bar-prep-questions

Bar prep questions — MBE or essay, targeted at your weak subjects and bar jurisdiction. Tracks misses and comes back to patterns. Use when the user says "bar prep", "MBE questions", "practice essay", or "test me for the bar".

Quality

88%

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

77%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 strong, highly actionable body with explicit validation gates and feedback loops, but it is a monolithic ~260-line file with notable internal repetition and embedded time-sensitive dates. Splitting reference material into bundle files and de-duplicating the exam-type gate messaging would lift the two middle scores.

Suggestions

Consolidate the exam-type gate: state it once (e.g. in '## Exam type') and have the top workflow and '## Load context' reference it, removing the repeated 'studying the wrong list is the one mistake that isn't recoverable' phrasing and the duplicated NCBE URL emphasis.

Move time-sensitive exam-transition facts (the 'As of the July 2026 administration' NextGen rollout status, jurisdiction adoption lists) into a dedicated 'Current exam landscape' or 'deprecated/old patterns' section so they age in one place rather than in the main flow.

Extract the jurisdiction divergence reference material (the divergence-area lists and per-rule tag rules) and the reusable output templates into referenced files (e.g. references/jurisdiction-handling.md, references/templates.md) so SKILL.md stays an overview with one-level-deep, clearly signaled links.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and the legal bar-exam specifics are load-bearing rather than concepts Claude already knows, but the exam-type gate and 'studying the wrong list is the one mistake that isn't recoverable' message are repeated across the top workflow, '## Exam type', and '## Load context', and the time-sensitive 'As of the July 2026 administration' date is embedded in the main flow rather than a deprecated section.	2 / 3
Actionability	Highly actionable for an instruction skill: exact config paths to load, specific flags (--session/--mbe/--essay), copy-paste-ready markdown templates for session reports, MBE answer explanations, essay feedback, and quoted gate prompts to show the student.	3 / 3
Workflow Clarity	A clear 9-step top-level sequence with two explicitly named validation gates ('Exam-type gate (do not skip)', 'Jurisdiction-rule gate — do not silently default') and feedback loops (explain after each answer, track patterns, session report routing to other drills); the session write is append-only with a fallback path so the destructive-op cap does not apply.	3 / 3
Progressive Disclosure	Well-organized into clear sections (so above a 1), but it is a single ~260-line file with no bundle references at all and content (jurisdiction divergence details, large output templates) that could plausibly be split into reference files; since it exceeds 50 lines, the 'good sections alone = 3' carve-out does not apply.	2 / 3
	Total	10 / 12 Passed

Description

100%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 concise, concrete description that names its domain and several specific actions, pairs the 'what' with an explicit 'Use when...' trigger clause, and occupies a clearly distinct niche. It hits the bar on every dimension without padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — generates 'Bar prep questions — MBE or essay', 'targeted at your weak subjects and bar jurisdiction', and 'Tracks misses and comes back to patterns' — rather than vague language; the main verb voice ('Tracks', 'comes back') is third person, so the possessive 'your' does not trigger a voice penalty.	3 / 3
Completeness	Clearly answers both what it does (MBE/essay questions targeted at weak subjects, tracks misses) and when to use it via the explicit 'Use when the user says...' trigger clause.	3 / 3
Trigger Term Quality	The explicit 'Use when the user says "bar prep", "MBE questions", "practice essay", or "test me for the bar"' clause gives good coverage of natural phrasing a law student would actually say.	3 / 3
Distinctiveness Conflict Risk	A clear niche (bar exam drilling for law students) with distinct triggers ('bar prep', 'test me for the bar') unlikely to conflict with other skills.	3 / 3
	Total	12 / 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/bar-prep-questions/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.