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.

74

Quality

93%

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

86%Weight 40%Scale 1-5

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

The body is highly actionable with executable code and verification commands, well-structured into a clear 3-step workflow, and cleanly separates the bulky lookup tables into a one-level-deep reference file. The only room for improvement is minor tightening of a few safety-rationale sentences and adding an explicit validate-fix-retry loop during generation rather than only post-hoc verification.

Suggestions

Trim a few safety-rationale sentences (e.g. 'guaranteed never to deliver to real mailboxes', the collision explanation) to lift conciseness to a 5 without losing the warning intent.

Promote verification into an explicit per-batch validate-fix-retry loop in the workflow steps so a failed range/domain check feeds back into regeneration before persistence, strengthening workflow_clarity.

Consider moving the full PII-tier classification table into the references file if the skill grows, to keep the core workflow lean while preserving the overview pointer.

DimensionReasoningScore

Conciseness

Dense, information-rich body with no padding of basic concepts and only safety-justified elaboration; a few sentences (e.g. 'guaranteed never to deliver to real mailboxes', the collision rationale) could be trimmed without losing clarity.

4 / 5

Actionability

Provides copy-paste-ready Python snippets for each PII type, concrete reserved test ranges, a populated lookup-table reference, and executable jq/grep verification commands covering the common generation cases.

5 / 5

Workflow Clarity

Steps 1-3 (identify fields, use safe values, persist markers) are clearly sequenced with a safety-guarantees checklist and verification commands; validation is present though it is post-generation rather than a per-step validate-fix-retry feedback loop.

4 / 5

Progressive Disclosure

Core workflow lives in SKILL.md while lookup tables are cleanly split into references/pii-lookup-tables.md, referenced twice via clear links one level deep, with a well-organized References section for external resources.

5 / 5

Total

18

/

20

Passed

Description

96%Weight 40%Scale 1-5

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, comprehensive, and clearly answers both what the skill does and when to use it with concrete trigger phrases. It is held back only slightly from full marks by its explicit relationship to sibling synthetic-data skills, which introduces minor overlap risk.

DimensionReasoningScore

Specificity

Enumerates multiple concrete generated PII types (emails, phone numbers, SSNs/national IDs, addresses, names, credit-card numbers via test BIN ranges, DOB) and the concrete action of wrapping Faker/mimesis with PII-aware constraints — comprehensive coverage.

5 / 5

Completeness

Explicitly answers both what ('Generates realistic-but-fake PII ... wrapping Faker / mimesis') and when ('Use when seeding test environments, building demo data, or replacing real PII in copied datasets') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural terms users would say (emails, phone numbers, SSNs, addresses, names, credit-card numbers) plus synonyms (SSNs/national IDs) and context phrases (test environments, demo data, real PII in copied datasets).

5 / 5

Distinctiveness Conflict Risk

Clear niche (synthetic PII for non-production environments) with distinct triggers, but it explicitly wraps/names sibling skills (faker-data, synthetic-data-toolkit, seed-data-curator), creating minor overlap risk with those related skills.

4 / 5

Total

19

/

20

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