customize

Guided customization of your employment practice profile — change one thing without re-running the whole cold-start interview. Adjust jurisdictional footprint, risk posture, escalation contacts, hiring review rules, termination review rules, handbook positions, investigation preferences, or matter workspace paths. Use when the user says "change my [thing]", "add a jurisdiction", "update my profile", "edit my config", or "customize".

Quality

100%

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

100%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 well-crafted, actionable workflow with concrete paths, paste-ready user messages, an explicit precondition gate, and a guardrails checklist. Minor weaknesses are mild verbosity in the map parentheticals and the absence of an explicit post-write verification step, but neither pulls any dimension below the top anchor.

Dimension	Reasoning	Score
Conciseness	The body is lean for an instruction-only skill: it assumes Claude's competence, explains no basic concepts, and every section drives action. The customizable-map parentheticals (e.g., "drives state-specific supplement logic") are purposeful context for the downstream-impact step rather than padding, so it sits at the lean/efficient anchor despite a touch of tightening possible.	3 / 3
Actionability	Guidance is concrete and instructive: exact config paths (~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md), ready-to-paste user-facing messages in blockquotes, and specific downstream-impact examples ("/wage-hour-qa and /termination-review will start applying WA rules"). For an instruction-only skill this is copy-paste-ready, specific guidance.	3 / 3
Workflow Clarity	A clear six-step sequence carries an explicit precondition validation gate (step 1's [PLACEHOLDER] check that blocks setup-not-done cases) and a confirm-before-write checkpoint (step 4), plus a Guardrails checklist for risky changes. The one gap is an explicit post-write verification loop, but the operation is a single low-risk field edit (not batch/destructive), so checkpoints are explicit rather than implicit.	3 / 3
Progressive Disclosure	No bundle files exist (no references/scripts/assets), and the SKILL.md is cleanly organized into When this runs / What to do / Guardrails with no nested references or wall-of-text. The content is cohesive in a single self-contained file with no need for external reference splits, meeting the well-organized-sections bar.	3 / 3
	Total	12 / 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, well-scoped description that clearly states the skill's purpose, enumerates concrete capabilities, and provides explicit natural-language triggers for when to invoke it. It is concise and distinct from generic configuration skills.

Dimension	Reasoning	Score
Specificity	The description enumerates eight concrete adjustable categories ("jurisdictional footprint, risk posture, escalation contacts, hiring review rules, termination review rules, handbook positions, investigation preferences, or matter workspace paths"), matching the anchor that lists multiple specific concrete actions rather than naming only a domain.	3 / 3
Completeness	It explicitly answers both what ("Guided customization of your employment practice profile — change one thing...") and when ("Use when the user says..."), with explicit trigger guidance, satisfying the highest anchor.	3 / 3
Trigger Term Quality	It offers several natural phrasings a user would actually say ("change my [thing]", "add a jurisdiction", "update my profile", "edit my config", or "customize"), giving good coverage of common variations rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	The niche is tightly scoped to an employment-legal practice profile ("without re-running the whole cold-start interview"), with distinct profile/config triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: anthropics/claude-for-legal
Path: employment-legal/skills/customize/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.