CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/faker-synthetic-data

Substitutes realistic replacement values for PII that a masking or de-identification step removed, nulled, or redacted, so a non-production dataset stays usable. Covers building an injective substitution map that keeps a shared identifier consistent everywhere it appears so joins survive; choosing deterministic (seeded) over random substitution, and the re-identification risk a shared or committed seed reintroduces, since a generator seed is a reproducibility control and not a cryptographic key; preserving field shape where a downstream system validates it, including check-digit values such as payment-card and national-ID numbers plus phone and postal formats; and why a value that merely looks realistic is not yet safe, leaving a residual re-identification measurement over the remaining quasi-identifiers. Use when a masking pipeline has nulled or dropped PII columns and the dataset now needs replacement values that keep cross-table joins intact.

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

100%

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

A well-structured, executable skill body that pairs a clear four-step workflow with validation feedback loops and a real worked example, while offloading depth to a single one-level reference. Concise, actionable, and well organized throughout.

DimensionReasoningScore

Conciseness

Lean and information-dense; assumes competence and avoids explaining generic library mechanics or basic concepts, deferring the full mechanic table to a referenced file while keeping only the runnable core inline.

3 / 3

Actionability

Provides fully executable, copy-paste-ready Python (Faker.seed, fake.unique, luhn check) with concrete asserts rather than pseudocode or abstract direction.

3 / 3

Workflow Clarity

Four-step sequence with explicit validation checkpoints (injectivity assert, no-collision diff against source, before/after join-key cardinality assert) and an anti-patterns table that closes the feedback loop on each failure mode.

3 / 3

Progressive Disclosure

SKILL.md is an overview that signals one clearly-labeled, one-level-deep reference (references/library-surface-and-seeding.md, which exists) for the mechanic tables; content is appropriately split with easy navigation.

3 / 3

Total

12

/

12

Passed

Description

85%

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 precise, concrete description that answers what and when explicitly and carves out a distinct niche. It is let down only by trigger-term quality, leaning on domain jargon over the plain phrases a non-expert user might naturally say.

Suggestions

Add a few plain-language trigger variants (e.g. "fake data", "generate test data", "replace nulled PII") alongside the technical terms to broaden natural-keyword coverage.

Consider front-loading the everyday phrasing before the detailed cryptographic/re-identification qualifiers so the most common trigger surfaces first.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — building an injective substitution map for join consistency, choosing deterministic vs random substitution, preserving check-digit field shapes, and measuring residual re-identification risk over quasi-identifiers.

3 / 3

Completeness

Clearly answers both what ("Substitutes realistic replacement values for PII...") and when, with an explicit "Use when a masking pipeline has nulled or dropped PII columns and the dataset now needs replacement values that keep cross-table joins intact" clause.

3 / 3

Trigger Term Quality

Includes relevant natural terms a user would say ("PII", "masking", "de-identification", "substitution"), but is heavy on specialist jargon ("injective substitution map", "quasi-identifiers", "re-identification risk") and lacks common lay variations.

2 / 3

Distinctiveness Conflict Risk

Occupies a clear niche — synthetic substitution after a masking/de-identification step for join-preservation — with triggers unlikely to fire for unrelated skills.

3 / 3

Total

11

/

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