cold-start-interview

Run the cold-start interview to learn your commercial contracts practice and write your team practice profile. Use on first use of the plugin, when `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md` is missing or still contains template placeholders, or when the user says "set up the plugin", "configure commercial contracts", "onboard me", or "let's get started". This is the only skill that should run on a fresh install.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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 body is highly actionable with strong workflow sequencing and validation checkpoints, but it is verbose for its token budget — motivational prose and a quadruple-documented --side flag inflate it — and it keeps a large profile template inline rather than using one-level-deep reference files for progressive disclosure.

Suggestions

Consolidate the --side flag behavior, which is currently explained in the top Instructions, its own section, the dedicated '## --side flag' section, and the Part 1 handling notes — state it once authoritatively and reference back.

Extract the full practice profile markdown template (roughly lines 401-572) into a references/practice-profile-template.md file and link to it, keeping SKILL.md an overview rather than a monolithic ~630-line file.

Trim the motivational 'Why this matters' and 'Fresh professional profile' prose to operational essentials; the persuasive framing competes with context budget without changing what Claude does.

Dimension	Reasoning	Score
Conciseness	The body is actionable and domain-specific, but includes motivational prose ('Why this matters', 'Fresh professional profile', orientation speeches) and repeats the --side flag across four separate sections, so it could be tightened rather than being lean throughout.	2 / 3
Actionability	Provides copy-paste-ready guidance throughout — quoted interview scripts, exact config paths, explicit flags, and a full markdown template for the practice profile with concrete table structures, fully executable by Claude.	3 / 3
Workflow Clarity	The multi-step interview has a clear numbered sequence, explicit config-state checking, and validation checkpoints such as verifying user-stated legal facts, pause/resume with [PENDING] markers, and reviewing skipped questions before writing the profile.	3 / 3
Progressive Disclosure	The skill is a single ~630-line monolithic file with well-organized headers, but no in-bundle references; the ~170-line practice profile template is inline content that would benefit from being split into a separate reference file, so structure is present but content that should be separate stays inline.	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 concise, written in third-person imperative voice, names concrete actions, and provides explicit trigger phrases plus a file-state condition for when to run. It cleanly answers both 'what' and 'when' with no fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'Run the cold-start interview to learn your commercial contracts practice and write your team practice profile' — matching the score-3 anchor listing several specific concrete actions, not vague language.	3 / 3
Completeness	Explicitly answers both what (run interview, learn practice, write profile) and when ('Use on first use of the plugin, when [path] is missing or still contains template placeholders, or when the user says ...'), with an explicit Use-when trigger clause.	3 / 3
Trigger Term Quality	Includes natural phrases a user would actually say — 'set up the plugin', 'configure commercial contracts', 'onboard me', 'let's get started' — giving good coverage of common variations rather than jargon.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche — 'This is the only skill that should run on a fresh install' — with distinct triggers tied to a specific config path, making it unlikely to fire for the wrong skill.	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 (644 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: commercial-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.