What do I need to use ToS Decoder?

The ToS / privacy policy text; What the service is; What they're most worried about.

Is ToS Decoder free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

ToS Decoder

Q: How do I know the ToS Decoder output is good?

The skill verifies itself against its own quality checks: Findings are ranked by real-world impact, not by the document's own order; Every 🔴/🟡 finding quotes the actual clause text or section number; Every finding gets a "should I care?" verdict tied to the user's stated use; Standard boilerplate is labelled 🟢 explicitly — reassurance is part of the product.

🔵 Stable🕐 updated 2026-10-06⚖️ rules checked 2026-07-14Not yet expert-reviewed · review it 🔷 SkillSpec L3 pm-decoders

Decode a terms of service or privacy policy into what you're actually agreeing to, ranked by real-world impact. Use when someone asks 'what am I agreeing to', 'decode this privacy policy', 'is this ToS bad', or 'should I click accept'. Produces a ranked findings table with a 'should I care?' verdict per finding, covering data resale, arbitration and class-action waivers, unilateral changes, content licenses, and what deletion really means.

▶ Run it free — no key needed 📝 Grade your existing draft ⬇ Add to Claude (works in Duet) 📱 Use as an app View SKILL.md ↗ What changed

🗣 Say this to your agent

“Decode this privacy policy.”“Is this ToS bad?”“Should I click accept?”

What to give it

▸The ToS / privacy policy text — pasted in full or in sections. With excerpts, decode what's there and list which high-impact topics (arbitration, data sharing, licenses, deletion) are missing from what was shared.

▸What the service is — and how they'll use it (casually vs. for business, uploading original work, storing sensitive data).

▸What they're most worried about — , if anything specific.

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

✓Findings are ranked by real-world impact, not by the document's own order

✓Every 🔴/🟡 finding quotes the actual clause text or section number

✓Every finding gets a "should I care?" verdict tied to the user's stated use

✓Standard boilerplate is labelled 🟢 explicitly — reassurance is part of the product

✓High-impact topics absent from the provided text are listed as unreviewed, not assumed fine

✓The disclaimer line appears verbatim in the artifact

⚠️ What it refuses to do

Do not invent clauses that aren't in the document — decode only the provided text

Do not soften a red flag to seem balanced — "everyone does this" doesn't make it harmless

Do not present jurisdiction-dependent rules (privacy rights, arbitration limits) as universal

Do not perform outrage at ordinary boilerplate — crying wolf buries the real findings

Do not skip the verdict — a list of clauses without "should I care?" is just a shorter ToS

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y -p pm-claude-skills pm-claude-skills-mcp

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="tos-decoder"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

ToS Decoder is one of 1326 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog