SKILLEMALL.ai
GitHub ↗ RU Sign in

AC eu-ai-act-classification

Classify AI systems under the EU AI Act (Regulation (EU) 2024/1689) and determine compliance obligations. Use when asked to assess AI risk level, check if an AI system is prohibited, determine high-risk status, identify GPAI model obligations, map provider/deployer responsibilities, or build an AI Act compliance roadmap. Covers the full classification decision tree (Prohibited → High-Risk → Limited → Minimal → GPAI), obligations by role (provider, deployer, importer, distributor), compliance timelines, and DACH-specific considerations (German works council, BaFin, BSI, BNetzA). Triggers on phrases like "classify this AI system", "is this high-risk under the AI Act", "AI Act risk assessment", "EU AI Act compliance", "prohibited AI practice", "GPAI obligations", "AI Act timeline".

lawve-ai/awesome-legal-skills Agent Skills author: lawve-ai 10 files body ≈ 3 205 tokens Open the sourcegithub.com↗ analyzed 69 min ago

Classify AI systems under the EU AI Act (Regulation (EU) 2024/1689) and determine compliance obligations.

As a process C 62/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, consistency

ProcedureSecurityWriting and documentsInfrastructuretype 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
A
98/100
safety, quality, tests
Safety 60%
99
Quality 40%
97
Run on models
none yet
Process rating
C
62/100
Has gaps
Inputs and preconditions w 11
0
Failures and branches w 10
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • 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/dach-specific.md:141
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (test fixture / example file)
      | Resilience against attacks | Adversarial robustness testing, penetration testing |
      fixture

    Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 62/100

    • 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. 9 mutating operations with no state check
    • 40Consistency. Frontmatter name (eu-ai-act-classification) differs from the folder (eu-ai-act-system-classifier-werner-plutat)
    • 60Result and completion. Output format stated, no completion criterion
    • 85Steps. 41 steps, 1 vague phrases
    • 100Tools and files. No external tools needed
    • 100When it triggers. States when to use and when not to
    • 100Execution cost. Instruction body is 3205 tokens

    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)
    • +2Single-language instructions
    • +5Description quotes 7 example trigger phrases
    • +3Description length 789: enough signal without eating the budget
    • +4Structure: 13 headings
    • +3Step-by-step instructions: 41 items
    • +3Output format is stated explicitly
    • +4Has examples (0 code blocks)
    • +4Reference files are cited in the instructions (7 of 7)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 97.