[curriculum-eval] 05-agentic-workflows-intro.md: active_learning — predict-then-reveal pattern missing for key-terms table
Maintainers usually reply within 1 day
Nobody has claimed this yet.
Assessment
- Difficulty
- 1/5
- Estimated time
- Under an hour
- Newbie friendliness
- 88/100
- Issue type
- Documentation
- Clarity
- Clearly specified
- Activity status
- Active
- Tech stack
- github-actions, markdown
- Domain
- content, documentation
Research direction
Edit workshop/05-agentic-workflows-intro.md. Read the existing predict-then-reveal prompt before “The two-file structure” and the nearby “Three key terms” table, then add one comparable prompt before the table. Run npx --yes markdownlint-cli2 "**/*.md"; done means the new prompt is present, consistent with the page’s activities and checkpoint, and lint passes.
Written by the indexing model from the issue text.
Description
File: workshop/05-agentic-workflows-intro.md
Overall Score: 5.4 / 10.0 (corpus mean: 6.1)
Flagged Dimensions:
| Dimension | Score | Benchmark | Delta |
|---|---|---|---|
| active_learning | 2.4 | ≥ activity density 3 (score 10) | -7.6 |
| cognitive_load | 8.5 | ≤ 800 words / ≤ 15 new concepts (score 10) | -1.5 |
Note: the rubric also flags missing_checkpoint, but this is a confirmed tooling bug (see scorecard issue) — the file has a well-formed ## :white_check_mark: Checkpoint with 6 specific checklist items plus a collapsible self-test. Dismissed.
Root Cause (≤ 2 sentences):
This page is the conceptual introduction to agentic workflows (1,107 words, 15 new concepts — near the ideal ceiling) but has only 0.72 activity density: two conceptual diagrams and three named "Activity" sections are described, yet the ratio of code blocks + checklist items to word count is low because most of the content is narrative explanation of the trigger/task-brief/safe-outputs model. The three labeled "Activity" sections (predict-the-answer, classify, write) are good active-learning design, but they're spread thin across a long conceptual narrative, diluting density.
Evidence (quoted from the file):
An Agentic Workflow is a plain-English task brief that an AI agent executes inside GitHub Actions. You write what you want — "summarize open issues and post a daily digest" — and the agent reads your repo, calls tools, and posts the output automatically.
Learning Science Rationale:
Mayer's multimedia principle on generative activity indicates that pairing conceptual diagrams with an explicit retrieval prompt increases retention over passive diagram viewing alone. Here, "The two-file structure" section does ask learners to predict which file GitHub Actions actually runs before showing the diagram — a good technique — but this pattern is not repeated for the "Three key terms" table, missing a low-cost opportunity to convert more of the page's prose into active recall.
Improvement Prompt (for an agent):
Edit workshop/05-agentic-workflows-intro.md to raise activity density by adding one short predict-then-reveal prompt before the "Three key terms" table, similar to the existing "write your prediction" pattern used before "The two-file structure" diagram (e.g., "Before reading the table below, guess: which of trigger, task brief, or safe outputs controls how the workflow writes back to GitHub?"). Keep this consistent with the page's existing three "Activity" sections and its checkpoint. Run npx --yes markdownlint-cli2 "**/*.md" after editing.
Expected Score After Fix: 6.0 / 10.0
Generated by 🔬 Curriculum Quality Evaluator · copilot · auto · 74.5 AIC · ⌖ 11.9 AIC · ⊞ 9K · ◷
- expires on Sep 23, 2026, 3:48 AM UTC
- Dominant language
- JavaScript
- Stars
- 52
- Forks
- 26
- Avg merge
- 12h 25m
- Merged PRs (30d)
- 18
Getting set up
Starts the project's dev container in your browser, under your own GitHub account.
- No Dockerfile or Docker Compose file
- No pull request template
- No contributing guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from githubnext/gh-aw-workshop
-
feedback simulation workshop
Difficulty 2/5 1-3 hours Newbie friendliness 66/100
githubnext/gh-aw-workshop#4370 ·
Maintainers usually reply within 1 day
-
feedback simulation workshop
Difficulty 2/5 1-3 hours Newbie friendliness 64/100
githubnext/gh-aw-workshop#4369 ·
Maintainers usually reply within 1 day
-
feedback simulation workshop
Difficulty 2/5 1-3 hours Newbie friendliness 74/100
githubnext/gh-aw-workshop#4368 ·
Maintainers usually reply within 1 day
-
documentation
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
githubnext/gh-aw-workshop#4366 ·
Maintainers usually reply within 1 day
-
documentation
Difficulty 1/5 Under an hour Newbie friendliness 88/100
githubnext/gh-aw-workshop#4365 ·
Maintainers usually reply within 1 day
All issues in githubnext/gh-aw-workshop
Similar issues
-
Difficulty 2/5 1-3 hours Newbie friendliness 62/100
Maintainers usually reply within 1 day
-
factory-active factory-automatic harness/claude-code task-identify-harness-labels-done task-identify-issue-type-done
Difficulty 2/5 1-3 hours Newbie friendliness 62/100
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 62/100
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
Maintainers usually reply within 1 day
-
documentation good first issue help wanted
Difficulty 1/5 1-3 hours Newbie friendliness 85/100
zmo2s/agent-toolbox#23 ·