cursor-privacy-settings

Configure Cursor privacy mode, data handling, telemetry, and sensitive file exclusion. Triggers on "cursor privacy", "cursor data", "cursor security", "privacy mode", "cursor telemetry", "cursor data retention".

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

65%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 accurate, well-structured, and actionable for configuration tasks, but it functions as a monolithic document that ignores its own bundle files. Linking the existing reference files and trimming the inline detail would materially improve progressive disclosure and conciseness.

Suggestions

Replace the inlined Privacy Mode / Data Flow / Sensitive File Exclusion / Network Security sections with concise overviews that link to the matching reference files (e.g., 'See [privacy-mode.md](references/privacy-mode.md)'), so the body becomes a navigable hub rather than a wall of text.

Move the SOC 2 / GDPR / HIPAA compliance-mapping tables and Enterprise Considerations into a dedicated reference file (e.g., references/compliance.md) and reference it from the body to reduce token load.

Add a short 'Verify your configuration' checklist (e.g., confirm Privacy Mode toggle, check telemetry is off, validate .cursorignore covers secrets) to introduce an explicit validation step into the configuration workflow.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and Cursor-specific (privacy tables, domain allowlists, config JSON), but the ~225-line body includes verbose compliance-mapping and enterprise-considerations sections that could be tightened or offloaded to references.	2 / 3
Actionability	Provides copy-paste-ready guidance: a complete .cursorignore block, settings.json snippets for telemetry/proxy, concrete settings-menu paths, and a domain allowlist — all executable rather than abstract.	3 / 3
Workflow Clarity	Content is well-organized into topical sections, but it is informational/configuration reference material with no multi-step process sequence or validation checkpoints, so it cannot reach the workflow-clarity ceiling.	2 / 3
Progressive Disclosure	Seven reference files exist (privacy-mode.md, data-handling.md, network-security.md, sensitive-file-exclusion.md, etc.) that mirror the body's sections, yet the body never signals or links them and inlines all of that content instead — 'references present but not clearly signaled; content that should be separate is inline'.	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 concise, specific, and uses natural trigger terms with explicit activation guidance. It clearly states what the skill does and when to invoke it without padding or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'Configure Cursor privacy mode, data handling, telemetry, and sensitive file exclusion' — naming several distinct actions rather than vague language.	3 / 3
Completeness	Explicitly answers both what (configure privacy mode/data handling/telemetry/exclusion) and when via the 'Triggers on ...' clause, which is equivalent to a 'Use when' trigger.	3 / 3
Trigger Term Quality	Provides good coverage of natural terms users would say: 'cursor privacy', 'cursor data', 'cursor security', 'privacy mode', 'cursor telemetry', 'cursor data retention'.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (Cursor privacy/security) with distinct trigger phrases, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/saas-packs/cursor-pack/skills/cursor-privacy-settings/SKILL.md
Commit: 399d94c

Reviewed: 4 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.