Away Brief logo

Away Brief

Organization
sno-ai
away-brief

Give the owner one page when they come back from sleep, a meeting or a long run: what got done, what is stuck, what waits for their answer, and what it cost in quota. Use when the owner asks what happened while they were away, wants a status page, or when you finish a long stretch of work and must report it.

Overview

Publishersno-ai
Repositorysno-station-skills
Skill nameaway-brief
Stars
604
Forks
415
Bundled files
3
LicenseApache-2.0
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.

  • 3 bundled files

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

  • Open source

    Published by sno-ai on GitHub. Read the source before you install it.

Installation

Install the Away Brief 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/sno-ai/sno-station-skills/tree/main/skills/H-reporting-and-visibility/away-brief/skill
  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/sno-ai/sno-station-skills.git /tmp/sno-station-skills
mkdir -p .claude/skills
cp -r /tmp/sno-station-skills/skills/H-reporting-and-visibility/away-brief/skill .claude/skills/away-brief
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Away Brief 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 Away Brief 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 Away Brief 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.

away-brief

sno away-brief run reads what already exists and prints one page of at most 60 lines. It changes nothing except its own list of quota readings, and Reach, which may note that it has seen the cards that the inbox read listed (it never moves, accepts or finishes them).

## Done       new commits, charters delivered since the cutoff (with how many checks are proven),
              progress records that finished or are still going
## Stuck      charters not finished (with the numbers of the checks not yet proven), progress records
              with tasks left that nobody has touched for two hours
## Needs you  Reach cards of type question or decision waiting in the inbox
## Spend      your heartbeats, and each vendor's quota now with the change since the last reading

A source it cannot read prints not read: <what> -> <why> and the rest of the page still prints. Each section has its own share of the 60 lines; items beyond it are replaced by an and N more not shown line, so a long Done list never pushes out what waits for the owner or the quota.

Prerequisites: bash 4+, GNU coreutils, git and jq. It uses sno deliver-proof (the deliver skill) to count proofs, sno reach inbox, sno heartbeat --list and sno subscription-quota-check when they are installed.

Use

  1. Run sno away-brief run --since 12h in the project's git folder. Change --since to the time the owner left (8h, 2d, or a date). Add --repo DIR for each other repository and --charters DIR for folders that hold charters or progress records outside those repositories. Add --as <your seat> (or set SNO_REACH_ADDR) so the inbox is read.
  2. Read the page and tell the owner the three things that matter most, in plain words: what is finished, what is blocked and why, and what needs their answer. Keep the page's evidence paths so they can open the file. Do not add work that is not on the page.
  3. Quota: a reading shows usage now, not spend. When the owner is about to leave, run sno away-brief mark once; it stores a reading, so the next page can show what was spent since. Without an earlier reading the page says so instead of guessing.

What the page can and cannot say

  • "Done" is only what is in git, in a delivered charter, or in a finished progress record. Work that was never committed or recorded does not appear.
  • "Stuck" is a charter whose recorded proofs are missing or failing, or a progress record (written by sno handoff-checkpoint) with tasks left and no update for two hours. An agent that is busy but does not write records looks quiet.
  • "Needs you" is only the seat you name. Questions sent to other seats are not shown.
  • The change in quota compares two readings of the same window; if the window reset in between, the page says so instead of showing a negative number.

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 Away Brief AI skill do?

Give the owner one page when they come back from sleep, a meeting or a long run: what got done, what is stuck, what waits for their answer, and what it cost in quota. Use when the owner asks what happened while they were away, wants a status page, or when you finish a long stretch of work and must report it.

Why use Away Brief on TypingMind?

Because you install it once and use it with any model. Away Brief 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 Away Brief in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/sno-ai/sno-station-skills/tree/main/skills/H-reporting-and-visibility/away-brief/skill. 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 Away Brief?

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 Away Brief?

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

Is the Away Brief AI skill free?

Yes. It is published on GitHub by sno-ai under the Apache-2.0 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 👇