CtrlK
BlogDocsLog inGet started
Tessl Logo

cold-start-interview

Practice-profile interview that recommends and installs a starter pack of community legal skills. This IS the cold start for the whole ecosystem — it asks what kind of lawyer you are and recommends what to install first. Use on fresh install, when the user says "get me started" or "what should I install", or to re-run the integration-availability check after adding or removing an MCP connector.

71

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

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 procedure with strong validation discipline. The two weaknesses are token efficiency (motivational and rationale prose that could be trimmed) and progressive disclosure (a large monolithic file that would benefit from splitting procedural detail into reference files).

Suggestions

Trim motivational and rationale prose — e.g. the 'Why this matters' paragraph, the '2 minutes / 15 minutes' value-prop preamble, and the 'Ten minutes of setup... a month of use' closing — to tighten conciseness without losing the actionable guidance.

Extract the long allowlist-building procedure (the numbered field-by-field instructions, deployment-context license seeding, and the freshness-reminders markdown table) into a reference file such as references/allowlist-setup.md, keeping SKILL.md as an overview that links one level deep.

Move the canned interview phrasings (Opening, Part 0 prompts, the five questions' quoted text) into references/interview-script.md so the main body stays a concise workflow outline.

DimensionReasoningScore

Conciseness

Mostly specific and useful, but padded with motivational prose ('Ten minutes of setup gets you a working profile. A month of use gets you one that reads like you wrote it yourself.'), 'Why this matters' rationale paragraphs, and a value-prop preamble ('2 minutes gets you... 15 minutes adds...') that could be trimmed. It is not a wall of concept explanation, but several passages could be tightened.

2 / 3

Actionability

Provides copy-paste-ready guidance: exact file paths, quoted user-facing phrasings, a concrete freshness-reminder markdown table, and precise validation rules ('Validate each answer shapes to N days, N months, or N years with N a positive integer ≤ 120 — reject free-form prose and re-ask').

3 / 3

Workflow Clarity

Clearly sequenced from cold-start check through install, with explicit validation checkpoints — verify user-stated legal facts before writing, confirm allowlist mode with the user, test MCP connections before reporting ✓, and pause/resume markers for incomplete setups.

3 / 3

Progressive Disclosure

Well-organized into sections, but it is a single ~275-line file with no own-bundle reference files; the allowlist-building procedure, freshness table, and canned question phrasings are inline where they could be split into one-level-deep references. Cross-plugin path references exist but are not this skill's disclosure structure.

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.

A strong description: concrete actions, natural trigger phrases, explicit what-and-when guidance, and a distinct niche. The only minor weakness is the slight marketing tone ('This IS the cold start'), which does not undermine the substance.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'recommends and installs a starter pack', 'asks what kind of lawyer you are', and 're-run the integration-availability check' — rather than vague language. The one marketing line ('This IS the cold start for the whole ecosystem') is mild but does not displace the concrete verbs.

3 / 3

Completeness

Explicitly answers both what it does ('Practice-profile interview that recommends and installs a starter pack') and when to use it ('Use on fresh install, when the user says "get me started"...'), satisfying the explicit 'Use when...' trigger requirement.

3 / 3

Trigger Term Quality

Includes natural phrases users would actually say — 'fresh install', 'get me started', 'what should I install', and 'adding or removing an MCP connector' — covering the common entry points for onboarding.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche — community legal-skill ecosystem onboarding keyed on 'what kind of lawyer you are' — with triggers unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
Reviewed

Table of Contents

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.