AC log-pii-redactor
Detect and redact personally identifiable information (PII) in application logs to comply with GDPR, CCPA, HIPAA, and PCI DSS. Knows the realistic 2026 PII surface — emails, phone numbers, SSNs, credit cards, IPv4/IPv6, JWT tokens, API keys, cloud secret patterns, addresses, names leaked via headers and stack traces. Picks the right strategy per field (irreversible mask vs deterministic tokenize vs salted hash vs drop) and ships a regex pack, a pre-prod scanner, and integration recipes for Fluent Bit, Logstash, Vector, and the OpenTelemetry Collector. Maps every redaction to the relevant compliance clause (GDPR Art 5/32, HIPAA Safe Harbor §164.514(b)(2), PCI DSS 3.4/3.5). Use when asked to scrub logs, build a redaction pipeline, audit a log stream for PII, design a tokenization scheme, prep for a SOC 2 or HIPAA audit, or stop sensitive data flowing into Datadog/Splunk/ELK/S3.
As a process C 57/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, running it twice
How to improve
- 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
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 57/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 19 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 4250 tokens
- 100Steps. 45 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 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
- +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 888: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 25 headings
- +3Step-by-step instructions: 45 items
- +3Output format is stated explicitly
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.