[curriculum-eval] curriculum-scorecard: overall page scores and trend analysis

Part Summary

Part	Files	Mean Score	Std Dev
Part 1 — core path (lessons 00–14)	`55`	`8.76 / 10.0`	`±0.48`
Part 2 — advanced (lessons 15+)	`29`	`8.83 / 10.0`	`±0.46`
Overall corpus	`86`	`8.73 / 10.0`	`±0.62`

Note: The corpus includes 2 pages classified as other (no lesson number), with mean 6.74 / 10.0 (±2.52). These are reported in the Other Scores table below.

Part 1 Scores (lessons 00–14)

File	Overall Score
`workshop/07a-your-first-workflow-terminal.md`	`7.73 / 10.0`
`workshop/02a-setup-codespace.md`	`7.88 / 10.0`
`workshop/02c-setup-browser.md`	`8.04 / 10.0`
`workshop/side-quest-09-01f-debugging-checklist.md`	`8.13 / 10.0`
`workshop/05-agentic-workflows-intro.md`	`8.16 / 10.0`
`workshop/side-quest-09-01a-pattern-long-plan-chain.md`	`8.20 / 10.0`
`workshop/side-quest-11-06-anthropic-key.md`	`8.22 / 10.0`
`workshop/side-quest-09-01d-pattern-permission-denied.md`	`8.39 / 10.0`
`workshop/side-quest-13-01-schedule-expressions.md`	`8.40 / 10.0`
`workshop/side-quest-09-01b-pattern-empty-results.md`	`8.41 / 10.0`
`workshop/side-quest-11-08-frontmatter-tools-outputs.md`	`8.41 / 10.0`
`workshop/side-quest-09-01c-pattern-safe-output-blocked.md`	`8.45 / 10.0`
`workshop/side-quest-09-01e-pattern-done-no-write.md`	`8.45 / 10.0`
`workshop/side-quest-13-02-pr-summary-pattern.md`	`8.45 / 10.0`
`workshop/side-quest-11-09-agent-session-phases.md`	`8.46 / 10.0`
`workshop/side-quest-11-01b-workflow-structure.md`	`8.50 / 10.0`
`workshop/side-quest-11-04-annotated-workflow.md`	`8.50 / 10.0`
`workshop/side-quest-07-01-compile-workflow.md`	`8.51 / 10.0`
`workshop/side-quest-06-03a-copilot-requests-permission.md`	`8.54 / 10.0`
`workshop/side-quest-01-02-environment-reference.md`	`8.56 / 10.0`
`workshop/side-quest-13-04-token-optimization.md`	`8.56 / 10.0`
`workshop/08-run-your-workflow.md`	`8.58 / 10.0`
`workshop/05b-agentic-workflows-security.md`	`8.64 / 10.0`
`workshop/side-quest-06-03-copilot-token.md`	`8.64 / 10.0`
`workshop/side-quest-11-05-event-triggers.md`	`8.64 / 10.0`
`workshop/side-quest-13-03-pr-checklist-pattern.md`	`8.65 / 10.0`
`workshop/07d-confirm-model-access.md`	`8.66 / 10.0`
`workshop/side-quest-06-01-install-troubleshooting.md`	`8.67 / 10.0`
`workshop/side-quest-11-07-openai-key.md`	`8.68 / 10.0`
`workshop/14-next-steps.md`	`8.70 / 10.0`
`workshop/09-agentic-editing.md`	`8.71 / 10.0`
`workshop/12-test-and-iterate.md`	`8.74 / 10.0`
`workshop/side-quest-11-02-yaml-frontmatter.md`	`8.75 / 10.0`
`workshop/side-quest-10-02-jailbreak-brief.md`	`8.76 / 10.0`
`workshop/side-quest-05-01-actions-power-user.md`	`8.78 / 10.0`
`workshop/side-quest-13-01-pr-labeler-pattern.md`	`8.79 / 10.0`
`workshop/side-quest-08-01-codespaces-actions-write.md`	`8.80 / 10.0`
`workshop/14b-pr-reviewer-workflow.md`	`8.84 / 10.0`
`workshop/side-quest-12-01-iterate-agent-output.md`	`8.88 / 10.0`
`workshop/08b-interpret-your-run.md`	`8.92 / 10.0`
`workshop/side-quest-09-01-debug-output.md`	`8.94 / 10.0`
`workshop/04-github-actions-intro.md`	`8.96 / 10.0`
`workshop/side-quest-01-01-terminal-basics.md`	`9.00 / 10.0`
`workshop/02b-setup-local.md`	`9.04 / 10.0`
`workshop/07c-your-first-workflow-copilot.md`	`9.24 / 10.0`
`workshop/side-quest-06-02-cca-codespace.md`	`9.25 / 10.0`
`workshop/side-quest-06-03c-copilot-github-token-ui-only.md`	`9.32 / 10.0`
`workshop/side-quest-11-03-better-prompts.md`	`9.36 / 10.0`
`workshop/05c-agentic-workflows-practice.md`	`9.44 / 10.0`
`workshop/side-quest-01-03-permission-errors.md`	`9.56 / 10.0`
`workshop/side-quest-05-02-aw-deep-dive.md`	`9.58 / 10.0`
`workshop/side-quest-06-03b-copilot-github-token.md`	`9.60 / 10.0`
`workshop/side-quest-10-01-agent-brief.md`	`9.70 / 10.0`
`workshop/side-quest-11-01-frontmatter-deep-dive.md`	`9.84 / 10.0`
`workshop/07a-part2-your-first-workflow-instructions.md`	`10.00 / 10.0`

