Goals logo

Goals

Community
tashfeenahmed
goals

Create, list, update, and complete goals, milestones, and tasks with hierarchical tracking

Overview

Publishertashfeenahmed
Repositoryscallopbot
Skill namegoals
Stars
56
Forks
9
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

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

Installation

Install the Goals 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/tashfeenahmed/scallopbot/tree/main/src/skills/bundled/goals
  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/tashfeenahmed/scallopbot.git /tmp/scallopbot
mkdir -p .claude/skills
cp -r /tmp/scallopbot/src/skills/bundled/goals .claude/skills/goals
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Goals 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 Goals 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 Goals 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.

Goals Skill

Manage hierarchical goals with a simple kanban workflow (backlog -> active -> completed).

Structure

Goals are organized hierarchically:

  • Goals - High-level objectives (e.g., "Learn Spanish")
  • Milestones - Major checkpoints within a goal (e.g., "Complete Duolingo basics")
  • Tasks - Specific action items within a milestone (e.g., "Finish lesson 5")

When to Use

Use the goals skill for:

  • Creating goals: "I want to learn Python this year"
  • Breaking down goals: Add milestones and tasks to goals
  • Tracking progress: View current status and progress percentages
  • Status updates: Mark items as active or completed
  • Proactive check-ins: Set up periodic reminders for goal progress

Input Format

The skill accepts JSON arguments via the SKILL_ARGS environment variable:

Create a goal

json
{
  "action": "create",
  "type": "goal",
  "title": "Learn Spanish",
  "checkin": "weekly",
  "due": "2024-12-31"
}

Create a milestone

json
{
  "action": "create",
  "type": "milestone",
  "title": "Complete Duolingo basics",
  "parent_id": "goal_abc123"
}

Create a task

json
{
  "action": "create",
  "type": "task",
  "title": "Finish lessons 1-5",
  "parent_id": "milestone_def456"
}

List goals

json
{
  "action": "list",
  "type": "goal",
  "status": "active"
}

list defaults to naturally active items. Age, due date, lifecycle, and genuine topic relevance determine activation. Pass the user's topic/name as query so a relevant older goal can return naturally; unrelated old goals remain quiet. scope: "all" is only the complete durable inventory and does not affect storage.

Show goal hierarchy

json
{
  "action": "show",
  "id": "goal_abc123"
}

Complete an item

json
{
  "action": "complete",
  "id": "task_xyz789"
}

Activate an item

json
{
  "action": "activate",
  "id": "goal_abc123"
}

Reopen a completed item

json
{
  "action": "reopen",
  "id": "task_xyz789"
}

Update an item

json
{
  "action": "update",
  "id": "goal_abc123",
  "title": "Master Spanish",
  "due": "2025-06-30"
}

Delete an item

json
{
  "action": "delete",
  "id": "goal_abc123"
}

Parameters

ParameterTypeRequiredDescription
actionstringYesOne of: create, list, show, activate, complete, reopen, update, delete
typestringFor create/listItem type: goal, milestone, or task
titlestringFor createTitle/description of the item
parent_idstringFor milestone/taskParent ID (goal for milestone, milestone for task)
idstringFor show/activate/complete/reopen/update/deleteItem ID
statusstringFor list/updateFilter or set: backlog, active, completed
duestringOptionalDue date (parsed naturally)
checkinstringFor goalsCheck-in frequency: daily, weekly, biweekly, monthly, none
tagsarrayOptionalTags for organization

Output Format

json
{
  "success": true,
  "output": "Goal created: Learn Spanish (ID: abc123)",
  "exitCode": 0
}

Examples

Set up a learning goal

  1. Create the main goal:
json
{"action": "create", "type": "goal", "title": "Learn Spanish", "checkin": "weekly"}
  1. Add milestones:
json
{"action": "create", "type": "milestone", "title": "Complete Duolingo basics", "parent_id": "abc123"}
  1. Add tasks:
json
{"action": "create", "type": "task", "title": "Finish lesson 5", "parent_id": "def456"}
  1. Activate the goal:
json
{"action": "activate", "id": "abc123"}
  1. Complete tasks as you progress:
json
{"action": "complete", "id": "task789"}
  1. View progress:
json
{"action": "show", "id": "abc123"}

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 Goals AI skill do?

Create, list, update, and complete goals, milestones, and tasks with hierarchical tracking

Why use Goals on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/tashfeenahmed/scallopbot/tree/main/src/skills/bundled/goals. 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 Goals?

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 Goals?

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

Is the Goals AI skill free?

Yes. It is published on GitHub by tashfeenahmed 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 👇