CC eu-ai-act-transparency-assessor-oliver-schmidt-prietz
Assesses which of the Art. 50(1)-(5) transparency obligations of the EU AI Act apply to a given AI system's provider or deployer, grounded in the final Code of Practice on Transparency of AI-Generated Content (June 2026) and the Commission's draft Art. 50 Guidelines. Covers AI-chatbot disclosure, deepfake and synthetic-content marking/watermarking, emotion-recognition and biometric-categorisation notices, the machine-readable marking duty, the obviousness exceptions, and the implementation timeline. Outputs a formal mini-report plus a per-obligation compliance checklist with gap flags. For breadth-first tier triage use the EU AI Act System Classifier; for raw Art. 50 text and Q&A use the EU AI Act Knowledge Base; for the full role x tier matrix use the EU AI Act Obligations Mapper.
Assesses which of the Art.
As a process C 57/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 1
-
high Concealment
en-hide-from-userreferences/obviousness-and-exceptions.md:125Instruction to hide actions from the user- **Do not tell the user marketing categorically qualifies** for the exception — but equally, don't assert
Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
edit-residuethe text marks something as outdated (lines 18, 21, 165, 232, 234, 237): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 16 mutating operations with no state check
- 60Failures and branches. 2 branches
- 70Execution cost. Instruction body is 4757 tokens
- 100Tools and files. No external tools needed
- 100Steps. 49 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 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
- +5Description has no quoted example phrases that should trigger the skill
- +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
- +3Description length 792: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 49 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (8 of 9)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.