cold-start-interview

House cold-start interview (request list + prior memo), or --new-deal for deal-specific context. Modular: identifies which practice areas apply (M&A, Board & Secretary, Public Company, Entity Management), then asks targeted questions for each active module and writes only the relevant sections to the plugin config. Use on fresh install, when CLAUDE.md still has [PLACEHOLDER] markers, when starting a new deal, or to re-check integrations or refresh a module.

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.

The content is highly actionable and well-sequenced with strong validation checkpoints, but it is a long monolithic document that repeats some logic and could split its module question banks into reference files for better progressive disclosure.

Suggestions

Consolidate the integration-check guidance into one section and reference it from step 1 and the --check-integrations flag instead of restating the full logic in three places.

Move the four per-module interview banks (Parts 2M, 2B, 2P, 2E) into separate reference files (e.g. references/m-and-a.md) and link to them from the main flow to reduce the monolithic body and improve progressive disclosure.

Trim justificatory 'why this matters' paragraphs to the operative instruction, keeping the concrete phrasings and question lists that drive actionability.

Dimension	Reasoning	Score
Conciseness	The body runs ~500 lines and repeats the integration-check logic in three places (step 1, Part 0 'What's connected?', and the --check-integrations flag) plus justificatory prose like 'An interviewer who makes people re-type what they've already written has failed the first job of an interviewer' that could be tightened; not the lean score-3 case.	2 / 3
Actionability	Highly actionable despite being instruction-only: verbatim blockquote phrasings to recite, exact config paths, concrete per-module question banks, and explicit branching rules ('If the answer is 2 or 3, say this once'), satisfying the executable-guidance bar.	3 / 3
Workflow Clarity	A clear numbered sequence (steps 1-6) flows into sequenced parts (0, 0.5, 1, 2M, 2B, 2P, 2E) with explicit validation checkpoints: the cold-start file check, the verify-user-stated-facts loop, pause/resume markers, and a pre-write quality check.	3 / 3
Progressive Disclosure	It is a single monolithic SKILL.md with no bundle files or one-level-deep references, and the per-module question banks (2M/2B/2P/2E) are content that could be split into reference files but is inline; sections are well-organized, so it is above the score-1 wall-of-text case but not the score-3 split-with-navigation case.	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.

The description is specific, third-person, and covers both what the skill does and when to use it with explicit natural-language triggers. It is concise and clearly distinguishable from other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'identifies which practice areas apply', 'asks targeted questions for each active module', and 'writes only the relevant sections to the plugin config', matching the score-3 anchor for several specific concrete actions.	3 / 3
Completeness	Clearly answers both what (modular interview that writes relevant config sections) and when via an explicit 'Use on fresh install, when CLAUDE.md still has [PLACEHOLDER] markers, when starting a new deal...' clause.	3 / 3
Trigger Term Quality	Natural trigger phrases a user would say appear explicitly: 'fresh install', 'starting a new deal', 're-check integrations', and 'refresh a module', giving good coverage rather than technical jargon alone.	3 / 3
Distinctiveness Conflict Risk	Targets a clear corporate-legal niche (M&A, Board & Secretary, Public Company, Entity Management cold-start setup) with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (501 lines); consider splitting into references/ and linking	Warning
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	12 / 16 Passed

Repository: anthropics/claude-for-legal
Path: corporate-legal/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.