Shared Context logo

Shared Context

Organization
zenobi-us
shared-context

Routes shared engineering context work to the right procedure — report or change where context is stored, pull an external source (Confluence page, Jira issue, web page, PDF, screenshot) into it, and publish the write so other agents see it. Use when the user says shared context, eng-context, alignment root, "save this page", "pull this in", "where does my context live", or when a write must land outside the repository clone.

Overview

Publisherzenobi-us
Repositorydotfiles
Skill nameshared-context
Stars
67
Forks
6
Bundled files
10
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.

  • 10 bundled files

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

  • Open source

    Published by zenobi-us on GitHub. Read the source before you install it.

Installation

Install the Shared Context 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.
  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/zenobi-us/dotfiles.git /tmp/dotfiles
mkdir -p .claude/skills
cp -r /tmp/dotfiles/files/devtools/agent/bundles/agent-core/skills/shared-context .claude/skills/shared-context
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Shared Context 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 Shared Context 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 Shared Context 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.

Shared Context

Origin-keyed engineering context. Alignment files and ingested source material live outside any single repository clone, keyed by the repository's git origin.

Step 0: resolve the root. Always.

bash
cd "<repository being worked on>" && "<skillroot>/scripts/shared-context/cli.ts"

You MUST run every cli.ts call with the working directory inside the repository you are working on. The CLI reads the origin from the working directory. Run it from the skill directory and it resolves a different repository and reports the wrong root.

<skillroot> is the directory holding the SKILL.md you are reading right now. Use that copy, not another one on disk — an installed plugin cache can be older than the source. The path to the CLI repeats the directory name: <skillroot>/scripts/shared-context/cli.ts. That is correct. Do not trim a segment.

Run the file directly, as shown. Its shebang starts bun through mise and installs the CLI's own dependencies on first run. You MUST NOT prefix the call with Bun's runner — that skips the shebang, and the call then fails in an installed copy that has no dependencies.

report is the default. cli.ts and cli.ts report do the same thing. Output:

storage: shared | repository
root: <ALIGNMENT_ROOT — use this for every write>
shared root: <equals root in shared mode, equals the repository root otherwise>
shared candidate: <where shared storage would live; printed only in repository mode>
origin: <git origin>
slug: <origin-derived directory name>

Router

You want toRead
See or change where context is storedreferences/storage.md
Know where a file goes and what it is namedreferences/layout.md
Pull an external source into contextreferences/ingest.md
Fetch one specific source typereferences/sources.md
Make a write visible to other agentsreferences/publishing.md

Rules that override convenience

  1. You MUST NOT run init or migrate from an implied request. Both mutate storage. Run either only when the user names that operation.
  2. You MUST write under the resolved root. You MUST NOT mix the repository root and the shared root in one task.
  3. You MUST use cli.ts anchor to get a target directory. Do not build the path by hand. Add --dry-run when you are planning and must not create anything.
  4. You MUST run cli.ts index <dir> after you add or remove a file in a source directory.
  5. If storage is shared, you MUST commit and push the write in the same turn. Read references/publishing.md first — the branch check there can stop the push.
  6. You MUST NOT overwrite a file that holds hand-written work. See the authored-content guard in references/layout.md.
  7. You MUST stop and report a non-zero exit status from cli.ts. Do not retry silently. This rule covers cli.ts only. An ordinary shell probe such as ls exits non-zero for an absent path, which is an answer, not a failure.

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 Shared Context AI skill do?

Routes shared engineering context work to the right procedure — report or change where context is stored, pull an external source (Confluence page, Jira issue, web page, PDF, screenshot) into it, and publish the write so other agents see it. Use when the user says shared context, eng-context, alignment root, "save this page", "pull this in", "where does my context live", or when a write must land outside the repository clone.

Why use Shared Context on TypingMind?

Because you install it once and use it with any model. Shared Context 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 Shared Context in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zenobi-us/dotfiles/tree/master/files/devtools/agent/bundles/agent-core/skills/shared-context. 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 Shared Context?

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 Shared Context?

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

Is the Shared Context AI skill free?

Yes. It is published on GitHub by zenobi-us 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 👇