Part 2 Scores (lessons 15+)

File	Overall Score
`workshop/15-conditional-logic.md`	`7.53 / 10.0`
`workshop/17-add-mcp-tools.md`	`8.32 / 10.0`
`workshop/20-persistent-memory.md`	`8.43 / 10.0`
`workshop/side-quest-20-01-memory-patterns.md`	`8.46 / 10.0`
`workshop/side-quest-16-02-secrets-and-permissions.md`	`8.54 / 10.0`
`workshop/side-quest-17-01-mcp-concepts.md`	`8.58 / 10.0`
`workshop/side-quest-26-01-forecast-costs.md`	`8.61 / 10.0`
`workshop/side-quest-17-02-security-architecture.md`	`8.62 / 10.0`
`workshop/side-quest-16-03-token-exfiltration.md`	`8.64 / 10.0`
`workshop/side-quest-17-03-prompt-injection.md`	`8.64 / 10.0`
`workshop/24-self-hosted-runners.md`	`8.65 / 10.0`
`workshop/26-manage-costs-and-budgets.md`	`8.68 / 10.0`
`workshop/side-quest-17-04-permission-escalation.md`	`8.76 / 10.0`
`workshop/16-connect-data-source.md`	`8.78 / 10.0`
`workshop/side-quest-16-01-github-output.md`	`8.79 / 10.0`
`workshop/side-quest-16-04-deterministic-vs-agentic-data-ops.md`	`8.80 / 10.0`
`workshop/side-quest-17-05-supply-chain-mcp.md`	`8.80 / 10.0`
`workshop/21-inline-sub-agents.md`	`8.82 / 10.0`
`workshop/side-quest-15-01-expressions-and-contexts.md`	`8.82 / 10.0`
`workshop/side-quest-16-05-long-lived-credentials.md`	`8.86 / 10.0`
`workshop/18-share-and-reuse.md`	`8.92 / 10.0`
`workshop/side-quest-17-07-repo-poisoning.md`	`9.00 / 10.0`
`workshop/22-error-handling-and-resilience.md`	`9.06 / 10.0`
`workshop/25-audit-and-observability.md`	`9.08 / 10.0`
`workshop/19-research-driven-training-node.md`	`9.14 / 10.0`
`workshop/23-ab-experiments.md`	`9.38 / 10.0`
`workshop/side-quest-25-01-audit-reference.md`	`9.66 / 10.0`
`workshop/side-quest-21-01-sub-agent-syntax.md`	`9.76 / 10.0`
`workshop/side-quest-17-06-output-injection.md`	`9.90 / 10.0`

