Plain-language summary of a policy or contract (not legal advice)
Explains a contract, terms of service or internal policy in plain language: key obligations, money and dates, termination, risks to check and questions to ask. A reading aid, not legal advice; it says when to get a lawyer.
Prompt in Operations by AISkillHub Library
What it does
Contracts and policies are written to be precise, not readable. This prompt produces a plain-language reading guide to a document you paste in, so you know what it says, what it asks of you, and what to ask about before signing or relying on it.
**Important: this is not legal advice.** The output is a summary to help you read and discuss a document. It can miss things, and it cannot tell you how a law applies in your jurisdiction or situation. For anything with significant money, liability, employment, property, regulatory or personal consequences, have a qualified lawyer review the document. The prompt repeats this note at the top of every output.
**Use it when** you need to understand a vendor agreement, SaaS terms, an NDA, a lease summary, an employee handbook policy, or a privacy policy before a conversation with the other party, your manager, or your lawyer.
**What you get** - A one-paragraph overview: what kind of document it is, between whom, and its main purpose. - Key terms in plain language: obligations for each party, money, dates and durations, renewal and termination, liability and indemnity, data and confidentiality, and dispute resolution, each with the clause number it comes from. - Things to check: clauses that are one-sided, unusual for the document type, vague, or that interact with each other. - Questions to ask the other party or a lawyer. - Terms the document uses but does not define, or defines elsewhere.
**What it will not do** - It will not tell you whether to sign, whether a clause is enforceable, or what a court would decide. - It will not summarise clauses that are not in the text you paste. If the document refers to other documents (an order form, a data processing addendum), it lists them as not reviewed. - It will not soften or omit unfavourable terms.
How to use it
## How to use
1. Open `prompts/plain-language-policy-summary.md` and copy everything below the title line. 2. Replace each `{{variable}}` with your own content. Paste long material (notes, transcripts, tables) directly in place of the variable; keep the surrounding tags so the model can tell inputs apart. 3. Start a new chat in ChatGPT, Claude or Gemini and paste the filled prompt as your first message. 4. Read the output against the quality checks at the end of the prompt before you use or send it.
## Variables
- `{{document_text}}`: the full text of the contract or policy. Include clause numbers if it has them. - `{{my_role}}`: your side, e.g. `the customer`, `the employee`, `the contractor`. - `{{my_concerns}}`: what you care about most, e.g. `cancelling early`, `who owns the work`, `data handling`. Optional. - `{{jurisdiction}}`: where you and the other party are based, if known. Used only to remind you what to ask a lawyer, not to give legal conclusions.
If you do not have a value for an optional variable, write `none` rather than deleting it, so the prompt still reads correctly.
## Reusing it
To reuse it often, save the prompt (with the variables left in) as the instructions of a Claude Project, a custom GPT or a Gemini Gem, then paste only the inputs in each new chat.
## Tips
- Remove personal identifiers and confidential commercial details your organisation does not allow in chat tools before pasting.
Files
Save each file at the path shown, relative to your project root.