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".
62
75%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/saas-packs/cursor-pack/skills/cursor-privacy-settings/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that concisely lists specific capabilities and provides explicit trigger terms. It uses third person voice correctly and covers both what the skill does and when it should be activated. The trigger terms are natural and well-varied, making it easy for Claude to select this skill appropriately.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Configure Cursor privacy mode, data handling, telemetry, and sensitive file exclusion.' These are distinct, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (configure privacy mode, data handling, telemetry, sensitive file exclusion) and 'when' (explicit trigger terms listed with 'Triggers on' clause serving as the 'Use when' equivalent). | 3 / 3 |
Trigger Term Quality | Includes explicit natural trigger terms that users would say: 'cursor privacy', 'cursor data', 'cursor security', 'privacy mode', 'cursor telemetry', 'cursor data retention'. Good coverage of natural variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific to Cursor privacy/security configuration. The combination of 'Cursor' + privacy/telemetry/data handling creates a clear niche unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a comprehensive reference for Cursor privacy settings with good use of tables and diagrams for information density. Its main weaknesses are that it leans heavily toward informational/reference content rather than actionable instructions Claude can execute, and the compliance/enterprise sections add significant length for content that is more policy documentation than task guidance. The skill would benefit from being trimmed to focus on what Claude can actually configure and verify, with reference material split into separate files.
Suggestions
Split compliance mapping (SOC 2, GDPR, HIPAA) and enterprise considerations into a separate COMPLIANCE.md reference file to reduce the main skill's token footprint
Add a clear top-level workflow: 'When asked to configure Cursor privacy: 1. Enable Privacy Mode, 2. Configure .cursorignore, 3. Set telemetry, 4. Verify settings — with explicit verification at each step'
Remove or condense informational content Claude doesn't need to be told (e.g., what TLS is, what embeddings are, general descriptions of data flow) and focus on actionable configuration steps
Add a decision tree or conditional guidance for common scenarios (e.g., 'If user mentions HIPAA → warn about no BAA, recommend these specific steps')
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-organized but includes some content Claude would already know or could infer (e.g., explaining what TLS is, basic proxy configuration patterns, compliance framework descriptions). The compliance mapping tables and enterprise considerations sections add significant length for information that is largely reference/policy content rather than actionable guidance. However, the tables and diagrams are efficient formats. | 2 / 3 |
Actionability | The skill provides concrete UI paths (e.g., 'Cursor Settings > General > Privacy Mode > ON'), specific settings.json configurations, and .cursorignore examples. However, much of the content is informational/descriptive rather than instructional (data flow diagrams, compliance mapping tables, 'what is stored' tables). There's no way to verify most claims programmatically, and the compliance sections describe policies rather than actions Claude can take. | 2 / 3 |
Workflow Clarity | The verification steps for Privacy Mode are clear (3-step check), and the defense-in-depth layering provides a logical sequence. However, there's no explicit workflow for the overall privacy configuration process — no ordered sequence like 'first do X, then verify Y, then configure Z.' The HIPAA section mentions consulting compliance teams but lacks a structured decision workflow for determining what actions to take. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and sections, and external resource links are provided at the end. However, this is a long monolithic file (~180 lines of content) that could benefit from splitting compliance mapping, network security, and enterprise considerations into separate reference files. No bundle files exist to offload detailed reference content. | 2 / 3 |
Total | 8 / 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.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Commit
8a9cd04
- 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.