Other Scores (no lesson number)

File	Overall Score
`workshop/day.md`	`4.96 / 10.0`
`workshop/side-quest-enterprise-setup.md`	`8.52 / 10.0`

Score Trends (history window: 20 commits)

File	Baseline	Latest	Delta	Direction
`workshop/07a-your-first-workflow-terminal.md`	`9.07`	`7.73`	`-1.34`	declining
`workshop/side-quest-13-01-schedule-expressions.md`	`8.68`	`8.40`	`-0.28`	declining
`workshop/14-next-steps.md`	`8.82`	`8.70`	`-0.12`	declining
`workshop/side-quest-11-04-annotated-workflow.md`	`8.53`	`8.50`	`-0.03`	stable
`workshop/side-quest-11-05-event-triggers.md`	`8.66`	`8.64`	`-0.02`	stable
`workshop/side-quest-11-06-anthropic-key.md`	`8.26`	`8.22`	`-0.04`	stable
`workshop/side-quest-11-07-openai-key.md`	`8.70`	`8.68`	`-0.02`	stable
`workshop/side-quest-11-08-frontmatter-tools-outputs.md`	`8.43`	`8.41`	`-0.02`	stable
`workshop/side-quest-16-01-github-output.md`	`8.83`	`8.79`	`-0.04`	stable
`workshop/26-manage-costs-and-budgets.md`	`8.70`	`8.68`	`-0.02`	stable
`workshop/02a-setup-codespace.md`	`7.88`	`7.88`	`+0.00`	stable
`workshop/02b-setup-local.md`	`9.04`	`9.04`	`+0.00`	stable
`workshop/02c-setup-browser.md`	`8.04`	`8.04`	`+0.00`	stable
`workshop/04-github-actions-intro.md`	`8.96`	`8.96`	`+0.00`	stable
`workshop/05b-agentic-workflows-security.md`	`8.64`	`8.64`	`+0.00`	stable
`workshop/07a-part2-your-first-workflow-instructions.md`	`10.00`	`10.00`	`+0.00`	stable
`workshop/07c-your-first-workflow-copilot.md`	`9.24`	`9.24`	`+0.00`	stable
`workshop/07d-confirm-model-access.md`	`8.66`	`8.66`	`+0.00`	stable
`workshop/08-run-your-workflow.md`	`8.58`	`8.58`	`+0.00`	stable
`workshop/08b-interpret-your-run.md`	`8.92`	`8.92`	`+0.00`	stable
`workshop/09-agentic-editing.md`	`8.71`	`8.71`	`+0.00`	stable
`workshop/12-test-and-iterate.md`	`8.74`	`8.74`	`+0.00`	stable
`workshop/15-conditional-logic.md`	`7.53`	`7.53`	`+0.00`	stable
`workshop/16-connect-data-source.md`	`8.78`	`8.78`	`+0.00`	stable
`workshop/17-add-mcp-tools.md`	`8.32`	`8.32`	`+0.00`	stable
`workshop/18-share-and-reuse.md`	`8.92`	`8.92`	`+0.00`	stable
`workshop/19-research-driven-training-node.md`	`9.14`	`9.14`	`+0.00`	stable
`workshop/20-persistent-memory.md`	`8.43`	`8.43`	`+0.00`	stable
`workshop/21-inline-sub-agents.md`	`8.82`	`8.82`	`+0.00`	stable
`workshop/22-error-handling-and-resilience.md`	`9.06`	`9.06`	`+0.00`	stable
`workshop/23-ab-experiments.md`	`9.38`	`9.38`	`+0.00`	stable
`workshop/24-self-hosted-runners.md`	`8.65`	`8.65`	`+0.00`	stable
`workshop/25-audit-and-observability.md`	`9.08`	`9.08`	`+0.00`	stable
`workshop/side-quest-01-01-terminal-basics.md`	`9.00`	`9.00`	`+0.00`	stable
`workshop/side-quest-01-02-environment-reference.md`	`8.56`	`8.56`	`+0.00`	stable
`workshop/side-quest-01-03-permission-errors.md`	`9.56`	`9.56`	`+0.00`	stable
`workshop/side-quest-05-01-actions-power-user.md`	`8.78`	`8.78`	`+0.00`	stable
`workshop/side-quest-05-02-aw-deep-dive.md`	`9.58`	`9.58`	`+0.00`	stable
`workshop/side-quest-06-01-install-troubleshooting.md`	`8.67`	`8.67`	`+0.00`	stable
`workshop/side-quest-06-02-cca-codespace.md`	`9.25`	`9.25`	`+0.00`	stable
`workshop/side-quest-06-03-copilot-token.md`	`8.64`	`8.64`	`+0.00`	stable
`workshop/side-quest-06-03a-copilot-requests-permission.md`	`8.54`	`8.54`	`+0.00`	stable
`workshop/side-quest-06-03b-copilot-github-token.md`	`9.60`	`9.60`	`+0.00`	stable
