cold-start-interview

About-you interview and materials intake — classes, bar jurisdiction, learning style (drill-me vs explain-to-me), past outlines, graded essays, old exams, MBE sets, syllabi, papers. Use on a fresh install, when the user says "set up" or "get started", or with --check-integrations to re-probe connectors.

Quality

85%

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 highly actionable, well-sequenced interview skill with strong validation checkpoints. Its weaknesses are length/repetition and a monolithic structure where substantial blocks could be split into reference files for better progressive disclosure.

Suggestions

Deduplicate the MCP connector-probing guidance: state the ✓/⚪/✗ verification rule once in a dedicated section and reference it from the other spots instead of restating it three to four times.

Factor the large reusable blocks (the real-client-matter check and the connector-availability procedure) into reference files under references/ and link to them one level deep, shrinking SKILL.md toward a lean overview.

Trim the explanatory rationale paragraphs (e.g., 'Why this matters. Every command in this plugin reads from the configuration…') to the minimum needed to motivate the instruction, since they add length without adding executable guidance.

Dimension	Reasoning	Score
Conciseness	The body is ~298 lines with notable repetition — the MCP connector-probing guidance (only report ✓ on a successful response; configured-but-untested marked ⚪) is restated in essence at lines 23, 150–156, 161–163, and 283 — plus rationale paragraphs that could be trimmed; it is mostly efficient but not lean.	2 / 3
Actionability	It gives exact config paths, concrete flags (--redo, --full, --check-integrations), copy-paste user-facing scripts, and specific thresholds (10–20 materials, LIMITED DATA flag, '3 or fewer' caveat); per the instruction-only scoring note, the absence of code is not penalized because the guidance is concrete and executable.	3 / 3
Workflow Clarity	It opens with a numbered 6-step sequence and backs it with explicit validation checkpoints: the 'Before writing — re-read' checklist (contradictions, drifted specifics, skipped gaps), the verify-user-stated-legal-facts feedback loop, and the connector-connectivity verification, with confirm-before-overwrite guarding the write step.	3 / 3
Progressive Disclosure	It is a single long monolithic file with no bundle files present; long inline blocks (the real-client-matter check, the connector-probing procedure, the full interview scripts) could be factored into one-level-deep references, so 'content that should be separate is inline' applies even though section headers are clear.	2 / 3
	Total	10 / 12 Passed

Description

92%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 that is specific, uses natural trigger terms, and explicitly covers both what and when. The only gap is trigger distinctiveness: the setup-oriented triggers are generic and could overlap with sibling cold-start skills.

Suggestions

Add a law-student-scoped qualifier to the trigger clause (e.g., 'Use on a fresh install of the law-student plugin, when the user says "set up my study profile" or "get started"') so the triggers are distinct from sibling cold-start skills and less likely to fire for the wrong plugin.

Lead with the distinctive law-student framing in the first clause so the niche is established before the generic setup triggers appear.

Dimension	Reasoning	Score
Specificity	The description enumerates concrete actions and intake items ("interview and materials intake — classes, bar jurisdiction, learning style (drill-me vs explain-to-me), past outlines, graded essays, old exams, MBE sets, syllabi, papers"), listing multiple specific concrete actions rather than just naming a domain, matching the score-3 anchor.	3 / 3
Completeness	It clearly answers both what ("About-you interview and materials intake — …") and when ("Use on a fresh install, when the user says 'set up' or 'get started', or with --check-integrations …") with an explicit 'Use when…'-style trigger clause, so it is not capped at 2.	3 / 3
Trigger Term Quality	It includes natural phrases a user would actually say ("fresh install", "set up", "get started") and explicitly ties them to invocation, giving good coverage of natural trigger terms.	3 / 3
Distinctiveness Conflict Risk	The what is a clear law-student niche (bar jurisdiction, MBE sets, drill-me vs explain-to-me), but the triggers ("set up", "get started", "fresh install") are generic and shared with sibling cold-start skills, so the 'distinct triggers' bar for a 3 is not met; it sits at 'somewhat specific but could overlap with similar skills'.	2 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 missing	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: anthropics/claude-for-legal
Path: law-student/skills/cold-start-interview/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.