CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/pii-masking-pipeline-builder

Build-an-X workflow that produces a PII masking pipeline spec from a source-data inventory. Walks the author through (1) classifying each field against pii-categories-reference, (2) picking a masking operator from data-masking-techniques-reference, (3) deciding pseudonymisation (reversible, in GDPR scope) vs anonymisation (irreversible, out of scope), (4) ordering the pipeline (detect → operator → audit), and (5) emitting a deployable config for Presidio + Faker + Synthea wrappers. Output is a YAML pipeline spec plus a per-field rationale table. Use after classifying a dataset's PII risk; this is the workflow that translates classification into runnable masking config.

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

Low

Low-risk findings worth noting

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 workflow with strong sequencing and validation checkpoints. The main weakness is token redundancy from two large, structurally similar YAML blocks.

Suggestions

Collapse Step 6 and Step 7's YAML into a single annotated example, or make Step 7 reuse the Step 6 shape with only the differing fields shown, to cut redundancy.

In the Step 6 spec, mark which fields are illustrative vs. required so authors don't copy placeholder values verbatim.

DimensionReasoningScore

Conciseness

Mostly efficient and free of basic-concept padding, but the Step 6 recommended-shape YAML and the Step 7 worked-example YAML overlap heavily in structure, adding notable token redundancy.

2 / 3

Actionability

Provides copy-paste-ready YAML specs, a concrete per-field operator decision tree, and filled classification/operator tables with specific provider methods and vault references.

3 / 3

Workflow Clarity

Seven clearly sequenced steps with explicit checkpoints — the Step 4 pseudonymisation/anonymisation gate and the Step 5 audit hook (sample N rows, leak-detection audit) provide the validation feedback loop a batch masking pipeline requires.

3 / 3

Progressive Disclosure

Well-organized single-file overview with clear sections; composed skills are listed one level deep in a clearly signaled References section, and no bundle files are needed beyond the inline content.

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 description that covers concrete actions, natural trigger terms, an explicit use-when clause, and a distinct niche. Voice is third person throughout. No significant weaknesses.

DimensionReasoningScore

Specificity

Lists multiple concrete actions: classifying each field, picking a masking operator, deciding pseudonymisation vs anonymisation, ordering the pipeline, and emitting a deployable config for Presidio + Faker + Synthea wrappers.

3 / 3

Completeness

Explicitly answers both what (produces a YAML pipeline spec plus per-field rationale table) and when ("Use after classifying a dataset's PII risk"), with an explicit trigger clause.

3 / 3

Trigger Term Quality

Natural terms a user would say are present — "PII masking", "PII risk", "masking pipeline", "classifying a dataset's PII risk" — covering the common way this need is expressed.

3 / 3

Distinctiveness Conflict Risk

The PII-masking-pipeline niche with Presidio/Faker/Synthea and GDPR pseudonymisation gate is a clear, distinct trigger 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