Judge Task Lifecycle logo

Judge Task Lifecycle

Organization
sno-ai
judge-task-lifecycle

Judge how a memory changes active-task state and whether it refers to an existing task. Use for mem-claw task-lifecycle model calls.

Overview

Publishersno-ai
Repositorysno-station
Skill namejudge-task-lifecycle
Stars
622
Forks
363
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Judge Task Lifecycle 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/tree/main/packages/memory/skills/judge-task-lifecycle
  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.git /tmp/sno-station
mkdir -p .claude/skills
cp -r /tmp/sno-station/packages/memory/skills/judge-task-lifecycle .claude/skills/judge-task-lifecycle
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Judge Task Lifecycle 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 Judge Task Lifecycle 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 Judge Task Lifecycle 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.

Judge Task Lifecycle

Judge task meaning. Do not decide from exact wording alone.

Active Task State

Apply the To-do Boundary section supplied from extract-atomic-memory before these state rules.

Decide in this order and stop at the first step that applies.

  1. Does the candidate report OR INSTRUCT that an existing active task is done, finished, handled, cancelled, or dropped? If yes, the answer is complete or remove on THAT task. Never open_or_refine, and never none. A report ("I finished X", "X is done") and an instruction ("mark X complete", "tick X off", "close X", "remove X from my list") both land here. An instruction to change a task's state IS the state change; do not treat it as a request you decline to act on. A candidate that speaks about an active task's ending is never a new task, however it is worded, and restating the task's name inside such a sentence is naming the task to close, not opening one.
  2. Otherwise, if the candidate describes work still to be done, use open_or_refine.
  3. Otherwise use none.
  • Use open_or_refine only for a current task that remains active.
  • Use complete only when the candidate says an active task was achieved.
  • Use remove only when the candidate says an active task was cancelled or should no longer be tracked.
  • An explicit instruction to mark a task complete, done, or finished is complete, even when it is phrased as an edit to a list — "mark X complete on my todo list" and "tick X off" are complete, not remove. Taking a finished task off a list is what completing it looks like; the words that decide are whether the work was done. Reserve remove for a task abandoned, cancelled, called off, no longer needed, or added by mistake — cases where the work will NOT happen.
  • Use none when the candidate does not change active-task state.
  • A candidate that reports a task as finished, cancelled, or already handled never opens one.
  • If that task is active, complete or remove it. If it is not active, make no task change.
  • Match tasks by meaning, not exact wording. Refine an existing task instead of opening a duplicate.

Existing Task Relation

  • Use same_instance when the assertion refers to one listed active task, including different wording with the same meaning.
  • Use distinct_instance when the assertion is a different active task.
  • Use none when the assertion does not describe an active-task relation.
  • Use uncertain when the evidence does not settle the relation.

Frequently asked questions

What does the Judge Task Lifecycle AI skill do?

Judge how a memory changes active-task state and whether it refers to an existing task. Use for mem-claw task-lifecycle model calls.

Why use Judge Task Lifecycle on TypingMind?

Because you install it once and use it with any model. Judge Task Lifecycle 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 Judge Task Lifecycle in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/sno-ai/sno-station/tree/main/packages/memory/skills/judge-task-lifecycle. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Judge Task Lifecycle?

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 Judge Task Lifecycle?

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

Is the Judge Task Lifecycle 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 👇