BB serious-incident-reporting
Assess, report, and manage serious incidents involving high-risk AI systems under Article 73 EU AI Act. Covers incident qualification, deadline buckets (2/10/15 days), authority notification, deployer duties (Art. 26(5)), cross-regulation mapping (GDPR/NIS2/MDR), corrective measures, and DACH-specific routing. Use when asked to evaluate whether an AI incident is reportable, draft an Article 73 notification, identify the right authority, or build an AI incident response process.
Assess, report, and manage serious incidents involving high-risk AI systems under Article 73 EU AI Act.
As a process B 73/100 · Nearly there — weak spots: inputs and preconditions, consistency, progress reporting
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 0
✓ No critical or high findings
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6728 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 73/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (serious-incident-reporting) differs from the folder (serious-incident-reporting-eu-ai-act-art-73-werner-plutat)
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 6728 tokens
- 85Steps. 260 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 5 branches, has a failure section
- 100Running it twice. Mutating operations check current state
- low 13 top-level sections: this looks like several domains in one skill
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)
- +4No input/output examples
- +2Single-language instructions
- +3Description length 482: enough signal without eating the budget
- +4Structure: 55 headings
- +3Step-by-step instructions: 260 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: 78.