skill-manager

Reference: detailed uninstall, disable, and re-enable workflows for community skills installed via the legal builder hub. Safe by default — refuses to touch first-party plugin skills, confirms before removing files, and logs every action. Loaded by the /legal-builder-hub:uninstall and /legal-builder-hub:disable skills.

Quality

83%

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 tight, executable, well-structured workflow with explicit validation and safety checkpoints and no token waste. It is an instruction-only skill and the guidance is fully actionable without code.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout; assumes competence, avoids explaining concepts Claude knows, and every section earns its place (e.g. compact log YAML block, terse step lists).	3 / 3
Actionability	Concrete, executable guidance: exact paths ('~/.claude/plugins/config/claude-for-legal/legal-builder-hub/install-log.yaml'), exact rename mappings ('SKILL.md → SKILL.md.disabled'), and a literal log entry block.	3 / 3
Workflow Clarity	Clearly sequenced numbered steps with explicit validation checkpoints ('If not found ... stop', 'No deletion without explicit yes') and error-recovery guidance; destructive operations are guarded.	3 / 3
Progressive Disclosure	Well-organized single-file skill (~120 lines, no external references needed) with clear section headers; no nested references and content appropriately self-contained.	3 / 3
	Total	12 / 12 Passed

Description

67%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 and well-scoped to a distinct niche with strong safety framing, but it lacks an explicit 'Use when...' trigger clause and natural user-facing trigger terms. Adding explicit when-to-use guidance would lift completeness and trigger quality.

Suggestions

Add an explicit 'Use when the user wants to uninstall, disable, or re-enable a community skill installed through the legal builder hub' clause.

Lead with what the skill does in user-facing terms rather than 'Reference: ...' framing.

Include natural trigger terms a user would say, e.g. 'remove skill', 'turn off skill', 're-enable skill'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('uninstall, disable, and re-enable workflows') plus specific safeguards ('refuses to touch first-party plugin skills, confirms before removing files, and logs every action').	3 / 3
Completeness	Clearly states what it does, but 'when to use it' is only implied via 'Loaded by the /legal-builder-hub:uninstall and /legal-builder-hub:disable skills' with no explicit 'Use when...' clause, capping completeness at 2.	2 / 3
Trigger Term Quality	Includes relevant terms ('uninstall', 'disable', 're-enable', 'skills') but lacks the natural trigger phrasing a user would say; it is framed as 'Reference: ...' and 'Loaded by the /... skills' rather than user-facing triggers.	2 / 3
Distinctiveness Conflict Risk	Scoped to a clear niche ('community skills installed via the legal builder hub') with first-party refusal, making it unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: anthropics/claude-for-legal
Path: legal-builder-hub/skills/skill-manager/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.