CC audit-rgpd-site-internet
Audit de conformité RGPD complet d'un site internet. Réalise une observation systématique du site selon une checklist de 10 sections (mentions légales, hébergeur, formulaires, newsletter, politique de confidentialité, cookies et bandeau, mots de passe, trackers et mesure d'audience, sous-traitants et transferts hors UE, accessibilité du recueil des droits) plus une annexe 22 items reproduisant les exigences des articles 13 et 14 RGPD. Produit un rapport structuré avec niveau de conformité global, points bloquants (risque 3), points de vigilance (risque 2), recommandations prioritaires et notes techniques. Le skill est tool-agnostique : il fonctionne avec un outil de navigation automatique (Claude in Chrome, Cowork ou équivalent) ou en mode dégradé copier-coller. Triggers : "audit RGPD site", "audit site internet", "vérifie ce site", "scanne ce site", "audit conformité site", "audite la conformité de [URL]", "audit cookies site", "audit politique de confidentialité site".
Audit de conformité RGPD complet d'un site internet.
As a process C 50/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, consistency
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 9504 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
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 6 mutating operations with no state check
- 40Consistency. Frontmatter name (audit-rgpd-site-internet) differs from the folder (audit-conformite-rgpd-site-internet-hugo-salard)
- 40Execution cost. Instruction body is 9504 tokens: crowds the task out of the window
- 50Failures and branches. 0 branches, has a failure section
- 60Steps. 171 steps, 5 vague phrases
- 60Result and completion. Output format stated, no completion criterion
- 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)
- +3Description length 987: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +4Structure: 47 headings
- +3Step-by-step instructions: 171 items
- +3Output format is stated explicitly
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.