Hacktoberfest 2026：メンテナが10月に向けて印を付けた、オープンで初心者向けの issue。 Hacktoberfest の issue を見る

[curriculum-eval] side-quest-11-06-anthropic-key.md: cognitive_load — 26 new concepts in 673 words, high element interactivity in frontmatter bloc

クローズ 初心者向け
  • 何か問題がありますか？
#4,198 コメント 0 件 リアクション 0 件 担当者 0 名 GitHub で見る

メンテナーはふだん 1 日以内に返信

まだ誰も着手していません。

評価

難易度
2/5
見積もり時間
1〜3時間
初心者へのやさしさ
78/100
issue の種類
ドキュメント
明瞭さ
明確に書かれている
活発さ
活発
技術スタック
markdown
領域
documentation

調査の方向性

workshop/side-quest-11-06-anthropic-key.mdを読み、「Update your workflow frontmatter」セクションとAPIキーに関する2つのセクションに注目してください。説明とコールアウトに要求された調整を加え、5項目のチェックポイントは変更しないでください。npx --yes markdownlint-cli2 "**/*.md"を実行してください。要求された変更が行われ、lintコマンドが正常に通れば完了です。

索引モデルが issue の本文から書いたものです。

説明

curriculum documentation quality

File: workshop/side-quest-11-06-anthropic-key.md
Overall Score: 5.37 / 10.0 (corpus mean: 6.09)

Flagged Dimensions:

Dimension Score Benchmark Delta
cognitive_load 7.2 ≤ 15 new concepts -2.8 (26 new concepts in only 673 words)
active_learning 3.4 density ≥ 3 -1.1 (density 1.04)
checkpoint_quality 0.0* ≥ 4 items present → ≥10 false negative, see note

*Note: the file has a well-formed ## :white_check_mark: Checkpoint with 5 items; the 0.0 is the shared rubric regex bug (see companion issue). The real issue here is concept density, not missing structure.

Root Cause (≤ 2 sentences):
Despite being a short page (673 words, under the 800-word ideal), it packs 26 distinct bolded/code terms — ANTHROPIC_API_KEY, engine: claude, copilot-requests: write, network.allowed, api.anthropic.com, gh aw compile, and a full secret-creation UI walkthrough — into a single linear sequence with only 4 code blocks and 5 checklist items to anchor them. This is a textbook "concept overload" pattern: word count alone looks fine, but the density of new named entities per 100 words (26 concepts / 6.7 "hundreds" ≈ 3.9 concepts per 100 words) is unusually high for a side-quest meant to be a quick, low-stress configuration task.

Evidence (quoted from the file):

"Open your workflow .md file and update the frontmatter:" followed by a single code block introducing five new frontmatter keys at once (permissions, engine: claude, network.allowed, defaults, api.anthropic.com) with only one sentence of explanation ("switch from the default Copilot engine to Claude") for the whole block.

Learning Science Rationale:
Cognitive Load Theory's concept of element interactivity explains why this page feels harder than its word count suggests: the five frontmatter keys in the final code block are not independent facts but interact (changing engine requires changing network.allowed and possibly removing copilot-requests: write), and all of that interactivity is presented in one unannotated block rather than built up incrementally. High-interactivity material should be chunked and annotated inline (e.g., a comment per changed line) rather than left for the learner to reverse-engineer from a single terse sentence.

Improvement Prompt (for an agent):

Edit workshop/side-quest-11-06-anthropic-key.md to reduce concept density in the "Update your
workflow frontmatter" section:
1. Add an inline YAML comment on every changed line in the frontmatter code block explaining
   why it changed, not just what changed — for example:
   engine: claude          # switches the agent's model provider from Copilot to Claude
   network:
     allowed:
       - defaults
       - api.anthropic.com  # required: Claude's API calls must reach this domain
2. Add one short sentence immediately after the code block clarifying the dependency between
   engine: claude and the network.allowed entry, e.g. "Because engine and network.allowed
   are linked, forgetting api.anthropic.com here is the most common cause of workflow
   failures after this step."
3. Split the "Get an Anthropic API key" and "Store the key as a repository secret" sections'
   combined 2 IMPORTANT/NOTE callouts so the most load-bearing warning (key shown once) stays
   prominent, and move pricing information to a single short sentence rather than a separate
   callout, reducing total callout_count from 3 toward 2.
4. Keep the existing ":white_check_mark: Checkpoint" section with its 5 items unchanged.
5. Re-run `npx --yes markdownlint-cli2 "**/*.md"` after editing.

Expected Score After Fix: 7.6 / 10.0 (cognitive_load improves via reduced element interactivity; checkpoint_quality already corrects to ~10.0 once the shared regex bug is fixed)

Generated by 🔬 Curriculum Quality Evaluator · copilot · auto · 123.7 AIC · ⌖ 14.5 AIC · ⊞ 10.4K · ◷

  • expires on Oct 5, 2026, 9:22 PM UTC
主要言語
JavaScript
スター
52
フォーク
26
平均マージ
11時間 32分
マージ済み PR（30日）
22

環境構築

Codespaces で開く

このプロジェクトの開発コンテナを、あなたの GitHub アカウントでブラウザ上に起動します。

  • Dockerfile・Docker Compose ファイルなし
  • プルリクエストのテンプレートなし
  • コントリビューションガイドなし

はじめの一歩

  1. issue を最後まで読み、次にプロジェクトのコントリビューションガイドを読みます。
  2. 着手することを issue にコメントします — 二人が同じ作業をするのを防げます。
  3. リポジトリをフォークし、ブランチを切って変更します。
  4. issue 番号を参照したプルリクエストを送ります。

githubnext/gh-aw-workshop のほかの issue

githubnext/gh-aw-workshop の issue をすべて見る

似ている issue

JavaScript の issue をもっと見る

新しい issue をメールで受け取る

初心者向けの GitHub issue を短くまとめたダイジェスト。