SKILLEMALL.ai
GitHub ↗ RU Sign in

AC eu-ai-act-obligations-oliver-schmidt-prietz

Maps the full set of legal obligations for the EU AI Act based on role + risk tier, producing an actionable compliance matrix with RACI assignments and implementation priorities. This skill should be used when the user asks to "map AI Act obligations", "check what we need to do under the AI Act", "create a compliance checklist", "check deployer obligations", "assess provider duties", or mentions Art. 26, Art. 16-17, AI literacy Art. 4, DPIA, fundamental rights assessment, or "Pflichtenkatalog" under the AI Act.

lawve-ai/awesome-legal-skills Agent Skills author: lawve-ai 20 files body ≈ 4 389 tokens Open the sourcegithub.com↗ analyzed 76 min ago

Maps the full set of legal obligations for the EU AI Act based on role + risk tier, producing an actionable compliance matrix with RACI assignments and…

As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency

ProcedureSecuritytype 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
96/100
safety, quality, tests
Safety 60%
98
Quality 40%
94
Run on models
none yet
Process rating
C
55/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

How to improve

    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 · 2

    ✓ No critical or high findings

    Medium and low: 2
    • low Risky intent intent-offensive-security references/gpai-obligations.md:95
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      **Obligation:** Perform model evaluation in accordance with standardised protocols and tools reflecting the state of the art, including conducting and documenting adversarial testing (red teaming) of
    • low Risky intent intent-offensive-security references/gpai-obligations.md:99
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Adversarial testing / red teaming (safety, misuse, bias, security)

    Files scanned: 20. 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 55/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 30Running it twice. 15 mutating operations with no state check
    • 40Consistency. Frontmatter name (eu-ai-act-obligations-oliver-schmidt-prietz) differs from the folder (eu-ai-act-obligations-mapper-oliver-schmidt-prietz)
    • 60Tools and files. Uses tools (web) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 70Execution cost. Instruction body is 4389 tokens
    • 100Steps. 40 steps
    • 100Failures and branches. 2 branches, has a failure section
    • 100Progress reporting. Reports progress

    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 6 example trigger phrases
    • +3Description length 516: enough signal without eating the budget
    • +4Structure: 12 headings
    • +3Step-by-step instructions: 40 items
    • +4Has examples (6 code blocks)
    • +4Reference files are cited in the instructions (16 of 16)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 94.