session

Run a focused N-question study session on a subject — MBE, essay, or flashcards. Tracks performance and updates the study plan. Use when the user says "run me 10 questions on [subject]", "do a session on [subject]", "let's do 5 cards on [subject]", or wants to drill a fixed number of questions and have the plan adapt.

Quality

93%

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

87%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, actionable workflow with concrete paths, flag routing, and a defined report format. The only gap is the absence of an explicit validation/verification step before persisting batch session results to the study plan.

Suggestions

Add a verification checkpoint before step 6's write — e.g., confirm the loaded study-plan.yaml parses and matches the expected schema before appending to session_history.

For the --essay/--mbe branches, state explicitly how a failed or ambiguous grade is resolved (re-grade, flag, or skip) so the batch loop has a feedback path.

Specify what to do if a referenced file (CLAUDE.md config or study-plan.yaml) is missing or malformed, so step 2–3 loading has an explicit fallback.

Dimension	Reasoning	Score
Conciseness	Lean and directive throughout — no preamble explaining what an MBE or flashcard is, each step assumes competence and earns its tokens ("Load ... study-plan.yaml ... Read session_history", "Route by method flag").	3 / 3
Actionability	Gives concrete, executable guidance: exact config paths to load, flag-based routing (--mbe/--essay/--flashcards), per-question grading behavior, and a precise report schema (Score, Missed with subtopic tags, Pattern, next recommendation).	3 / 3
Workflow Clarity	Steps 1–7 are clearly sequenced with conditional branches ("if it exists", "If study-plan.yaml exists / If not"), but this batch operation (running N questions then writing session results to plan files) has no explicit validation or verification checkpoint, so per the batch-operation guideline workflow clarity is capped at 2.	2 / 3
Progressive Disclosure	Under 50 lines with no bundle files needed; the single well-organized numbered list serves as a clear overview, and cross-skill routing (bar-prep-questions, flashcards, study-plan) is appropriately signaled rather than inlined.	3 / 3
	Total	11 / 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 strong description: third-person voice, concrete capabilities, explicit natural-language triggers, and a clear non-overlapping niche. It answers both what and when without padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Run a focused N-question study session", "Tracks performance", "updates the study plan" — across MBE, essay, and flashcard modes, matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	Clearly answers what it does (runs a focused N-question session, tracks performance, updates the plan) and when to use it via an explicit "Use when the user says..." clause, satisfying both halves.	3 / 3
Trigger Term Quality	Quotes natural phrases a user would actually say — "run me 10 questions on [subject]", "do a session on [subject]", "let's do 5 cards on [subject]" — giving good coverage of natural trigger terms.	3 / 3
Distinctiveness Conflict Risk	The niche — fixed-count question drilling with plan adaptation — is distinct, and the quoted triggers ("run me 10 questions", "let's do 5 cards") are unlikely to fire for unrelated 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/session/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.