`workshop/side-quest-06-03c-copilot-github-token-ui-only.md`	`9.32`	`9.32`	`+0.00`	stable
`workshop/side-quest-07-01-compile-workflow.md`	`8.51`	`8.51`	`+0.00`	stable
`workshop/side-quest-08-01-codespaces-actions-write.md`	`8.80`	`8.80`	`+0.00`	stable
`workshop/side-quest-09-01-debug-output.md`	`8.94`	`8.94`	`+0.00`	stable
`workshop/side-quest-09-01a-pattern-long-plan-chain.md`	`8.20`	`8.20`	`+0.00`	stable
`workshop/side-quest-09-01b-pattern-empty-results.md`	`8.41`	`8.41`	`+0.00`	stable
`workshop/side-quest-09-01c-pattern-safe-output-blocked.md`	`8.45`	`8.45`	`+0.00`	stable
`workshop/side-quest-09-01d-pattern-permission-denied.md`	`8.39`	`8.39`	`+0.00`	stable
`workshop/side-quest-09-01e-pattern-done-no-write.md`	`8.45`	`8.45`	`+0.00`	stable
`workshop/side-quest-09-01f-debugging-checklist.md`	`8.13`	`8.13`	`+0.00`	stable
`workshop/side-quest-10-01-agent-brief.md`	`9.70`	`9.70`	`+0.00`	stable
`workshop/side-quest-10-02-jailbreak-brief.md`	`8.76`	`8.76`	`+0.00`	stable
`workshop/side-quest-11-01-frontmatter-deep-dive.md`	`9.84`	`9.84`	`+0.00`	stable
`workshop/side-quest-11-01b-workflow-structure.md`	`8.50`	`8.50`	`+0.00`	stable
`workshop/side-quest-11-02-yaml-frontmatter.md`	`8.75`	`8.75`	`+0.00`	stable
`workshop/side-quest-11-03-better-prompts.md`	`9.36`	`9.36`	`+0.00`	stable
`workshop/side-quest-11-09-agent-session-phases.md`	`8.46`	`8.46`	`+0.00`	stable
`workshop/side-quest-12-01-iterate-agent-output.md`	`8.88`	`8.88`	`+0.00`	stable
`workshop/side-quest-15-01-expressions-and-contexts.md`	`8.84`	`8.82`	`-0.02`	stable
`workshop/side-quest-16-02-secrets-and-permissions.md`	`8.54`	`8.54`	`+0.00`	stable
`workshop/side-quest-16-03-token-exfiltration.md`	`8.64`	`8.64`	`+0.00`	stable
`workshop/side-quest-16-04-deterministic-vs-agentic-data-ops.md`	`8.80`	`8.80`	`+0.00`	stable
`workshop/side-quest-16-05-long-lived-credentials.md`	`8.86`	`8.86`	`+0.00`	stable
`workshop/side-quest-17-01-mcp-concepts.md`	`8.58`	`8.58`	`+0.00`	stable
`workshop/side-quest-17-02-security-architecture.md`	`8.62`	`8.62`	`+0.00`	stable
`workshop/side-quest-17-03-prompt-injection.md`	`8.64`	`8.64`	`+0.00`	stable
`workshop/side-quest-17-04-permission-escalation.md`	`8.76`	`8.76`	`+0.00`	stable
`workshop/side-quest-17-05-supply-chain-mcp.md`	`8.80`	`8.80`	`+0.00`	stable
`workshop/side-quest-17-06-output-injection.md`	`9.90`	`9.90`	`+0.00`	stable
`workshop/side-quest-17-07-repo-poisoning.md`	`9.00`	`9.00`	`+0.00`	stable
`workshop/side-quest-20-01-memory-patterns.md`	`8.46`	`8.46`	`+0.00`	stable
`workshop/side-quest-21-01-sub-agent-syntax.md`	`9.76`	`9.76`	`+0.00`	stable
`workshop/side-quest-25-01-audit-reference.md`	`9.66`	`9.66`	`+0.00`	stable
`workshop/side-quest-26-01-forecast-costs.md`	`8.61`	`8.61`	`+0.00`	stable
`workshop/side-quest-enterprise-setup.md`	`8.52`	`8.52`	`+0.00`	stable
`workshop/05-agentic-workflows-intro.md`	`7.76`	`8.16`	`+0.40`	improving
`workshop/05c-agentic-workflows-practice.md`	N/A	`9.44`	N/A	new
`workshop/day.md`	N/A	`4.96`	N/A	new
`workshop/14b-pr-reviewer-workflow.md`	N/A	`8.84`	N/A	new
`workshop/side-quest-13-01-pr-labeler-pattern.md`	N/A	`8.79`	N/A	new
`workshop/side-quest-13-02-pr-summary-pattern.md`	N/A	`8.45`	N/A	new
`workshop/side-quest-13-03-pr-checklist-pattern.md`	N/A	`8.65`	N/A	new
`workshop/side-quest-13-04-token-optimization.md`	N/A	`8.56`	N/A	new

