AB gpai-code-of-practice
Assess compliance with the EU General-Purpose AI (GPAI) Code of Practice under the AI Act (Regulation (EU) 2024/1689). Use when asked to determine GPAI model provider obligations, assess Code of Practice compliance, evaluate transparency or copyright requirements for GPAI models, check systemic risk obligations, build a GPAI compliance roadmap, or prepare for AI Office requests. Covers all three Code chapters (Transparency, Copyright, Safety & Security), the 12 commitments and their measures, systemic risk classification (Article 51), provider obligations (Articles 53 and 55), open-source exemptions, enforcement timeline, Commission/AI Office supervision, and DACH-specific overlays such as BSI cybersecurity and works council implications. Triggers on phrases like "GPAI compliance", "Code of Practice assessment", "GPAI model obligations", "systemic risk evaluation", "AI Act transparency requirements", "GPAI copyright policy", "general-purpose AI compliance".
Assess compliance with the EU General-Purpose AI (GPAI) Code of Practice under the AI Act (Regulation (EU) 2024/1689).
As a process B 75/100 · Nearly there — weak spots: inputs and preconditions, consistency, progress reporting
How to improve
- 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-securityreferences/systemic-risk-framework.md:198Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Penetration testing and security audits
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
edit-residuethe text marks something as outdated (lines 130): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 75/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (gpai-code-of-practice) differs from the folder (gpai-code-of-practice-compliance-werner-plutat)
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4131 tokens
- 85Steps. 39 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Result and completion. Output format and completion criterion are stated
- 100Failures and branches. 1 branches, has a failure section
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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 971: 120–800 characters recommended
- +4No input/output examples
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +4Structure: 17 headings
- +3Step-by-step instructions: 39 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (6 of 6)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.