Skip to content

improve(workshop): step 15 readability, callout density, and active-learning density#1785

Merged
pelikhan merged 4 commits into
mainfrom
copilot/curriculum-eval-fix-readability-issues
Jul 21, 2026
Merged

improve(workshop): step 15 readability, callout density, and active-learning density#1785
pelikhan merged 4 commits into
mainfrom
copilot/curriculum-eval-fix-readability-issues

Conversation

Copilot AI commented Jul 21, 2026

Copy link
Copy Markdown
Contributor

Step 15 scored below corpus mean: FK grade 6.2 (target 8–12), 4 callout blocks (limit 3), and activity density of 1.45 (target ≥ 3.0/100 words).

workshop/15-conditional-logic.md

  • Callout blocks 4 → 3: converted [!TIP] about ${{ steps.recent.outputs.commit_count }} into inline prose in the frontmatter section
  • Prose density: rewrote short choppy sentences into multi-clause technical prose — "Understand the problem" now explains why hollow reports erode trust; the commit-count explanation covers the full pipeline (git logwc -ltr -d ' '$GITHUB_OUTPUT) in a single cohesive sentence
  • Hands-on exercise added: "Exercise: Add a weekend skip condition" — learners chain && conditions, compile, trigger, and verify the skipped-state icon in the Actions log
  • Concept trimming: stripped inline $GITHUB_OUTPUT / expression minutiae from the NOTE callout; replaced with a richer pointer to the side quest

workshop/side-quest-15-01-expressions-and-contexts.md

Absorbs the 5 excess concepts removed from the main step:

  • "Combine multiple conditions"&&/|| operators with three practical YAML patterns
  • "Gather time-based context with shell steps"date +%A pattern for conditions not available in any GitHub Actions context object, tied directly to the weekend-skip exercise
# Example of the combined condition learners build in the exercise
if: steps.recent.outputs.commit_count != '0' && steps.day.outputs.day != 'Saturday' && steps.day.outputs.day != 'Sunday'

Copilot AI and others added 2 commits July 21, 2026 09:25
…s in step 15

- Reduce callout blocks from 4 to 3 (convert TIP to inline prose)
- Rewrite short sentences into fuller technical prose (target FK 8-10)
- Add hands-on Exercise: weekend skip condition with step-by-step instructions
- Expand side-quest-15-01 with 'Combine multiple conditions' and
  'Gather time-based context' sections covering && / || patterns and
  the date +%A shell technique — absorbing the 5 excess concepts from
  the main step
- Update side-quest checkpoint with two new items

Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
…section in step 15

Per code review: split exercise step 3 into three distinct action items
(compile, trigger, inspect) and remove the now-redundant 'Test your
condition' section — its skipped-step image is preserved inline.

Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
Copilot AI changed the title [WIP] Fix readability issues in 15-conditional-logic.md improve(workshop): step 15 readability, callout density, and active-learning density Jul 21, 2026
Copilot AI requested a review from pelikhan July 21, 2026 09:27
@pelikhan
pelikhan marked this pull request as ready for review July 21, 2026 09:28

@github-actions github-actions Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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 ✅ AW Accuracy PR Reviewer for #1785 · 68.6 AIC · ⌖ 4.81 AIC · ⊞ 4.3K

Comment thread workshop/15-conditional-logic.md Outdated
```

This condition skips the compiler-generated agent job entirely when `commit_count` is `0`.
This condition is evaluated during [compilation](https://github.github.com/gh-aw/reference/compilation-process/) and embedded into the generated lock file, causing the agent job to be skipped entirely whenever `commit_count` evaluates to `'0'`. You can also reference the count inside your prompt text to give the model concrete context — for example: `"Summarise the last ${{ steps.recent.outputs.commit_count }} commits"` anchors the analysis to the actual number of changes rather than leaving the model to guess the scope.

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Inaccuracy: if: is not evaluated during compilation.

The changed line states:

"This condition is evaluated during compilation and embedded into the generated lock file..."

Compilation only embeds the if: expression verbatim into the lock file — the expression is evaluated at runtime by GitHub Actions. This is necessarily true because steps.recent.outputs.commit_count is a step output that only exists when the workflow is running; it cannot be evaluated at compile time.

Suggested fix:

This condition is embedded into the generated lock file during [compilation](https://github.github.com/gh-aw/reference/compilation-process/); at runtime, GitHub Actions evaluates it and skips the agent job entirely whenever `commit_count` evaluates to `'0'`.

@pelikhan

Copy link
Copy Markdown
Contributor

@Copiloy review comment at #1785 (comment)

@pelikhan

Copy link
Copy Markdown
Contributor

@copilot review comment at #1785 (comment)

Compilation only embeds the expression verbatim into the lock file;
GitHub Actions evaluates it at runtime when the step output exists.

Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>

Copilot AI commented Jul 21, 2026

Copy link
Copy Markdown
Contributor Author

@copilot review comment at #1785 (comment)

Fixed in 8fb2c65. The sentence now reads: "This condition is embedded into the generated lock file during compilation; at runtime, GitHub Actions evaluates it and skips the agent job entirely whenever commit_count evaluates to '0'."

@pelikhan
pelikhan merged commit e72a377 into main Jul 21, 2026
@pelikhan
pelikhan deleted the copilot/curriculum-eval-fix-readability-issues branch July 21, 2026 09:47
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[curriculum-eval] 15-conditional-logic.md: readability — FK grade level 6.2 and 4 callout blocks exceed thresholds

2 participants