cold-start-interview

Cold-start interview — builds your watchlist, indexes the policy library, and learns your materiality threshold so the monitor surfaces signal instead of noise. Use on fresh install, when reconfiguring (--redo), or when re-checking what connectors are actually responding (--check-integrations).

Quality

81%

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

62%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 content is highly actionable and well-sequenced with strong validation checkpoints, but it is significantly over-long and monolithic. Rationale padding and an absent bundle structure (referenced files don't exist) hold back conciseness and progressive disclosure.

Suggestions

Cut rationale passages like 'Why this matters' and de-duplicate the integration-check guidance (stated at line 14 and again at lines 131-147) to respect the token budget.

Move the long interview scripts and the materiality/feed markdown template blocks into referenced files under references/ so SKILL.md becomes a lean overview with one-level-deep links.

Either create the referenced files (references/company-profile-template.md, QUICKSTART.md) or remove the dangling references so progressive disclosure is honest about what ships with the skill.

Dimension	Reasoning	Score
Conciseness	The body runs ~359 lines with extensive rationale padding ('Why this matters', repeated integration-check instructions at lines 14 and 131-147) and prose-heavy explanations that exceed what Claude needs to execute the interview.	1 / 3
Actionability	Exact config paths, named config sections, ready-to-paste user-facing phrasing, and copy-ready markdown template blocks (materiality threshold, feed configuration) make the guidance fully executable.	3 / 3
Workflow Clarity	A clearly sequenced Part 0-4 flow with explicit checkpoints: pause/resume markers, before-writing review of skipped questions, and verification of user-stated legal facts before they are written to config.	3 / 3
Progressive Disclosure	Section organization is clear and references are named (company-profile-template.md, CLAUDE.md, QUICKSTART.md), but no references/ or assets/ directories exist and the long inline interview scripts and template blocks would be better split into separate files.	2 / 3
	Total	9 / 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 distinctive, with explicit 'Use when...' triggers tied to concrete invocation flags. It cleanly answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Names three concrete actions ('builds your watchlist', 'indexes the policy library', 'learns your materiality threshold') plus a clear purpose, matching the multiple-specific-actions anchor.	3 / 3
Completeness	Clearly answers both what (builds watchlist, indexes policy library, learns materiality threshold) and when ('Use on fresh install, when reconfiguring...'), with an explicit trigger clause.	3 / 3
Trigger Term Quality	'fresh install', 'reconfiguring', '--redo', and '--check-integrations' are explicit invocation triggers a user would naturally issue; coverage is good and specific rather than generic jargon.	3 / 3
Distinctiveness Conflict Risk	A scoped cold-start interview for a regulatory-legal plugin with flag-based triggers occupies a clear niche unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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
Path: regulatory-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.