged Dimensions:

Dimension Score Benchmark Delta
cognitive_load 7.2 ≤ 15 concepts 26 concepts (−4.7 on concept count)
active_learning 3.4 density ≥ 3 1.02 per 100 words

Root Cause (≤ 2 sentences):
A short setup how-to (685 words) counts 26 new concepts, mostly provider, console, secret, and frontmatter terms with 11 external links. The steps are separated by prose rather than copy-paste commands, giving a density of 1.02.

Evidence (quoted from the file):

You have an Anthropic account at [console.anthropic.com]((console.anthropic.com/redacted)

Learning Science Rationale:
Mayer's coherence principle says extraneous material, here 11 external links in 685 words, harms learning transfer. Task-based how-to pages perform best with a minimal numbered action sequence, each action followed by an expected result, which also supports verification and self-explanation.

Improvement Prompt (for an agent):

Edit workshop/side-quest-11-06-anthropic-key.md. Reduce external links to the minimum needed (console URL, one docs link). Convert each H2 into a short numbered action sequence with one copy-paste `gh secret set ANTHROPIC_API_KEY` command, and add an "Expected result" line after each command. Remove background explanation that duplicates side-quest-11-07-openai-key.md and link to it instead. Keep the Before You Start and Checkpoint sections. Run: npx --yes markdownlint-cli2 "**/*.md".

Expected Score After Fix: 6.9 / 10.0

Generated by 🔬 Curriculum Quality Evaluator · copilot · auto · ~49 AIC · ⌖ ~1 AIC · ⊞ 5K · ◷

  • expires on Nov 15, 2026, 7:04 AM UTC
主要语言
JavaScript
星标
62
派生
43
平均合并
11 小时 26 分钟
30 天内合并 PR
13

环境准备

在 Codespaces 中打开

在浏览器里用你自己的 GitHub 账号启动这个项目的开发容器。

  • 没有 Dockerfile 或 Docker Compose 文件
  • 没有 Pull Request 模板
  • 没有贡献指南

从这里开始

  1. 先读完整个 Issue,再读项目的贡献指南。
  2. 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
  3. Fork 仓库,在一个分支上完成修改。
  4. 提交 Pull Request,并在描述里引用这个 Issue 编号。

githubnext/gh-aw-workshop 的其他 Issue

查看 githubnext/gh-aw-workshop 的全部 Issue

相似的 Issue

更多 JavaScript Issue

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。