How do I install the Tasks skill?

Run npx skillmds@latest add grandamenium/tasks in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Tasks safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Tasks?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Tasks free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

grandamenium (@grandamenium) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Tasks by grandamenium — Agent Skill

Name: Tasks
Author: grandamenium

Tasks

You are about to start any meaningful piece of work — a research task, a build, a draft, a deployment, anything with a deliverable. Before you begin, create a task. During the work, mark it in_progress and write WORKING ON to daily memory. When done, complete it with a result summary and log a task_completed event. If you are blocked, set the task to blocked with the reason. If a human needs to do something first, assign it to them. Without a task, your work is invisible to the dashboard and the user.

grandamenium a1f337d 2.5 KB Updated Sep 17, 2026

File contents

Task System

Every significant piece of work must have a corresponding task. Tasks enable coordination, accountability, and measurable progress.

Task Types

Agent tasks - Work executed autonomously by the assigned agent
Human tasks - Requires human decision, input, or approval (assigned_to=human)

Lifecycle

1. Create (BEFORE starting work)

cortextos bus create-task "<title>" --desc "<description>" [--assignee <agent>] [--priority <p>] [--project <name>]

2. Mark in progress

cortextos bus update-task <task_id> in_progress

3. Execute the work

4. Complete

cortextos bus complete-task <task_id> --result "[output summary]"

5. Log KPI (if measurable)

cortextos bus log-event task task_completed info --meta '{"task_id":"ID","kpi_key":"metric_name","value":1}'

The `needs_approval` Field

true - external actions: sending emails, merging PRs, deploying, public announcements false - internal work: research, drafts, feature branches, testing

Tasks with needs_approval: true create an approval item that must be reviewed before executing external actions.

Script Reference

Action	Command
Create	`cortextos bus create-task "<title>" --desc "<desc>" [--assignee <a>] [--priority <p>]`
List	`cortextos bus list-tasks [--status S] [--agent A] [--priority P]`
Update	`cortextos bus update-task <id> <status>`
Complete	`cortextos bus complete-task <id> --result "[summary]"`
Log event	`cortextos bus log-event <category> <event> <severity> --meta '[json]'`

Statuses: pending, in_progress, blocked, completed

Priorities: urgent, high, normal, low

Best Practices

Always create before starting - ensures tracking and coordination
Be specific - clear titles, descriptions with success criteria
Complete thoroughly - include what was accomplished and where outputs are
Log KPIs - when work advances a measurable goal

---name: tasksdescription: You are about to start any meaningful piece of work — a research task, a build, a draft, a deployment, anything with a deliverable. Before you begin, create a task. During the work, mark it in_progress and write WORKING ON to daily memory. When done, complete it with a result summary and log a task_completed event. If you are blocked, set the task to blocked with the reason. If a human needs to do something first, assign it to them. Without a task, your work is invisible to the dashboard and the user.---# Task SystemEvery significant piece of work must have a corresponding task. Tasks enable coordination, accountability, and measurable progress.## Task Types- **Agent tasks** - Work executed autonomously by the assigned agent- **Human tasks** - Requires human decision, input, or approval (assigned_to=human)## Lifecycle### 1. Create (BEFORE starting work)```bashcortextos bus create-task "<title>" --desc "<description>" [--assignee <agent>] [--priority <p>] [--project <name>]```### 2. Mark in progress```bashcortextos bus update-task <task_id> in_progress```### 3. Execute the work### 4. Complete```bashcortextos bus complete-task <task_id> --result "[output summary]"```### 5. Log KPI (if measurable)```bashcortextos bus log-event task task_completed info --meta '{"task_id":"ID","kpi_key":"metric_name","value":1}'```## The `needs_approval` Field**true** - external actions: sending emails, merging PRs, deploying, public announcements**false** - internal work: research, drafts, feature branches, testingTasks with `needs_approval: true` create an approval item that must be reviewed before executing external actions.## Script Reference| Action | Command ||--------|---------|| Create | `cortextos bus create-task "<title>" --desc "<desc>" [--assignee <a>] [--priority <p>]` || List | `cortextos bus list-tasks [--status S] [--agent A] [--priority P]` || Update | `cortextos bus update-task <id> <status>` || Complete | `cortextos bus complete-task <id> --result "[summary]"` || Log event | `cortextos bus log-event <category> <event> <severity> --meta '[json]'` |**Statuses:** pending, in_progress, blocked, completed**Priorities:** urgent, high, normal, low## Best Practices- **Always create before starting** - ensures tracking and coordination- **Be specific** - clear titles, descriptions with success criteria- **Complete thoroughly** - include what was accomplished and where outputs are- **Log KPIs** - when work advances a measurable goal

Frequently asked questions