Privacy policy diff summarizer
Skill sisodiabhumca/agent-skills/skills/privacy-policy-diff-summarizer
Production-Ready Agent Skills : product analytics, growth experiments, CRM, research synthesis, postmortems, data contracts, SaaS spend, compliance, architecture maps, and LLM eval and many more.
npx -y skills add sisodiabhumca/agent-skills --skill privacy-policy-diff-summarizerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Diff two privacy policy texts and produce a vendor-neutral summary of materially changed sections and risk flags.
SKILL.md
1.5 KB, as published. Nobody here has run it
When to invoke
- You have an updated privacy policy and need a quick summary of changes.
- You need to flag potentially material changes (data collected, sharing, retention, user rights).
- You want an evidence-backed diff that can be reviewed by legal/compliance.
Inputs needed
--oldpath to the previous policy text (UTF-8)--newpath to the updated policy text (UTF-8)
Workflow
- Normalize whitespace and split into paragraphs.
- Compute a paragraph-level diff.
- Extract:
- added and removed paragraphs
- most-changed paragraphs (by similarity)
- Apply heuristic risk flags (keyword rules), e.g.:
- new data categories: location, biometrics, health, children
- new sharing: advertisers, partners, affiliates
- retention expansion
- cross-border transfers
- Emit a JSON report with:
- change summary
- top changes (with old/new snippets)
- triggered risk flags
Output format
JSON to stdout:
material_change_score(0-100)added_paragraphs,removed_paragraphschanged_paragraph_pairsrisk_flags
Guardrails
- Vendor-neutral: operates on plain text and heuristic rules only.
- Not legal advice; always route to counsel for final review.
- Avoid overconfident conclusions: report evidence (snippets) for each flag.
Reference code
privacy_policy_diff_summarizer.py