SKILLEMALL.ai
GitHub ↗ RU Sign in

CD dpa-art-28-oliver-schmidt-prietz

Review, draft, or redline a Data Processing Agreement (DPA / Auftragsverarbeitungsvertrag / AVV) under Art. 28 GDPR, or prepare a Joint Controller Arrangement under Art. 26 GDPR. Supports bilingual output (DE/EN), both controller- and processor-side perspectives, and two review depths — quick (Art. 28(3)(a)–(h) coverage) and negotiation-grade (clause-by-clause risk scoring).

lawve-ai/awesome-legal-skills Agent Skills author: lawve-ai 25 files body ≈ 3 199 tokens Open the sourcegithub.com↗ analyzed 88 min ago

Review, draft, or redline a Data Processing Agreement (DPA / Auftragsverarbeitungsvertrag / AVV) under Art.

As a process D 48/100 · Unfinished process — References files that are not bundled: references/2021-915-commission-text-{en,de}.md, templates/dpa-{commercial,strict,hybrid}-{en,de}.md, templates/jca-{en,de}.md

AnalyzerLegaltype 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
C
84/100
safety, quality, tests
Safety 60%
98
Quality 40%
64
Run on models
none yet
Process rating
D
48/100
Unfinished process
References files that are not bundled: references/2021-915-commission-text-{en,de}.md, templates/dpa-{commercial,strict,hybrid}-{en,de}.md, templates/jca-{en,de}.md
Tools and files w 18
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The text references files that are not there: add them or drop the references.
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 templates/dpa-commercial-en.md:292
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - **Penetration testing**: Annual penetration testing by qualified independent third parties.
  • low Risky intent intent-offensive-security templates/dpa-strict-en.md:204
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - **Penetration testing**: annually by qualified independent third parties.

Files scanned: 25. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: references/2021-915-commission-text-{en,de}.md
  • warning missing-ref reference to a missing file: templates/dpa-{commercial,strict,hybrid}-{en,de}.md
  • warning missing-ref reference to a missing file: templates/jca-{en,de}.md
  • warning missing-ref reference to a missing file: templates/jca-{lang}.md

Process rating: all ten parameters 48/100

Will not run. References files that are not bundled: references/2021-915-commission-text-{en,de}.md, templates/dpa-{commercial,strict,hybrid}-{en,de}.md, templates/jca-{en,de}.md
  • 0Tools and files. 4 referenced file(s) missing: references/2021-915-commission-text-{en,de}.md, templates/dpa-{commercial,strict,hybrid}-{en,de}.md, templates/jca-{en,de}.md
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 6 mutating operations with no state check
  • 40Consistency. Frontmatter name (dpa-art-28-oliver-schmidt-prietz) differs from the folder (data-processing-agreement-art-28-gdpr-oliver-schmidt-prietz)
  • 50When it triggers. No condition that starts the skill
  • 60Result and completion. Output format stated, no completion criterion
  • 85Steps. 83 steps, 1 vague phrases
  • 100Failures and branches. 3 branches, has a failure section
  • 100Execution cost. Instruction body is 3199 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 10 top-level sections: this looks like several domains in one skill
  • medium 8 test cases, all positive: not one "should refuse" or "should ask first"
  • 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)
  • +4No input/output examples
  • +2Single-language instructions
  • +3Description length 377: enough signal without eating the budget
  • +4Structure: 16 headings
  • +3Step-by-step instructions: 83 items
  • +3Output format is stated explicitly
  • +4Reference files are cited in the instructions (6 of 8)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 64.