[curriculum-eval] 15-conditional-logic.md: active_learning — 25 new concepts with activity density of 1.16

[github-actions]

File: workshop/15-conditional-logic.md
Overall Score: 8.20 / 10.0 (corpus mean: 8.78)

Flagged Dimensions:

Dimension	Score	Benchmark	Delta
cognitive_load	7.2 / 10	≤ 15 new concepts (10)	−2.8
active_learning	3.8 / 10	≥ 3 activity density (10)	−6.2

Root Cause (≤ 2 sentences):
The step introduces 25 new concepts across 864 words (commit_count, GITHUB_OUTPUT, steps context, if: key, deterministic steps, conditional short-circuit, shell commands, wc -l, echo redirect, and more) while producing only 5 code blocks across a dense narrative — an activity density of 1.16. Despite improved scores from a prior fix (+0.75 trend), the concept-to-practice ratio remains too high for a step that requires learners to integrate three independent mechanisms simultaneously.

Evidence (quoted from the file):

"The approach breaks into three parts: 1. Run a shell command to count commits from the last 24 hours and write the result to $GITHUB_OUTPUT. 2. Reference that output using the steps context expression ${{ steps.recent.outputs.commit_count }}. 3. Add a top-level if: key in the workflow frontmatter that skips the agent job when the count evaluates to zero."

Learning Science Rationale:
Sweller's element interactivity principle identifies high-interactivity content (three mechanisms that must be understood together) as especially prone to cognitive overload when presented without scaffolded checkpoints between stages. Mayer's Segmenting Principle recommends pausing between conceptual segments so learners can integrate each chunk before the next is introduced. Adding a "Pause and predict" prompt between each of the three numbered stages would let learners form and test their mental model incrementally.

Improvement Prompt (for an agent):

Edit workshop/15-conditional-logic.md to reduce concept overload and improve active learning:
1. After the "Understand the problem" section and before "Add a commit-count step", add a short "Pause and predict" callout (use a plain blockquote, not an alert) asking: "Before reading further, predict: where in the workflow file will the `if:` condition live — in the frontmatter or in the task brief? Why?"
2. After each of the three numbered stages (commit step / if condition / verify), add one concrete verification step the learner can run locally (e.g., "Run `gh aw compile` and confirm the lock file includes the `if:` key").
3. Expand the Checkpoint to at least 6 items, each tied to one of the three stages plus a final end-to-end run.
4. Do not add numbered headings. Run markdownlint after editing.

Expected Score After Fix: 8.9 / 10.0

Warning

Firewall blocked 1 domain

The following domain was blocked by the firewall during workflow execution:

• awmgmcpg

To allow these domains, add them to the network.allowed list in your workflow frontmatter:

network:
  allowed:
    - defaults
    - "awmgmcpg"

See Network Configuration for more information.

Generated by 🔬 Curriculum Quality Evaluator · 86 AIC · ⌖ 7.39 AIC · ⊞ 6.2K · ◷

• expires on Jul 26, 2026, 4:39 AM UTC