Skip to content
Skills Library
AI & agents · Planning

ntasks

/ntasks

Rules for tracking work in Ntasks, the task list a person shares with their AI agents, through the ntasks MCP server's tools. Use at the start of every session and whenever you choose, start, find or finish work, including a bug, debt, a follow-up or a question for a person that you come across while doing something else, and whenever a step needs a person's decision or approval. Use instead of TODO comments, lists in documents or memory notes.

Repository
Ntasks ↗
Licence
AGPL-3.0
Last repository change
13.11.2026

Assessment and security

86/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content21 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
5
Scripts
0
HTML comments
0
URLs in SKILL.md
2
Deprecation

No signals detected. Repository changed on 13.11.2026, without references to retired models or APIs.

Licence

AGPL-3.0, copyleft: przeróbki udostępniane innym muszą mieć tę samą licencję.

What it does and when to use it

Rules for tracking work in Ntasks, the task list a person shares with their AI agents, through the ntasks MCP server's tools. Use at the start of every session and whenever you choose, start, find or finish work, including a bug, debt, a follow-up or a question for a person that you come across while doing something else, and whenever a step needs a person's decision or approval. Use instead of TODO comments, lists in documents or memory notes.

Original author description

Rules for tracking work in Ntasks, the task list a person shares with their AI agents, through the ntasks MCP server's tools. Use at the start of every session and whenever you choose, start, find or finish work, including a bug, debt, a follow-up or a question for a person that you come across while doing something else, and whenever a step needs a person's decision or approval. Use instead of TODO comments, lists in documents or memory notes.

How it works

  1. Ntasks
Original SKILL.md headings · 12 lines, 252 words
SKILL.md preview
---
name: ntasks
description: Rules for tracking work in Ntasks, the task list a person shares with their AI agents, through the ntasks MCP server's tools. Use at the start of every session and whenever you choose, start, find or finish work, including a bug, debt, a follow-up or a question for a person that you come across while doing something else, and whenever a step needs a person's decision or approval. Use instead of TODO comments, lists in documents or memory notes.
---

## Ntasks

- Ntasks is the only list of open work. Reach it through the `ntasks` MCP server's tools.
- Call `get_task_guide` before task work for the workflow and writing guide. Read it again when `list_workspaces` returns a new `guideVersion`.
- Before drafting, call `get_task_template` with the matching type: `task`, `bug`, `decision` or `human_action` for steps that unblock separate work. Use the sections that apply. If your server has no template tool, open the [Markdown files](https://github.com/notice-cx/Ntasks/tree/main/skills/ntasks/templates).
- File work you find as a task. Search with `list_tasks` and `query` across projects first. Keep progress, findings, decisions and hand-overs on the task. If another tool asks for a note, give it a task link.
- Claim before building. Pass `touches`, check for overlaps and read any parent context. The guide explains how to coordinate overlapping work and share facts on an epic.
- Record progress after each push and attach the pull request when you open it. A recorded pull request usually closes the task when it merges. Close remaining work with evidence when it is done. The guide explains the exceptions.
- Label work only a person can do `human`. Use `choices` for a decision and `request_human_approval` to ask permission. Use `request_human_action` when the person's steps unblock a separate deliverable. When the steps are the whole job, keep one task, including any check or record of the result.
- If the `ntasks` tools are missing, ask the person to connect the server (https://github.com/notice-cx/Ntasks/blob/main/docs/agents.md), and track no work anywhere else until they do.
Files in this package (5)
  • SKILL.md 2 KB
  • templates/bug.md 1 KB
  • templates/decision.md 1 KB
  • templates/human-action.md 1 KB
  • templates/task.md 1 KB

Versions

The database has no other skills named ntasks.

Database snapshot: 13.11.2026 · package version d9f6fb68a693 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 90memory
    This skill should be used when the user asks to record a design decision, search past project decisions, inspect the Alfred memory timeline, or work with the alfred-memory MCP server. Use it to call the namespaced MCP tools instead of inventing history.
  • 100mnemos
    Persistent memory and learning-loop skills for AI coding agents using mnemos MCP tools. Use whenever mnemos_* MCP tools are available and you are doing work worth remembering. Cross-session memory, conventions, corrections, and architectural decisions surface back into context…
  • 90orca-mcp
    Drive coding agents running in Orca (stablyai/orca) through the orca-mcp tools: start workers in their own worktrees, watch their state, wait for them to finish, answer them and clean up. Use when the user wants work handed to Claude Code, Codex or another agent inside Orca,…
  • 100using-swarm
    Get work done by the person's Swarm through its MCP tools: delegate goals to Swarm or give jobs straight to its workers, follow and review them, deliver results, request media, and set up workers, schedules, workflows and environments when the person wants them. Use when the…
  • 100openviking-memory
    Recall and persist long-term memory through the OpenViking MCP tools. Use at the start of any substantive task (coding, configuration, debugging, multi-step or tool-based work) to retrieve relevant prior knowledge with find/search/read, and during or after work to persist…
  • 100session-search
    Use Moraine MCP tools to recover prior agent-session context when the user refers to earlier work, decisions, failures, branches, files, or other agents.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.