SKILLEMALL.ai
GitHub ↗ RU Sign in

BC eu-ai-act-classification-oliver-schmidt-prietz

Determines whether a technology qualifies as an AI system under Art. 3(1) of the EU AI Act and classifies its risk tier (prohibited, high-risk, GPAI with systemic risk, limited risk, minimal risk). This skill should be used when the user asks to "classify an AI system under the AI Act", "determine the AI Act risk tier", "check if something is an AI system", "assess prohibited practices", "check high-risk classification", "determine Art. 6 exception applicability", or mentions "KI-Verordnung", "Risikoklassifizierung", Art. 5, Annex III, or GPAI systemic risk.

lawve-ai/awesome-legal-skills Agent Skills author: lawve-ai 16 files body ≈ 5 984 tokens Open the sourcegithub.com↗ analyzed 2 h ago

Determines whether a technology qualifies as an AI system under Art.

As a process C 50/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches

ProcedureData and analyticstype 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
B
93/100
safety, quality, tests
Safety 60%
99
Quality 40%
84
Run on models
none yet
Process rating
C
50/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 1

✓ No critical or high findings

Medium and low: 1
  • low Risky intent intent-offensive-security references/gpai-systemic-risk.md:115
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | Model evaluation | Art. 55(1)(a) | Perform model evaluation, including adversarial testing (red teaming) |

Files scanned: 16. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5984 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 50/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 11 mutating operations with no state check
  • 40Consistency. Frontmatter name (eu-ai-act-classification-oliver-schmidt-prietz) differs from the folder (eu-ai-act-system-classifier-oliver-schmidt-prietz)
  • 70When it triggers. States when to use, but not when not to
  • 70Execution cost. Instruction body is 5984 tokens
  • 100Tools and files. No external tools needed
  • 100Steps. 38 steps

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)
  • +3Output format is not stated: the model decides each time
  • +2Single-language instructions
  • +5Description quotes 8 example trigger phrases
  • +3Description length 564: enough signal without eating the budget
  • +4Structure: 11 headings
  • +3Step-by-step instructions: 38 items
  • +4Has examples (8 code blocks)
  • +4Reference files are cited in the instructions (12 of 12)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.