SKILLEMALL.ai
GitHub ↗ RU Sign in

DD ai-act-knowledge

EU AI Act Knowledge Engine — authoritative regulatory Q&A grounded in 70 official EU source documents (including the 2026 Commission draft guidelines on Art. 6 high-risk classification — general principles, Annex I, Annex III). Answers any question about the AI Act with article-level citations from the full regulation text, Commission guidelines, EDPB/EDPS opinions, codes of practice, harmonised standards, FRIA guides, incident templates, and sector-specific guidance. This skill should be used when the user asks about the "EU AI Act", "AI Act regulation", "Regulation 2024/1689", "KI-Verordnung", asks to "explain an AI Act article", "what does Article X say", "AI Act requirements", "AI Act penalties", "AI Act timeline", "GPAI obligations", "high-risk AI", "prohibited AI practices", "AI Act and GDPR", "fundamental rights impact assessment", "AI Act standards", "AI Act national implementation", "AI literacy", "serious incident reporting", "Digital Omnibus", "AI regulatory sandbox", or any question about EU artificial intelligence regulation. Also triggers on German terms: "KI-Gesetz", "KI-Verordnung", "Hochrisiko-KI", "KI-Kompetenz", "Grundrechte-Folgenabschaetzung", "GPAI-Verhaltenskodex". For assessment workflows that produce a classification decision rather than a knowledge answer, offer to run a structured risk-tier classification in-session.

lawve-ai/awesome-legal-skills Agent Skills author: lawve-ai 80 files body ≈ 3 215 tokens Open the sourcegithub.com↗ analyzed 89 min ago

EU AI Act Knowledge Engine — authoritative regulatory Q&A grounded in 70 official EU source documents (including the 2026 Commission draft guidelines on Art.

As a process D 37/100 · Unfinished process — References files that are not bundled: templates/draft-guidance-art73-high-risk.md, templates/serious-incident-template-gpai.md

ProcedureWriting and documentsInfrastructureResearchtype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
D
75/100
safety, quality, tests
Safety 60%
93
Quality 40%
49
Run on models
none yet
Process rating
D
37/100
Unfinished process
References files that are not bundled: templates/draft-guidance-art73-high-risk.md, templates/serious-incident-template-gpai.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. Shorten the description to 1024 characters.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 7

✓ No critical or high findings

Medium and low: 7
  • low Risky intent intent-offensive-security references/codes-of-practice/gpai-code-detailed.md:263
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - End-user feedback collection, dedicated reporting channels, bug bounty programs, community-driven evaluations.
  • low Risky intent intent-offensive-security references/codes-of-practice/gpai-code-detailed.md:774
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Run bug bounty programs for public-facing endpoints where appropriate.
  • low Risky intent intent-offensive-security references/codes-of-practice/gpai-code-final.md:1141
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    3. **Validation of network software integrity,** through (a) competitive bug bounty programs to encourage public participation in security testing of public-facing endpoints as appropriate to mitigate
  • low Risky intent intent-offensive-security references/core/regulation-title-XI-XIII-final.md:542
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    2. Where applicable, a detailed description of the measures put in place for the purpose of conducting internal and/or external adversarial testing (e.g. red teaming), model adaptations, including ali
  • low Risky intent intent-offensive-security references/cybersecurity/enisa-advisory-opinion.md:170
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - How to conduct vulnerability assessments or red teaming exercises to identify weaknesses in AI systems and infrastructure, consistent with "shift left" approaches.
  • low Risky intent intent-offensive-security references/cybersecurity/enisa-advisory-opinion.md:368
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    1. Review existing EU policy on usage of AI systems applied to cybersecurity and propose amendments, if needed, to leverage AI in cybersecurity (e.g., allow the use in blue teaming and red teaming).
  • low Risky intent intent-offensive-security references/cybersecurity/enisa-advisory-opinion.md:370
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    3. Organise workshops/hackathons for developing/designing AI tools to support cybersecurity tasks, both in the blue and red team's sides.

Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1366 chars, limit 1024
  • warning missing-ref reference to a missing file: templates/draft-guidance-art73-high-risk.md
  • warning missing-ref reference to a missing file: templates/serious-incident-template-gpai.md
  • note edit-residue the text marks something as outdated (lines 119): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 37/100

Will not run. References files that are not bundled: templates/draft-guidance-art73-high-risk.md, templates/serious-incident-template-gpai.md
  • 0Tools and files. 2 referenced file(s) missing: templates/draft-guidance-art73-high-risk.md, templates/serious-incident-template-gpai.md
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 4 mutating operations with no state check
  • 40Consistency. Frontmatter name (ai-act-knowledge) differs from the folder (eu-ai-act-knowledge-base-oliver-schmidt-prietz)
  • 55Failures and branches. 1 branches
  • 70When it triggers. States when to use, but not when not to
  • 85Steps. 20 steps, 2 vague phrases
  • 100Execution cost. Instruction body is 3215 tokens
  • low No test case covers injection arriving through data

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 1365: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • +2Single-language instructions
  • +5Description quotes 26 example trigger phrases
  • +4Structure: 13 headings
  • +3Step-by-step instructions: 20 items
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 49.