cold-start-interview

House cold-start for the litigation plugin — branches by role (in-house, firm associate, solo) and side (plaintiff, defense, both), captures risk calibration, landscape, and house style, and writes the practice profile CLAUDE.md. Use on a fresh install, when the user wants to set up or redo the practice profile, or to re-check available integrations.

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 body is a thorough, highly actionable interview orchestration with strong workflow sequencing and validation checkpoints, but it is overlong for its context budget and ships as a monolithic single file with no progressive disclosure into reference bundles. Tightening the rationale prose and splitting the role-specific paths into reference files would lift the two lowest dimensions.

Suggestions

Trim persuasive rationale and tone-justification prose ('Why this matters', 'This isn't a disclaimer...', 'highest-leverage moments in the product') to pure instruction to improve conciseness.

Move the In-house, Solo, and Firm-associate path detail into separate reference files (e.g. references/in-house-path.md) with one-level-deep links from the main body to improve progressive disclosure.

Consolidate the repeated orientation/preamble scripts into a single referenced block to reduce duplication and token cost.

Dimension	Reasoning	Score
Conciseness	At ~515 lines the body is largely actionable but padded with persuasive rationale and tone-coaching prose ('This isn't a disclaimer...', 'Why this matters', 'one of the highest-leverage moments in the product') that Claude does not need; it could be tightened substantially without losing instruction, so it is not lean enough for a 3.	2 / 3
Actionability	Highly actionable for an instruction-only skill: exact quoted prompts, precise file paths, copy-paste output formats (the ✓/⚪/✗ integration report, the '<!-- SETUP PAUSED AT -->' comment, the LIMITED DATA footer), and explicit branching rules; absence of code is not penalized because the guidance is concrete and ready to use.	3 / 3
Workflow Clarity	A clear top-level sequence (steps 1-7) plus explicit validation checkpoints — 'Before writing — re-read' to catch contradictions/drift, gap surfacing with a mandatory wait, verify-user-stated-legal-facts, and pause/resume feedback loops — giving the feedback loops and checklists the 3 anchor requires.	3 / 3
Progressive Disclosure	No bundle files exist and the skill is a single ~515-line monolith; the three role paths (in-house, solo, firm-associate) and the orientation scripts are inline content that could be split into one-level-deep reference files. It is well-organized with headers but does not meet the 3 anchor's requirement of well-signaled references and appropriately split content, and the under-50-line simple-skill exemption does not apply.	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, complete, and distinct: it names concrete actions, gives an explicit 'Use when...' trigger covering fresh install / setup / re-check scenarios, and targets a clear litigation-setup niche. Voice is third person throughout, so no voice penalty applies.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'branches by role (in-house, firm associate, solo) and side (plaintiff, defense, both), captures risk calibration, landscape, and house style, and writes the practice profile CLAUDE.md' — matching the anchor for multiple specific concrete actions; not a 2 because it goes beyond naming a domain to enumerating distinct actions.	3 / 3
Completeness	Explicitly answers both what ('branches... captures... writes the practice profile CLAUDE.md') and when ('Use on a fresh install, when the user wants to set up or redo the practice profile, or to re-check available integrations') with an explicit 'Use on...' trigger clause.	3 / 3
Trigger Term Quality	Includes natural phrasings a user would say — 'fresh install', 'set up or redo the practice profile', 're-check available integrations' — giving good coverage of real trigger language rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	A clear niche — litigation-plugin cold-start that writes a practice profile — with role/side-specific triggers unlikely to fire for unrelated skills; not generic enough to conflict with other 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 (515 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: litigation-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.