cold-start-interview

Run the cold-start interview — learns your AI governance practice and writes `~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md` from your AI policy, a reference impact assessment, and key vendor AI agreements. Use when the practice profile is missing or contains `[PLACEHOLDER]` markers, or when user says "set up ai governance plugin", "onboard me", "configure ai governance".

Quality

83%

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 skill is a thorough, highly actionable interview script with strong workflow checkpoints and validation, but it is overlong and monolithic; conciseness and progressive disclosure suffer from inline verbatim coaching and a large embedded template that belong in reference files.

Suggestions

Tighten or relocate the verbatim 'say this' coaching and justification blocks ('Why this matters', 'Fresh professional profile' corollary) to remove padding while keeping the branching logic and interview questions.

Move the full practice-profile template (lines ~448-593) into a references/ file and link to it one level deep, reducing SKILL.md to an overview.

Consider extracting the per-part interview prompts into a reference file so the main SKILL.md stays a concise overview of the workflow.

Dimension	Reasoning	Score
Conciseness	At ~677 lines the body is padded with verbatim model-voice paragraphs, repeated 'say this once' coaching, and justification blocks ('Why this matters', the 'Fresh professional profile' corollary) that could be tightened without losing the domain-specific guidance Claude does not already know.	2 / 3
Actionability	Highly actionable: concrete interview questions, explicit branching logic by practice setting, exact config file paths, a full copy-paste practice-profile template with tables, and specific flags (--redo, --check-integrations).	3 / 3
Workflow Clarity	Clear numbered top-level sequence plus Parts 0-6, with explicit validation checkpoints (cold-start state check, verify user-stated legal facts, MCP tool-call verification before reporting ✓, pre-write gap review, pause/resume markers) and feedback loops.	3 / 3
Progressive Disclosure	Well-organized into sections but monolithic — no bundle files exist, and the ~145-line embedded practice-profile template plus the long interview script are inline content that could be split into one-level-deep references.	2 / 3
	Total	10 / 12 Passed

Description

90%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 strong and complete, clearly stating both capabilities and trigger conditions with natural user phrases. The only issue is second-person voice ('your AI governance practice', 'your AI policy'), which the rubric penalizes on specificity.

Suggestions

Rewrite in third-person voice ('Runs the cold-start interview — learns the user's AI governance practice and writes the config from their AI policy, a reference impact assessment, and key vendor AI agreements.') to avoid the second-person specificity penalty.

Dimension	Reasoning	Score
Specificity	It names concrete actions — 'Run the cold-start interview', 'learns your AI governance practice and writes ... from your AI policy, a reference impact assessment, and key vendor AI agreements' — but the description is written in second person ('your AI governance practice', 'your AI policy'), which the judging guidelines penalize by reducing the specificity score by one.	2 / 3
Completeness	Explicitly answers both what (run the interview, learn the practice, write the config) and when (missing profile, placeholder markers, or named user phrases), with a clear 'Use when ...' clause.	3 / 3
Trigger Term Quality	Good coverage of natural phrases users would actually say — 'set up ai governance plugin', 'onboard me', 'configure ai governance' — alongside state-based triggers ('the practice profile is missing or contains [PLACEHOLDER] markers').	3 / 3
Distinctiveness Conflict Risk	Scoped to AI governance plugin onboarding with a specific config path and distinctive trigger phrases; unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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 (689 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: ai-governance-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.