Os Say Simple logo

Os Say Simple

CommunityPopular
kharmanskyi
os-say-simple

ALWAYS invoke this skill when the user asks for simpler or shorter about something said or written - "say it simply", "what does this mean", "I don't understand your answer", "too long", "wait, what?", "bro" - in any language, about any text: your own answer, a report, a review comment, an error. "I don't understand what to DO" is os-step-by-step; this skill restates text. It restates for a reader who does not read code: leads with the point, keeps every number, warning and caveat - no facts added, no bad news dropped. A number returns exactly that many points, most important first.

Overview

Publisherkharmanskyi
Repositoryopen-steps
Skill nameos-say-simple
Stars
1.2K
Forks
106
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

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

Installation

Install the Os Say Simple 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/kharmanskyi/open-steps/tree/main/skills/os-say-simple
  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/kharmanskyi/open-steps.git /tmp/open-steps
mkdir -p .claude/skills
cp -r /tmp/open-steps/skills/os-say-simple .claude/skills/os-say-simple
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Os Say Simple 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 Os Say Simple 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 Os Say Simple 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.

os-say-simple

A text exists and the user cannot use it. This skill rewrites it into words they can act on - the pack's rescue skill: the others fire at moments of work, this one whenever any text, including your own, needs saying again properly. It changes only the words. Never the facts.

Language

Write in the language the user speaks in this session. Detect it from the conversation. Keep code, file names and identifiers in English.

When to use

  • The user asks for simpler or shorter, in any phrasing: "say it simply", "in plain words", "what does this mean", "I don't understand", "too long", "wait, what?", "bro".
  • The user pastes text and asks what it says.
  • The user gives the skill a number - they want exactly that many points.

Not this skill:

  • "Is this true?" is verification - os-check-work; a restatement stays exactly as true as its source.
  • "What do I do?" right after an answer that asked the user to act is a walkthrough - os-step-by-step. Asked about the road ahead, it is os-whats-next.

What text to restate

  1. Whatever the user points at: pasted text, a named file, a report in the reports folder. Read it if it is a file.
  2. Nothing pointed at: your own last substantial answer. A bare "wait, what?" always means the thing you just said.

The controlled-language rules

Drawn from the ideas behind ASD-STE100, the Simplified Technical English standard from aerospace manuals. This pack follows the ideas; it does not claim conformance to the standard.

  • One sentence, one idea. In instructions: one action per sentence.
  • Active voice. Name who does what - "the check refused the deploy", never "the deploy was refused".
  • Short sentences. A sentence that needs a breath in the middle is two.
  • One word, one meaning - and one meaning, one word. Never rotate synonyms for the same thing; the reader will assume the difference is meaningful.
  • Present tense unless the time itself is the fact.
  • Lists over dense paragraphs - but a list is not permission to drop the connections between items.

These rules shape every restatement - and when a term has to stay (rule 6), the sentences around it obey them with the term kept exact.

With a number

3 means exactly three points. Most important first, one sentence each.

  • Fewer real points than asked for: give the real ones and say the source holds no more. Never pad.
  • A warning or a risk is always one of the points. It outranks good news.

Hard rules

  1. Add nothing, drop no bad news. Every warning, risk, number and caveat in the source survives the rewrite. A summary that loses the ⚠ line is a lie by omission. Security, data loss and anything hard to undo are spelled out in full, never shortened.
  2. Numbers stay exact. No rounding money, counts or dates. A ticket or pull request number that names an action stays.
  3. As true as the original, no truer. The source's claims stay claims: "the report says the tests pass", not "the tests pass" - unless this session verified it. Offer os-check-work when the user needs true.
  4. Unclear stays unclear. Where the source is ambiguous, say "the original does not say" - never resolve ambiguity by guessing.
  5. Lead with the point. No preamble, no "here is a simpler version" - the first line is already the answer.
  6. A term with no plain equivalent gets described by what the user would see or do, with the term once in brackets - same move as the whole pack.
  7. Code and commands are exact strings. Never paraphrase what someone would type or run; explain around it.
  8. Aim for half the length or less - except where rule 1 or an exact-N request forbids it.

Known gotchas

  • "I don't understand" about your own answer is feedback, not an attack. Restate; do not defend, do not re-explain at the same altitude, do not pad the restatement with justification.
  • Restating is not editing. If while restating you notice your original was wrong, that is a correction - say so plainly. Never fix it silently inside the "simpler" version.
  • Mid-task "wait, what?" - restate, then continue the task. Do not lose the thread the question interrupted.
  • A text that is already plain gets one line saying so and nothing else. Manufacturing a different version to look useful is padding.
  • No number given, long source - the one-screen rule from the rest of the pack applies: about ten lines, fifteen at the ceiling.

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 Os Say Simple AI skill do?

ALWAYS invoke this skill when the user asks for simpler or shorter about something said or written - "say it simply", "what does this mean", "I don't understand your answer", "too long", "wait, what?", "bro" - in any language, about any text: your own answer, a report, a review comment, an error. "I don't understand what to DO" is os-step-by-step; this skill restates text. It restates for a reader who does not read code: leads with the point, keeps every number, warning and caveat - no facts added, no bad news dropped. A number returns exactly that many points, most important first.

Why use Os Say Simple on TypingMind?

Because you install it once and use it with any model. Os Say Simple 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 Os Say Simple in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kharmanskyi/open-steps/tree/main/skills/os-say-simple. 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 Os Say Simple?

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 Os Say Simple?

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

Is the Os Say Simple AI skill free?

Yes. It is published on GitHub by kharmanskyi 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 👇