801-regulations-eu-ai-act

Use when reviewing, designing, or modifying Java enterprise systems that use AI, LLMs, AI agents, RAG, tool calling, workflow automation, or model-based decision support and need EU AI Act regulatory awareness. This should trigger for requests such as Review a Java AI system for EU AI Act controls; Design governance for an AI agent with enterprise tools; Add human oversight and auditability to LLM workflows; Assess RAG or model-driven decision support before production release. Part of Plinth Toolkit

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/801-regulations-eu-ai-act/SKILL.md

Quality

Content

71%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 regulatory review skill with a clear sequenced workflow, explicit validation/escalation checkpoints, and excellent progressive disclosure via verified bundle files. Its main weakness is redundancy — references and trigger phrases are repeated across sections — which costs token efficiency.

Suggestions

Remove the trailing 'Reference' section that re-lists the two reference files already linked in the intro, or conversely drop the intro links and keep only the consolidated Reference section.

Trim the 'When to use this skill' list since those trigger phrases already appear verbatim in the frontmatter description, replacing it with a one-line pointer if needed.

Add an explicit fix-and-retry feedback loop in the workflow (e.g., re-run the questionnaire step after a gap is found) so recovery, not just escalation, is specified.

Dimension	Reasoning	Score
Conciseness	Mostly substantive and domain-specific rather than padding, but it duplicates content: the reference files are linked both in the intro and again in a trailing 'Reference' section, and 'When to use this skill' repeats the trigger phrases already in the description, so it could be tightened.	3 / 5
Actionability	Gives concrete, executable guidance for an instruction-only skill — named files to read in order, a questionnaire checklist, redaction rules, classification categories, and a report template — with only minor gaps since the real review detail lives in the bundled assets rather than inline.	4 / 5
Workflow Clarity	A clearly sequenced 5-step workflow with explicit checkpoints ('Stop and escalate immediately if prohibited-practice signals are identified', 'Check for gaps between recorded answers and implementation evidence'), though the recovery path is escalate/stop rather than a fix-and-retry loop.	4 / 5
Progressive Disclosure	SKILL.md acts as a clear overview with well-signaled, one-level-deep links to real bundled files (two references plus questionnaire and report-template assets, all verified present), keeping detail appropriately split out of the main body.	5 / 5
	Total	16 / 20 Passed

Description

87%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, well-targeted description that clearly states both capability and trigger conditions in third person with concrete example requests. Minor tightening of the top-level action verbs and a few additional synonyms would push specificity and trigger quality to full marks.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('reviewing, designing, or modifying Java enterprise systems') plus specific trigger tasks ('Review a Java AI system', 'Design governance for an AI agent', 'Add human oversight', 'Assess RAG'), though the top-level verbs remain somewhat broad, so it stops just short of fully comprehensive coverage.	4 / 5
Completeness	Explicitly answers both what the skill does and when to use it via a 'Use when...' clause plus a 'This should trigger for requests such as...' list with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural keyword coverage ('Java enterprise systems', 'AI agents', 'RAG', 'tool calling', 'EU AI Act', 'human oversight and auditability') with realistic user phrasings; a few synonyms or common variations are missing, keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Targets a clear, narrow niche (EU AI Act regulatory awareness for Java enterprise AI systems/agents) with distinct triggers, giving minimal overlap risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

87%

Warnings & errors only

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

Criteria	Description	Result
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
Path: skills/801-regulations-eu-ai-act/SKILL.md
Commit: f6dfc6f

Reviewed: about 2 hours ago

Table of Contents

Discovery Implementation Validation

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.