CtrlK
BlogDocsLog inGet started
Tessl Logo

cold-start-interview

Run the cold-start interview to learn your IP practice and write your practice profile. Use on first install when the practice profile is missing or still contains placeholders, when re-onboarding with --redo, or when re-probing integrations with --check-integrations after connecting or disconnecting an MCP. This is the ONLY skill that should run on a fresh install.

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.

Highly actionable and well-sequenced with strong validation checkpoints, but the body is long and monolithic: motivational framing and inline reference-worthy material inflate the token budget and skip progressive disclosure into separate files.

Suggestions

Tighten or cut motivational framing (e.g. "Why this matters", "This isn't a disclaimer", repeated practice-mix branching rationale) to lift conciseness toward lean.

Extract the stable reference material — role/privilege framings, integration connection how-tos, and the company-profile question list — into reference files the body points to, so SKILL.md becomes an overview that progressively discloses detail.

De-duplicate the practice-mix branching guidance, which is stated in both the "Practice mix" section and the Part 1 / downstream pruning notes.

DimensionReasoningScore

Conciseness

The ~480-line body is purposeful but padded — motivational prose ("Why this matters", "This isn't a disclaimer") and restated branching logic push it past lean; it is not a 1 because it avoids generic-concept explanation, but not a 3 because every token does not earn its place.

2 / 3

Actionability

Copy-paste interview scripts, enumerated option sets, exact config paths, and explicit MCP-call validation rules give fully executable, specific guidance; per the scoring notes the absence of code in this instruction-only skill is not penalized.

3 / 3

Workflow Clarity

A clear numbered sequence (Instructions 1-8, Parts 0-6) with explicit validation checkpoints — placeholder checks, fact-verification feedback loops, "only report ✓ on a successful MCP call", pre-write review of skipped questions, and diff-before-overwrite.

3 / 3

Progressive Disclosure

No bundle files exist and the skill is a monolithic ~480-line SKILL.md; its references are clearly signaled one-level pointers (so not a 1), but lengthy role framings, privilege notes, and integration how-tos remain inline rather than split into reference files.

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, third-person description that names concrete actions, gives explicit multi-situation trigger guidance, and asserts a clear distinctiveness claim. It cleanly answers both what the skill does and when to use it.

DimensionReasoningScore

Specificity

Names multiple concrete actions — "Run the cold-start interview to learn your IP practice and write your practice profile" — matching the anchor that lists several specific actions, not merely a domain plus a few actions.

3 / 3

Completeness

Clearly answers what (run interview, learn practice, write profile) and when ("Use on first install...", re-onboarding, integration changes) with an explicit trigger clause, so it is not capped at 2.

3 / 3

Trigger Term Quality

Explicit "Use on first install when the practice profile is missing or still contains placeholders, when re-onboarding with --redo, or when re-probing integrations with --check-integrations" covers natural trigger situations a user would actually describe.

3 / 3

Distinctiveness Conflict Risk

"This is the ONLY skill that should run on a fresh install" plus IP-practice-specific triggers give it a clear niche unlikely to fire for the wrong skill.

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.