CtrlK
BlogDocsLog inGet started
Tessl Logo

803-regulations-gdpr

Use when reviewing, designing, or modifying Java enterprise systems that process personal data and need GDPR-aware engineering controls. This should trigger for requests such as Review a Java service for GDPR privacy controls; Design data-subject rights workflows; Add retention, deletion, pseudonymization, or privacy-safe logging; Assess data transfer, DPIA, breach evidence, or processor/controller boundary concerns before production release. Part of Plinth Toolkit

66

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

77%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.

A well-structured instruction skill: a gated, validated six-step workflow with explicit evidence rules, redaction handling, and clean one-level-deep bundle organization that all checks out on disk. The primary weakness is redundancy — the not-legal-advice and sanitized-evidence caveats and the when-to-use list are each repeated multiple times, inflating token cost without adding guidance.

Suggestions

State the "not legal advice" disclaimer once (e.g., keep the Constraints entry, remove the two repetitions in the opening paragraphs) — it currently appears three times in ~100 lines.

Consolidate the repeated sanitized-evidence rule: keep the SANITIZED EVIDENCE ONLY constraint and remove its verbatim restatements in workflow steps 2 and 4, leaving only a short cross-reference.

Trim or merge the 'When to use this skill' section, which duplicates the frontmatter description's trigger list nearly verbatim; a one-line pointer would preserve discoverability at lower token cost.

DimensionReasoningScore

Conciseness

The body is mostly efficient but carries noticeable repetition: the "not legal advice" disclaimer appears at least three times ("This Skill is not legal advice", "The response produced by this Skill does not represent legal advice", "Do not provide legal advice or replace review by..."); the sanitized-evidence rule is restated three times (SANITIZED EVIDENCE ONLY constraint, workflow step 2, step 4); and the "When to use this skill" section repeats the frontmatter description almost verbatim. This matches the 'mostly efficient but some unnecessary explanation or could be tightened' anchor rather than 4, where only minor trimming would be needed.

3 / 5

Actionability

For an instruction-only skill the guidance is concrete and executable: exact files to read in a specified order, an enumerated checklist of artifacts to inspect (DTOs, controllers, repositories, SQL/NoSQL schemas, migrations, cache keys, search-index mappings), explicit output rules ("Record only an enumerated answer with a repository path and line reference... otherwise mark it `Unknown`", "Do not proceed... until all 22 questions"), and a concrete redaction token `[REDACTED_SECRET]`. It misses a 5 because some specifics live only in the referenced files (e.g., answer format, report fields) and the control recommendations in step 5 remain category-level rather than worked examples in the body.

4 / 5

Workflow Clarity

The six-step workflow is clearly sequenced with explicit validation gates and feedback loops: "Do not start implementation review until the chapters summary... are understood", "Do not proceed to implementation review or the report until all 22 questions have an approved evidence reference or an `Unknown` marker", and the error-recovery loop "If raw free text is the only available source, stop and request a maintainer-prepared sanitized fact record". Step 4's gap-check between questionnaire answers and approved evidence adds a checkpoint, matching the 5 anchor (explicit validation steps, feedback loops, checklist-driven process); this is a read-only review, so the destructive-operation cap does not apply.

5 / 5

Progressive Disclosure

The SKILL.md body is an overview that clearly signals four one-level-deep bundle files — two references and two assets — all verified to exist on disk, announced up front ("GDPR chapters summary reference", "Java engineering examples reference", "Questionnaire asset", "Report template asset"), integrated into the workflow with their purpose stated, and restated in a closing Reference section. No nesting or buried references, matching the 5 anchor of a clear overview with well-signaled one-level-deep references.

5 / 5

Total

17

/

20

Passed

Description

83%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.

A strong description that clearly states the domain, lists multiple concrete capabilities, and provides an explicit 'Use when' clause with enumerated trigger phrases. Its main weaknesses are a few missing natural synonyms (erasure, right to be forgotten) and unmentioned core activities like questionnaire evidence collection and report generation.

DimensionReasoningScore

Specificity

The description names the domain ("Java enterprise systems that process personal data") and lists several concrete actions ("Review a Java service for GDPR privacy controls", "Design data-subject rights workflows", "Add retention, deletion, pseudonymization, or privacy-safe logging", "Assess data transfer, DPIA, breach evidence"), matching the 'several specific actions; minor gaps' anchor. It falls short of the 5 anchor because coverage is not fully comprehensive — report generation and questionnaire-driven evidence collection, core to the skill, are not mentioned, and 'modifying Java enterprise systems' is somewhat generic.

4 / 5

Completeness

It explicitly answers both: what ("reviewing, designing, or modifying Java enterprise systems that process personal data" with "GDPR-aware engineering controls") and when ("Use when..." plus "This should trigger for requests such as..." followed by four concrete trigger phrases). This matches the 5 anchor — clear what and when with explicit trigger phrases — rather than the 4 anchor where the 'when' is present but less explicit, since the trigger list is enumerated.

5 / 5

Trigger Term Quality

Good keyword coverage with natural terms a user would say: 'GDPR', 'privacy controls', 'data-subject rights', 'retention', 'deletion', 'pseudonymization', 'DPIA', 'breach', 'processor/controller', 'personal data'. It misses some common synonyms such as 'right to be forgotten', 'erasure', 'privacy compliance', or specific Java stack names (Spring Boot, Quarkus) that appear in the body, so it does not reach the comprehensive-with-synonyms 5 anchor.

4 / 5

Distinctiveness Conflict Risk

The niche is fairly distinct — Java enterprise + GDPR privacy engineering — with domain-specific triggers ('DPIA', 'data-subject rights', 'processor/controller boundary') unlikely to fire for unrelated skills. However, "Part of Plinth Toolkit" implies sibling regulation skills, and generic privacy/security review requests (e.g., a general 'check this service for privacy issues') could overlap with adjacent security or regulation skills, leaving minor overlap risk rather than the clear-niche-minimal-conflict 5 anchor.

4 / 5

Total

17

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 6 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository
jabrena/plinth
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.