BB gdpr-data-export-tool
Build, audit, and operate Article 15 (right of access) and Article 20 (data portability) data export pipelines for GDPR, plus the equivalent CCPA/CPRA "right to know" and UK DPA 2018 SARs. Covers subject identification and authentication tiers (passkey, magic link, in-app re-auth, ID verification), data inventory across Postgres / MySQL / Elasticsearch / Mongo / S3 / Stripe / Intercom / Segment / Mixpanel / Snowflake / SaaS sub-processors, JSON+CSV+HTML packaging with a human-readable index, secure delivery (signed URL with 7-day expiry, password-protected zip, in-app download), 30-day SLA tracking and extension protocol, shared-record handling (third-party data minimization), audit logging for the controller's accountability obligation under Article 5(2), and Article 12 fee/refusal policy. Triggers on "gdpr export", "data subject access request", "dsar", "right of access", "article 15", "article 20", "right to data portability", "ccpa data export", "cpra request", "subject access request", "personal data export", "data portability", "right to know", "privacy export pipeline".
As a process B 70/100 · Nearly there — weak spots: result and completion
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- Shorten the description to 1024 characters.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1093 chars, limit 1024 - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 6216 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 70/100
- 0Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 6216 tokens
- 100Steps. 71 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 tags): a typed call is more reliable
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 1093: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 14 example trigger phrases
- +4Structure: 22 headings
- +3Step-by-step instructions: 71 items
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 39.