[curriculum-eval] side-quest-11-06-anthropic-key.md: cognitive_load — 26 new concepts in a 685-word setup guide

未关闭 适合新手
#5,746 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
78/100
Issue 类型
文档
描述清晰度
描述清楚
活跃度
活跃
技术栈
markdown

调研方向

先阅读 workshop/side-quest-11-06-anthropic-key.md,并对照 workshop/side-quest-11-07-openai-key.md,后者是要照搬的结构。然后把页面改写成每个步骤一个操作,并为每个操作给出预期结果(gh secret set ANTHROPIC_API_KEY、gh aw compile),将网络隔离选项折叠为单个 <details> 块,并在保留 :clipboard: Before You Start 和 :white_check_mark: Checkpoint 小节的同时,为每个术语添加一次链接。当页面与同级文件的结构一致且 npx --yes markdownlint-cli2 "**/*.md" 通过时即完成。

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: 5.4 / 10.0 (corpus mean: 6.1)

Flagged Dimensions:

Dimension Score Benchmark Delta
cognitive_load 7.2 ≤ 15 concepts (26) −2.8
active_learning 3.4 density ≥ 3 (1.02) −6.6

(missing_checkpoint dismissed: a 5-item checkpoint exists; see detector issue.)

Root Cause (≤ 2 sentences):
Length is fine, but the page layers account setup, secrets, engine: claude frontmatter, compile and network allow-listing, with heavy inline linking that counts as new concepts. Steps are described in prose with few fenced commands.

Evidence (quoted from the file):

- [ ] (If using network isolation) api.anthropic.com is in the network.allowed list

Learning Science Rationale:
Procedural setup tasks benefit from the worked-example effect (Sweller): one command or UI action per step with an immediate expected result lowers cognitive load more than explanatory prose and parallel optional branches.

Improvement Prompt (for an agent):

Edit workshop/side-quest-11-06-anthropic-key.md: restructure into one action per step with an expected-output line each (e.g. `gh secret set ANTHROPIC_API_KEY` and `gh aw compile`), move the network-isolation option into a single <details> block, link each term once, and target ≤ 15 new concepts and activity density ≥ 3. Mirror the structure of side-quest-11-07-openai-key.md for consistency. Keep :clipboard: Before You Start and the :white_check_mark: Checkpoint section; run `npx --yes markdownlint-cli2 "**/*.md"`.

Expected Score After Fix: 6.0 / 10.0 (≈ 8.5 once the detector is fixed)

Generated by 🔬 Curriculum Quality Evaluator · copilot · auto · ~40 AIC · ⌖ ~1 AIC · ⊞ 5K · ◷

  • expires on Nov 16, 2026, 5:04 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。