Overall Trend

Baseline mean score: 8.80
Latest mean score: 8.73
Delta: -0.07
Direction: declining

Bloom's Taxonomy Distribution

Level	Count
remember	5
understand	9
apply	48
analyze	6
evaluate	7
create	11

The corpus has a healthy pyramidal shape with a strong apply base (48 steps) and meaningful coverage at analyze (6) and evaluate (7). Bloom's gap analysis confirms both minimum thresholds are met (has_min_understand_steps: true, has_min_analyze_steps: true). No gap proposals were generated.

Notable Alerts

workshop/07a-your-first-workflow-terminal.md dropped −1.34 points (9.07 → 7.73) — the sharpest decline in the history window. Checkpoint quality fell from full score to 5.0 (only 2 checklist items remaining). Warrants immediate review.
workshop/day.md (new) scores 4.96 — the lowest in the corpus. It is classified as is_learning_page: true but contains no active learning activities and no checkpoint. If this page is a facilitation agenda rather than a learner-facing instructional page, its is_learning_page classification should be reviewed.
workshop/15-conditional-logic.md has 31 new concepts — more than double the 15-concept ideal — driving a cognitive load score of 5.1 and the second-lowest overall score (7.53).

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 · 64.8 AIC · ⌖ 9.59 AIC · ⊞ 6.2K · ◷

expires on Jul 25, 2026, 4:39 AM UTC