CtrlK
BlogDocsLog inGet started
Tessl Logo

generating-practice-questions

Generate educational practice questions from lecture notes to test student understanding. Use when users request practice questions, exam preparation materials, study guides, or assessment items based on lecture content.

68

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable skill body that appropriately offloads templates and topic examples to bundle files. Its main gaps are mild redundancy in coverage rules and the absence of an explicit post-generation validation checkpoint.

Suggestions

Add an explicit verification step at the end of the workflow (e.g., 'Before outputting, confirm every question meets its type's quality criteria and that no answer key is included').

De-duplicate the True/False coverage rule, which is stated identically in 'Question Structure' and again under 'Type 1: True/False'.

Consolidate the output-format guidance so the per-format template pointers appear once rather than being introduced across separate sections.

DimensionReasoningScore

Conciseness

Mostly lean and free of padding about concepts Claude already knows, but coverage guidance repeats between the 'Question Structure' and per-type sections (e.g., the 'one per learning objective, or 3-5' T/F rule appears twice) and could be tightened.

2 / 3

Actionability

For an instruction-only skill it gives concrete, specific guidance: input-extraction details (pdfplumber, strip preamble before \begin{document}, preserve math environments), per-type required structures, specific example questions, and pointers to complete templates.

3 / 3

Workflow Clarity

The generation order (T/F → Explanatory → Coding → Use Case) and output structure are clearly sequenced, but there is no explicit validation/verification checkpoint confirming the generated questions satisfy the stated quality criteria before output.

2 / 3

Progressive Disclosure

The body is a well-organized overview with one-level-deep, clearly signaled references to real bundle files — examples in references/examples_by_topic.md and templates in assets/questions_template.tex and assets/markdown_template.md — keeping bulky material out of the main file.

3 / 3

Total

10

/

12

Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that answers both what and when with natural trigger terms and a clear niche. The only mild weakness is that it names a single primary action rather than enumerating several concrete capabilities.

DimensionReasoningScore

Specificity

Names a concrete action and domain ('Generate educational practice questions from lecture notes to test student understanding') but lists only one core action rather than the multiple distinct concrete actions required for a 3.

2 / 3

Completeness

Explicitly states what it does (generate practice questions from lecture notes) and when to use it ('Use when users request practice questions, exam preparation materials, study guides, or assessment items based on lecture content').

3 / 3

Trigger Term Quality

'practice questions, exam preparation materials, study guides, or assessment items' covers the natural phrasings a user would say when requesting this skill.

3 / 3

Distinctiveness Conflict Risk

The lecture-content-to-practice-questions niche with exam-prep/study-guide triggers is clearly distinct and unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
datawhalechina/agent-skills-with-anthropic
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.