SKILLEMALL.ai
GitHub ↗ RU Sign in

CC analyse-dpa-fournisseur-hugo-salard

Analyse systématique d'un Data Processing Agreement (DPA) au regard de l'article 28 RGPD, des lignes directrices EDPB 07/2020 et 02/2024, des CCT 2021 (décision d'exécution 2021/914), des recommandations EDPB 01/2020 (mesures supplémentaires post-Schrems II), et du Règlement (UE) 2024/1689 (Règlement IA). Produit un rapport structuré clause par clause (18 clauses : 13 obligatoires + 5 complémentaires) avec diagnostic 🟢/🟡/🔴, remédiations prêtes à insérer, analyse détaillée des transferts internationaux, vérification Règlement IA, et questions à poser au fournisseur. Triggers : "analyse de DPA", "audit DPA", "vérifier un DPA", "DPA fournisseur", "data processing agreement", "art. 28 RGPD", "sous-traitant RGPD", "négociation DPA", "review DPA", "conformité contrat sous-traitance".

lawve-ai/awesome-legal-skills Agent Skills author: lawve-ai 7 files body ≈ 7 491 tokens Open the sourcegithub.com↗ analyzed 71 min ago

Analyse systématique d'un Data Processing Agreement (DPA) au regard de l'article 28 RGPD, des lignes directrices EDPB 07/2020 et 02/2024, des CCT 2021…

As a process C 50/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches

AnalyzerTableauWriting and documentstype 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
87/100
safety, quality, tests
Safety 60%
99
Quality 40%
68
Run on models
none yet
Process rating
C
50/100
Has gaps
Inputs and preconditions w 11
0
Failures and branches w 10
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 SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • 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-security resources/clauses-remediation-types.md:54
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
    > « Le Sous-traitant met en œuvre les mesures techniques et organisationnelles suivantes, conformément à l'article 32 du RGPD : [liste à adapter selon le fournisseur]. Ces mesures comprennent au minim
    quoted

Files scanned: 7. 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 body-long SKILL.md body ≈ 7491 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 50/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 3 mutating operations with no state check
  • 40Consistency. Frontmatter name (analyse-dpa-fournisseur-hugo-salard) differs from the folder (analyse-rgpd-de-dpa-fournisseur-hugo-salard)
  • 60Result and completion. Output format stated, no completion criterion
  • 70Execution cost. Instruction body is 7491 tokens
  • 85Steps. 104 steps, 1 vague phrases
  • 100Tools and files. No external tools needed
  • low 11 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

  • +4Description does not say when NOT to use the skill (false activations)
  • -246 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 10 example trigger phrases
  • +3Description length 791: enough signal without eating the budget
  • +4Structure: 36 headings
  • +3Step-by-step instructions: 104 items
  • +3Output format is stated explicitly
  • +4Has examples (6 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.