Manage Current Focus logo

Manage Current Focus

Community
magickaichen
manage-current-focus

Prioritize or update one declared current-focus view in a governed vault. Use to accept, complete, block, defer, or reorder commitments, or reconcile sourced status with current attention.

Overview

Publishermagickaichen
Repositoryknowledge-loom
Skill namemanage-current-focus
Stars
53
Forks
1
Bundled files
5
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.

  • 5 bundled files

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

  • Open source

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

Installation

Install the Manage Current Focus 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/magickaichen/knowledge-loom/tree/main/skills/manage-current-focus
  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/magickaichen/knowledge-loom.git /tmp/knowledge-loom
mkdir -p .claude/skills
cp -r /tmp/knowledge-loom/skills/manage-current-focus .claude/skills/manage-current-focus
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Manage Current Focus 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 Manage Current Focus 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 Manage Current Focus 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.

Manage Current Focus

Requires Node.js 20+ and local file/command access.

Maintain one operational attention view without turning it into a full backlog or silently adding parallel work.

Load authority and resolve one view

Resolve this SKILL.md to its canonical path, following symlinks. Set <skill-root> to the directory containing that canonical file. Read <skill-root>/references/protocol.md completely. From the active project directory, inspect node "<skill-root>/scripts/knowledge-loom.mjs" resolve --help, then run resolve, appending a selector only when one was supplied. Treat its returned canonical root as the only selected vault. Read its contract and instruction roots, then follow Prepare inbound access before loading the selected focus view and linked current notes. Preserve an explicit read-only request. After integration, reload governing files before reasoning from the updated view. Stop vault work on any resolution error.

  • Use an explicitly named view when provided.
  • Use the only configured view when exactly one exists.
  • Ask when multiple views are plausible.
  • Never merge personal and shared views automatically.

If the vault declares no focus view, report that focus management is not configured and propose initialization as separate follow-up work.

Select review or update

  • Review: analyze the configured view and return a recommendation without editing it.
  • Update: evaluate the protocol's current-state write authorization. Continue only when the policy and request or sourced material change authorize an edit.

This branch is resolved when the operation is explicitly read-only or an authorized material state change has been identified.

Establish current evidence

Treat the focus file as an attention view, not the source of truth. Verify unstable completion, blocking, ownership, deadline, or priority claims in declared authoritative sources before changing the view.

Distinguish:

  • discussion from a commitment;
  • possible work from accepted work;
  • active execution from Next;
  • dependency waiting from voluntary deferral;
  • durable project status from the compact focus view.

Apply the configured selection lens

Use the vault-specific policy text for selection criteria. Do not import another vault's career, health, household, or organizational lens.

For every candidate, require:

  • why it deserves attention now;
  • an executable next action;
  • owner or dependency when relevant;
  • a concrete done condition;
  • an authoritative source or durable linked note;
  • a restart point when interruption is likely.

Respect max_top and max_active. Keep exactly one Start here when required. A new top item must name the item moved to Next, Waiting, Later, or Not now. Never create a hidden fourth priority.

Apply an authorized update

Before editing, follow the protocol's pre-write Git and preservation steps. Keep project history and design detail in linked notes rather than expanding the focus file. Apply the smallest edit that records the accepted state change and explicit displacement.

Validate and finish

After an edit, run:

bash
node "<skill-root>/scripts/knowledge-loom.mjs" audit <vault-path>

Confirm WIP limits, unique Start here, source links, explicit displacement, and the selected subject/view. Then follow the protocol's commit, sync, backup, and failure behavior. For a review, report the recommended Start here and displacement without claiming a write. For an update, report the new Start here, the displaced or completed item, every affected path, and the exact lifecycle state. Completion requires all configured focus invariants to hold and every required lifecycle state to be known.

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 Manage Current Focus AI skill do?

Prioritize or update one declared current-focus view in a governed vault. Use to accept, complete, block, defer, or reorder commitments, or reconcile sourced status with current attention.

Why use Manage Current Focus on TypingMind?

Because you install it once and use it with any model. Manage Current Focus 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 Manage Current Focus in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/magickaichen/knowledge-loom/tree/main/skills/manage-current-focus. 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 Manage Current Focus?

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 Manage Current Focus?

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

Is the Manage Current Focus AI skill free?

Yes. It is published on GitHub by magickaichen 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 👇