socratic-drill

Socratic drilling — it asks, you answer, it pushes back. Does NOT give you the answer until you've earned it. Use when the user says "drill me on", "quiz me", "socratic", "test me on [subject]", or wants to study actively.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%Weight 40%Scale 1-3

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

A tight, highly actionable instruction skill with a clear sequenced workflow and well-organized sections; its main weakness is mild duplication between the top-level step summary and the detailed drill section.

Suggestions

Collapse the opening 5-step summary into the detailed 'The drill' section, or make the summary a one-line pointer to it, to remove the duplication that holds conciseness at 2.

State the 'don't give the answer' constraint once authoritatively (e.g. in 'Purpose') and have later sections reference it rather than restating it.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no explanation of contracts or consideration), but the opening 5-step summary largely duplicates the later 'The drill' section, and the 'don't give the answer' rule is restated several times — room to tighten.	2 / 3
Actionability	For an instruction-only skill, the guidance is copy-paste-ready: exact scripted lines per answer branch and a verbatim real-matter warning blockquote to recite.	3 / 3
Workflow Clarity	The drill is clearly sequenced (Pick topic → Ask → Listen/push back → Confirm only when earned) with explicit per-branch feedback loops and checkpoints for stuck/guessing students; this is not a destructive/batch op so the validation-cap does not apply.	3 / 3
Progressive Disclosure	No bundle files exist and none are needed; content is organized into clear, navigable sections with the only external pointer being a user-context config file (not a nested bundle reference), so content is appropriately inline and right-sized.	3 / 3
	Total	11 / 12 Passed

Description

80%Weight 40%Scale 1-3

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, distinctive description with explicit trigger guidance and a clear what/when structure; its only weakness is second-person voice ('you answer'), which the rubric penalizes on the specificity dimension.

Suggestions

Rewrite in third person to avoid the second-person voice penalty, e.g. 'Asks questions, takes answers, pushes back — does not give the answer until it is earned.'

Reframe 'it asks, you answer' as a list of distinct concrete behaviors to better satisfy the multi-action specificity anchor.

Dimension	Reasoning	Score
Specificity	Concrete behavioral actions are named ('it asks, you answer, it pushes back', 'Does NOT give you the answer until you've earned it'), but the description uses second person ('you answer') which the rubric penalizes by reducing specificity by 1; the multi-action list threshold for a 3 is also not met.	1 / 3
Completeness	Both 'what' (asks/answers/pushes back, withholds the answer) and 'when' (an explicit 'Use when...' clause listing concrete triggers) are clearly answered.	3 / 3
Trigger Term Quality	Natural user phrasings are well covered — 'drill me on', 'quiz me', 'socratic', 'test me on [subject]', 'wants to study actively' — giving good coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	A clear niche (Socratic drilling for active law study) with distinct trigger phrases makes it unlikely to fire for an unrelated skill.	3 / 3
	Total	10 / 12 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: anthropics/claude-for-legal
Path: law-student/skills/socratic-drill/SKILL.md
Commit: 4a6c651

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

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.