gosprinto/compliance-skills/pii-detector

PII Developer Skill — USA Focus

Automatic PII checks during development. Fires on both what the user asks for AND what Claude is about to generate — not just on keyword matching.

Core Principle

Check before generating. Never produce code and then suggest fixes. The sequence is always: detect intent → run relevant checks → generate correct code.

If there is ANY ambiguity — check it. False positives are cheap. Missed PII in production is a breach, a fine, or both.

When suggesting fixes, use the language, framework, and idioms of the code being reviewed. Never suggest a fix in a different language than the one being written. If the codebase is Python, fix in Python. If Rails, fix in Ruby. If Go, fix in Go. Claude infers the language from context — no need to specify.

Step 1 — Detect the Mode

Read the user's request AND what Claude is about to produce. Choose the mode first — this determines everything else.

Planning / Review mode — user is discussing, designing, reviewing, or asking Claude to read/check existing code. No new code being generated. → Load: modes/planning.md → Enrich Claude's natural response with PII notes. No standalone report.

Signals: "review", "read", "look at", "check this", "share thoughts", "how should I build", "I want to build X", "help me design", "feedback on", "thoughts on", reading or analyzing an existing file without generating new code.

Generation mode — Claude is about to write new code from scratch. → Load relevant layer(s) from the table below. Check first, generate second.

Signals: "build it", "create", "generate", "write", "implement", "scaffold", "make", "add this feature" — active code production.

Repo scan mode — user explicitly requests a full audit. → Load: modes/repo-scan.md + all layers.

Signals: "scan my repo", "full audit", "PII report", "check all my models", "audit my codebase".

When in doubt between planning/review and generation: default to planning/review. Enriching a response is always safer than running a check that wasn't needed.

Step 2 — Generation Mode: Map to Layers

Only applies when generating new code. Multiple layers can apply simultaneously.

When multiple layers apply (e.g. building an auth API endpoint): load all relevant layers and merge the checks.

Always load patterns/fields.md when a model or schema is involved. Always load rules/non-negotiables.md when any PII field is detected.

Step 3 — Regulations (Always Apply All, Never Ask)

Step 4 — Run Checks, Then Generate (Inline Mode Only)

1. Load the relevant layer file(s) from Step 1
2. Run all checks defined in those layers against what's about to be built
3. Output findings in the standard format (see below)
4. Generate corrected code immediately — with all fixes already applied

Never generate broken code first. Never suggest fixes as an afterthought. The check and the corrected output happen in a single pass.

Output Format

Inline (any single-task coding):

⚡ PII Check — [what's being built]
 
🔴 Fix now:
  [specific issue] → [exact fix]
 
🟡 Fix soon:
  [specific issue] → [exact fix]
 
🟢 Consider:
  [suggestion]
 
Regulations: [only ones actually triggered]

Then generate the corrected code immediately after.

Repo scan: structured report with file + line references. Load modes/repo-scan.md.

Rules for all output:

• Reference actual field names, file names, and line numbers — never be generic
• "Encrypt ssn with AES-256, store as BYTEA" not "encrypt sensitive fields"
• Skip empty sections — don't pad with N/A categories
• List only regulations actually triggered by findings