Simplify Member Rules logo

Simplify Member Rules

Community
backtrue
simplify-member-rules

Organize existing points, membership, subscription, and digital-benefit rules into explanations customers can understand. Check each scenario for unchanged benefits before and after rewriting, and design comprehension tests that do not reveal answers. Use when rules are excessive, names are confusing, or exceptions are hard to find; take the existing system as input and deliver rule mappings, customer explanations, test questions, and an answer sheet

Overview

Publisherbacktrue
Repositorythinkwithblack-skill
Skill namesimplify-member-rules
Stars
249
Forks
24
Bundled files
4
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by backtrue on GitHub. Read the source before you install it.

Installation

Install the Simplify Member Rules AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/backtrue/thinkwithblack-skill/tree/main/en/extensions/simplify-member-rules
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/backtrue/thinkwithblack-skill.git /tmp/thinkwithblack-skill
mkdir -p .claude/skills
cp -r /tmp/thinkwithblack-skill/en/extensions/simplify-member-rules .claude/skills/simplify-member-rules
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Simplify Member Rules in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Simplify Member Rules on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Simplify Member Rules is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Simplifying Member Rules and Checking Understanding

For ordinary chat, upload packs/simplify-member-rules.md, which includes the shared rules, this method, and required references

Organize the existing system into a verifiable rule table, then rewrite the customer explanation. Preserve eligibility, benefit value, deadlines, fees, and exceptions so customers can determine what they can do. See Sources and adopted scope for method sources

Required inputs

Upload existing membership terms, customer explanations, and the scope to organize, with the applicable version, date, and product type. Include customer-service misunderstanding records or interview responses if available, removing unnecessary personal information such as names and contact details

General teaching questions may use examples with explicit assumptions; actual rewriting must follow the supplied system. When the same condition conflicts across documents, list original locations and points to confirm while organizing the remaining confirmed material first

1. Organize the original rules

Number every rule, retain its source location, and complete the table below. Mark fields absent from the source as “Not provided,” distinguishing a nonexistent benefit from missing information

Rule ID / sourceTrigger actionApplicable products and eligibilityWhat is receivedWhen usableScope and expiryStacking and exclusionsRefund / cancellation / expiry handling

Separate qualification progress from spendable points; distinguish physical goods, paid subscriptions, permanently purchased digital content, and gifted benefits. Record fees, minimum spend, redemption caps, partial refunds, and negative-point handling according to the original terms

2. Simplify the expression

Find synonymous items with different names, repeated explanations, different multipliers for the same action, hidden exceptions, and conditions requiring calculations across pages. For each, choose to standardize names, merge identical explanations, move information to where it is used, or retain differences, recording the before-and-after mapping

Different points and product benefits may be listed separately on one page. Preserve scope and conditions when merging text; retain separate rules when balances, redemption ratios, or refund mechanisms differ. Treat requests to remove exceptions, raise thresholds, shorten expiry periods, or merge balances as system-change proposals separate from wording simplification

3. Verify benefits using the same scenarios

List applicable scenarios such as purchases, recurring charges, partial refunds, skipping one period, subscription cancellation, and expiry of paid digital benefits. Test only scenarios actually included in the system; for permanently purchased content, check access after cancellation of other services

Scenario and conditionsOriginal rule IDsBenefits / fees under original wordingBenefits / fees after rewritingSame or differentPoints to confirm

Check boundaries for thresholds, expiry, availability timing, and redemption caps, such as below, exactly at, and above a threshold. When amounts are provided, retain formulas and rounding methods

Results for the same scenario must match before and after rewriting. If they differ, correct the wording; if the original terms contradict themselves, leave the location pending confirmation rather than choosing the interpretation that favors the brand or customer

When points are reclaimed, separately list the original balance, points due for reclamation, actual deduction, outstanding reclamation, and available balance, calculated under the original terms. The overview, full rules, and answer table within the same customer explanation must agree. List only missing items that affect this question's judgment; directly retain conditions already provided clearly. Count equivalent scenarios using actual table rows and separately mark rows whose outcomes remain unconfirmed

4. Write the customer explanation

Start with a short overview explaining “what to do next, what you get, and when and where you can use it,” followed by the complete rule table. Place deadlines, fees, exclusions, and refund / cancellation effects next to the relevant benefit so customers can decide at that moment

Every statement must trace to a rule ID. Keep offers, exceptions, benefits, and customer-service promises absent from the source pending confirmation

5. Prepare comprehension tests

Design open questions using the same scenarios and ask customers to find answers themselves and explain their reasoning, such as “After returning one item in this order, which points can you still use?” or “After canceling the subscription, what content can you access next month?” Do not reveal correct answers in the questions

Deliver questions and answers separately. The moderator's answer sheet lists original rules, expected judgment, acceptable expressions, and points to confirm; do not show answers before customers respond. Mark questions with conflicting rules as pending confirmation and fix them before including them in accuracy calculations

Record actual verbatim answers, correctness, the answer-finding process, and locations of misunderstandings. When comparing two wordings, keep benefits and scenarios identical and record which version each participant saw and in what order. Label AI reasoning as simulation; the user supplies human responses after testing. Report correct counts and denominators for each question from actual valid responses, separating preference ratings from understanding results

Delivery

Deliver the original rule table, rewrite comparison and equivalent scenarios, customer explanation, participant questions, and moderator answer sheet. If human responses already exist, also organize actual misunderstandings and revision locations; after completion, wait for the user's next data batch

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Simplify Member Rules AI skill do?

Organize existing points, membership, subscription, and digital-benefit rules into explanations customers can understand. Check each scenario for unchanged benefits before and after rewriting, and design comprehension tests that do not reveal answers. Use when rules are excessive, names are confusing, or exceptions are hard to find; take the existing system as input and deliver rule mappings, customer explanations, test questions, and an answer sheet

Why use Simplify Member Rules on TypingMind?

Because you install it once and use it with any model. Simplify Member Rules is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Simplify Member Rules in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/backtrue/thinkwithblack-skill/tree/main/en/extensions/simplify-member-rules. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Simplify Member Rules?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Simplify Member Rules?

As many as you like. As long as a model supports skills, you can use Simplify Member Rules with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Simplify Member Rules AI skill free?

Yes. It is published on GitHub by backtrue under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