CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/synthetic-pii-generator

Generates realistic-but-fake personally identifiable information (PII) - emails, phone numbers, SSNs / national IDs, addresses, names, credit-card numbers (test BIN ranges), date-of-birth - for non-production environments. Wraps Faker / mimesis with PII-aware constraints so generated values match real format expectations (Luhn-valid card numbers, region-valid phone formats, ITIN/SSN format) without ever generating real-person data. Use when seeding test environments, building demo data, or replacing real PII in copied datasets.

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Overview
Quality
Evals
Security
Files

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable skill body with executable code, clear step sequencing, and verification checkpoints, plus a properly externalized one-level-deep reference bundle. The main weakness is mild verbosity: the Overview re-explains the synthetic-PII concept and one line in Step 1 repeats it, which keeps conciseness at level 2.

Suggestions

Tighten the Overview: drop the definitional sentence ('Synthetic PII is data that looks like the real thing...') since Claude already understands PII, and lead directly with what the skill does.

Remove the redundant trailing line in Step 1 ('the matching real-data pattern (format) without matching a real person') which restates the Overview; the preceding table already conveys intent.

Trim the 'Limitations' prose into a denser bullet list to recover token budget without losing the KYC-drift, locale-coverage, and tokenization distinctions.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete tables, code, and anti-patterns, but the Overview re-explains a concept Claude already knows ('Synthetic PII is data that looks like the real thing... but never matches a real person') and the closing line of Step 1 ('the matching real-data pattern (format) without matching a real person') repeats the same idea; it could be tightened, so it sits at level 2 rather than the lean level 3.

2 / 3

Actionability

Provides fully executable, copy-paste-ready snippets (Faker email with safe/unsafe contrast, mimesis Address(Locale.JA), date_of_birth(minimum_age=18, maximum_age=80)) plus concrete YAML fixtures and runnable bash verification commands, matching the level-3 anchor for executable code/commands.

3 / 3

Workflow Clarity

Sequences Step 1 (classify) → Step 2 (generate safe values) → Step 3 (persist markers) with an explicit 'Verification commands' block acting as a validation checkpoint for the batch PII-generation operation; validation steps are present rather than missing, satisfying the level-3 anchor.

3 / 3

Progressive Disclosure

Body is an overview with a well-signaled, one-level-deep reference to references/pii-lookup-tables.md (a real verified file), and the bulky lookup tables are correctly externalized rather than inlined, matching the level-3 anchor of a clear overview pointing to clearly signaled references.

3 / 3

Total

11

/

12

Passed

Description

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.

A strong, third-person description that names specific PII data types and format constraints, and pairs them with an explicit 'Use when' trigger clause. It is comprehensive and distinguishable; the only minor weakness is that the what-clause is dense, which slightly reduces scannability but not the substantive completeness.

DimensionReasoningScore

Specificity

Enumerates many concrete data types and actions ('emails, phone numbers, SSNs / national IDs, addresses, names, credit-card numbers (test BIN ranges), date-of-birth') plus format constraints ('Luhn-valid card numbers, region-valid phone formats, ITIN/SSN format'), matching the level-3 anchor listing multiple specific concrete actions.

3 / 3

Completeness

Explicitly answers both what ('Generates realistic-but-fake... PII... Wraps Faker / mimesis with PII-aware constraints') and when ('Use when seeding test environments, building demo data, or replacing real PII in copied datasets'), matching the level-3 anchor that pairs a what-clause with an explicit 'Use when' trigger.

3 / 3

Trigger Term Quality

Contains natural user-facing terms a person would say when needing the skill ('PII', 'emails, phone numbers, SSNs... addresses, names, credit-card numbers... date-of-birth', 'test environments, building demo data', 'real PII in copied datasets'); not merely score-2 because coverage spans common variations across data types rather than a single keyword.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (synthetic PII for non-production environments) with distinct triggers unlikely to overlap with other skills; not score-2 because it does not read as a generic data/document skill.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

Table of Contents