CtrlK
BlogDocsLog inGet started
Tessl Logo

807-regulations-eu-digital-services-act

Use when reviewing, designing, or modifying Java enterprise systems that may support intermediary services, hosting services, online platforms, marketplaces, content moderation, recommender systems, advertising delivery, complaint workflows, transparency reporting, or systemic-risk evidence under the EU Digital Services Act. This should trigger for requests such as Review a Java online platform for DSA controls; Design notice-and-action or appeal workflows; Add recommender, ad transparency, moderation, audit, researcher access, or privacy-safe observability evidence; Assess online-platform transparency controls before production release. Part of Plinth Toolkit

53

Quality

59%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/807-regulations-eu-digital-services-act/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

31%Scale 1-5

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

This skill is a regulatory compliance review guide that suffers severely from verbosity and repetition—the same enumerated lists of concerns appear nearly identically in the scope, constraints, workflow, and review sections. Despite being titled for 'Java Online Platform Engineering,' it contains zero code examples, no concrete implementation patterns, and no executable guidance, deferring all specifics to reference files. The workflow structure is reasonable but lacks validation checkpoints critical for compliance-related reviews.

Suggestions

Eliminate the extensive repetition: the lists of governance concerns (intermediary classification, VLOP/VLOSE status, etc.) appear 4-5 times verbatim—consolidate into a single authoritative list and reference it.

Add concrete Java code examples inline: show at minimum one Spring Boot controller for notice intake, one content decision audit log entity/DTO, and one moderation workflow state machine snippet to justify the 'Java' focus.

Add explicit validation gates in the workflow: e.g., 'STOP: If intermediary classification is unclear after Step 2, do not proceed to Step 3—escalate to legal/compliance first' with a concrete checklist.

Cut the introductory paragraphs (first 4 paragraphs) to 2-3 sentences maximum—Claude does not need to be told what a skill is or that it's not legal advice multiple times.

DimensionReasoningScore

Conciseness

Extremely verbose and repetitive. The same lists of concerns (intermediary classification, VLOP/VLOSE status, illegal-content determinations, advertising or recommender interpretation, audit or researcher access duties, systemic-risk conclusions, regulatory interpretation) are repeated nearly verbatim across multiple sections. Concepts are restated 4-5 times. The skill explains at length what it is and isn't rather than getting to actionable content. Claude already understands regulatory review patterns and doesn't need this level of repetition.

1 / 5

Actionability

Despite being a Java-focused skill, there is zero executable code, no concrete commands, no specific configuration examples, and no copy-paste ready snippets. The guidance remains at a high-level checklist level ('review Java code, configuration, controllers, DTOs...') without showing what a content decision audit log looks like, what a Spring Boot controller for notice intake should contain, or any concrete implementation pattern. The engineering examples are deferred entirely to a reference file that wasn't provided.

2 / 5

Workflow Clarity

The 5-step workflow is sequenced and logical (read references → classify scope → review implementation → recommend controls → generate report), but validation checkpoints are absent. There is no feedback loop for when classification is uncertain, no explicit 'stop and escalate' gate between steps, and no verification that controls actually work. For a skill involving compliance-critical operations, the lack of validation steps is a significant gap.

3 / 5

Progressive Disclosure

The skill appropriately references external files for detailed content (chapters summary, engineering examples, report template) and keeps the main file as an overview. References are clearly signaled with full paths. However, since no bundle files were provided, we cannot verify the referenced files exist or contain appropriate content. The main file itself is still too long due to repetition, which undermines the disclosure structure.

4 / 5

Total

10

/

20

Passed

Description

87%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.

This is a strong description that clearly defines a narrow niche at the intersection of Java enterprise development and EU Digital Services Act compliance. It excels at completeness with explicit 'Use when' guidance and concrete trigger examples, and its specificity to both a technology and regulatory domain minimizes conflict risk. The main weakness is that the long enumeration of sub-domains (intermediary services, hosting services, online platforms, marketplaces, etc.) makes it somewhat dense and harder to parse quickly.

DimensionReasoningScore

Specificity

The description lists several specific actions: reviewing, designing, modifying Java enterprise systems, designing notice-and-action/appeal workflows, adding recommender/ad transparency/moderation/audit features, and assessing transparency controls. It covers many concrete actions but reads more like a domain enumeration than a crisp capability list.

4 / 5

Completeness

Explicitly answers both 'what' (reviewing/designing/modifying Java enterprise systems for DSA compliance across multiple domains) and 'when' with a clear 'Use when...' clause and concrete trigger phrases like 'Review a Java online platform for DSA controls' and 'Design notice-and-action or appeal workflows'.

5 / 5

Trigger Term Quality

Includes many natural trigger terms users would say: 'DSA', 'Digital Services Act', 'content moderation', 'notice-and-action', 'recommender systems', 'transparency reporting', 'complaint workflows', 'Java online platform'. Missing some variations like 'DSA compliance', 'EU regulation', or 'platform regulation' but overall good keyword coverage.

4 / 5

Distinctiveness Conflict Risk

Highly distinctive niche combining Java enterprise systems with EU Digital Services Act compliance. The intersection of a specific technology stack (Java) with a specific regulatory framework (DSA) and enumerated compliance domains makes this very unlikely to conflict with other skills.

5 / 5

Total

18

/

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

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.