CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/data-masking-techniques-reference

Pure-reference catalog of data-masking techniques and de-identification privacy models. Enumerates the seven canonical masking operators (substitution, shuffling, number/date variance, encryption, hashing, nulling, masking-out / character-scrambling) plus tokenisation, redaction, format-preserving encryption, and Microsoft Presidio's six built-in operators. Distinguishes reversible techniques (pseudonymisation candidates per GDPR Art. 4(5)) from irreversible techniques (anonymisation candidates), and maps them to NIST SP 800-188 privacy models - k-anonymity, l-diversity, t-closeness, differential privacy (deep model definitions in references/). Cites ISO/IEC 20889:2018 for the standard taxonomy. Use to pick the right masking operator per field type and risk level.

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 reference catalog with a clear sequenced workflow and clean one-level progressive disclosure. The only weakness is conciseness: basic technique definitions and framing text restate knowledge Claude already has.

Suggestions

Trim the per-technique definitional prose (e.g. the "Replace the real value..." and "Apply a one-way hash..." openers) down to the skill-specific value-add — reversibility, distribution, referential-integrity, and risk notes — since Claude already knows what hashing, encryption, and masking-out are.

Collapse the repeated GDPR Art. 4(5) framing across the Overview, the pseudonymisation/anonymisation table, and the Anti-patterns row into a single concise statement to cut duplicated tokens.

Consider moving the seven-technique primers' generic "Use for" bullets into the per-field picking table, which already captures the same decision more compactly.

DimensionReasoningScore

Conciseness

Mostly efficient and substantive (operator parameters, decision tables, anti-patterns), but per-technique primers ("Apply a one-way hash (SHA-256 / SHA-512)", "Replace the real value with an authentic-looking value") restate concepts Claude already knows and the body runs ~335 lines for a "pure reference".

2 / 3

Actionability

Concrete, copy-ready guidance throughout: Presidio operator names with parameters, `OperatorConfig(operator_name, params={})` signature, an invocation example, and per-field / anti-pattern decision tables.

3 / 3

Workflow Clarity

"How to use this reference" gives a clearly sequenced 6-step decision process with checkpoints (step 4 "Confirm the scope outcome", step 6 "Cross-check the anti-patterns"), and the worked example walks each field through those steps.

3 / 3

Progressive Disclosure

Body is an overview that offloads deep privacy-model definitions to a single one-level-deep reference, references/privacy-models.md, repeatedly linked with clear markdown navigation; no nested reference chains.

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, specific, third-person description that names concrete techniques and models, includes an explicit "Use to..." trigger, and carves out a distinct niche. Voice and trigger guidance both meet the top anchor.

DimensionReasoningScore

Specificity

Enumerates many concrete items: "the seven canonical masking operators (substitution, shuffling, number/date variance, encryption, hashing, nulling, masking-out / character-scrambling) plus tokenisation, redaction, format-preserving encryption, and Microsoft Presidio's six built-in operators", matching the multi-action anchor.

3 / 3

Completeness

Explicitly answers both what (a pure-reference catalog of techniques/models) and when ("Use to pick the right masking operator per field type and risk level"), matching the explicit-trigger anchor.

3 / 3

Trigger Term Quality

Natural user-facing terms are well covered: "data-masking techniques", "de-identification", "masking operator", "field type and risk level"; the regulatory jargon (NIST/GDPR IDs) appears only in support, not as the trigger.

3 / 3

Distinctiveness Conflict Risk

Clear niche (per-field masking-operator selection) with distinct triggers and explicit adjacency to sibling skills (pii-masking-pipeline-builder, pii-categories-reference), unlikely to fire for unrelated skills.

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