BC gdpr-audit
GDPR Compliance Audit — General Data Protection Regulation (EU) 2016/679 (GDPR). Free to install; scoring runs on the CQDev cloud compliance engine (free API Key, 100 free calls). Covers 25 core items. Use when: the user asks to run the gdpr-audit skill, or requests a GDPR 合规深度审计 / General Data Protection Regulation (EU) 2016/679 (GDPR). Trigger: gdpr-audit, GDPR 合规审计, 欧盟隐私审计, GDPR audit, 数据保护审计 Pricing: Free skill; cloud scoring uses points (Check 1 / Audit 10 per run) from compliancehub.cn Anonymous trial: no Key? The skill auto-runs up to 5 real cloud-scored trials (7-day window) with a local anon_id, then points you to one-click registration carrying your anon_id. ⚠️ Cloud scoring sends your answers to compliancehub.cn. `--non-interactive` preview lists the items WITHOUT sending answers; it attempts to fetch the latest rule set from the cloud rule library and falls back to a built-in snapshot when offline. 🔐 Account provisioning is OPT-IN via the web: register for a free API Key at https://compliancehub.cn/account.html?skill=gdpr-audit, then supply it to this skill via the COMPLIANCEHUB_API_KEY environment variable or ~/.config/compliancehub/gdpr-audit.key. This skill never collects your email/password. 💡 Free preview: --non-interactive lists the 25 items without a Key
GDPR Compliance Audit — General Data Protection Regulation (EU) 2016/679 (GDPR).
As a process C 52/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Shorten the description to 1024 characters.
- 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: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1298 chars, limit 1024 - note
frontmatter-keyunknown frontmatter key "permissions"
Process rating: all ten parameters 52/100
- 0Result and completion. Does not say what the result is
- 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
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 13 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1027 tokens
- 100Running it twice. No mutating operations
- 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1297: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 12 headings
- +3Step-by-step instructions: 13 items
- +4Has examples (3 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.