MCPInstall

add-task

creates draft task file in .specs/tasks/draft/ with original user intent

Installs
1.2K
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/neolabhq/context-engineering-kit --skill add-task
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads add-task automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Create Draft Task File

Role

Your role is to create a draft task file that exactly matches the user's request.

Goal

Create a task file in .specs/tasks/draft/ with:

  • Clear, action-oriented title (verb + specific description)
  • Appropriate type classification (feature/bug/refactor/test/docs/chore/ci)
  • Correct dependencies if any
  • Useful description preserving user intent
  • Correct file name

Input

  • User Input: The task description/title provided by the user (passed as argument)
  • Target Directory: Default is .specs/tasks/draft/

Instructions

1. Ensure Directory Structure

Run the folder creation script to create task directories and configure gitignore:

bash ${CLAUDE_PLUGIN_ROOT}/scripts/create-folders.sh

This creates:

  • .specs/tasks/draft/ - New tasks awaiting analysis
  • .specs/tasks/todo/ - Tasks ready to implement
  • .specs/tasks/in-progress/ - Currently being worked on
  • .specs/tasks/done/ - Completed tasks
  • .specs/scratchpad/ - Temporary working files (gitignored)
  • .specs/analysis/ - Analysis of the task
  • .specs/reports/ - Reports of the task

Fallback: if script not found, or there another issue, create folder structure manually and add .specs/scratchpad/ to .gitignore

2. Analyze Input

  1. Parse the user's request:

    • Extract the core task objective
    • Identify implied type (bug, feature, task)
    • List of task files that this task depends on
  2. Clarify if ambiguous (only if truly unclear):

    • Is this a bug fix or new feature?
    • Any related tasks or dependencies? (if not proided, then assume none)

3. Structure the Task

  1. Create action-oriented title:

    • Start with verb: Add, Fix, Update, Implement, Remove, Refactor
    • Be specific but concise
    • Examples:
      • "Add validation to login form"
      • "Fix null pointer in user service"
      • "Implement caching for API responses"
  2. Determine type:

    TypeUse When
    featureNew functionality or capability
    bugSomething is broken or not working correctly
    refactorCode restructuring without changing behavior
    testAdding or updating tests
    docsDocumentation changes only
    choreMaintenance tasks, dependency updates
    ciCI/CD configuration changes

4. Generate File Name

  1. Create short name from the task title:

    • Lowercase the title
    • Replace spaces with hyphens
    • Remove special characters
    • Keep it concise (3-5 words max)
    • Example: "Add validation to login form" -> add-validation-login-form
  2. Form file name: <short-name>.<issue-type>.md

    • Examples:
      • add-validation-login-form.feature.md
      • fix-null-pointer-user-service.bug.md
      • restructure-auth-module.refactor.md
      • add-unit-tests-api.test.md
      • update-readme.docs.md
      • upgrade-dependencies.chore.md
      • add-github-actions.ci.md
  3. Verify uniqueness: Check .specs/tasks/draft/, .specs/tasks/todo/, .specs/tasks/in-progress/, and .specs/tasks/done/ for existing files with same name

5. Create Task File

Use Write tool to create .specs/tasks/todo/<short-name>.<issue-type>.md:

---
title: <ACTION-ORIENTED TITLE>
depends_on: <list of task files that this task depends on>
---

## Initial User Prompt

{EXACT user input as provided}

## Description

// Will be filled in future stages by business analyst

Constraints

  • Do NOT invoke the plan skill - the workflow handles subsequent phases
  • Do NOT create files outside .specs/tasks/draft/
  • Do NOT modify existing task files
  • Do NOT write description, only put // ... placeholder as specified in the task file.
  • Do NOT write depends_on section if no dependencies are provided.

Expected Output

Return to the orchestrator:

  1. Task file path: Full path to created file (e.g., .specs/tasks/todo/add-validation-login-form.feature.md)
  2. Generated title: The action-oriented title created
  3. Issue type: task, bug, or feature

Format:

Created task file: .specs/tasks/draft/<name>.<type>.md
Title: <action-oriented title>
Type: <task|bug|feature>
Depends on: <list of task files that this task depends on>

Success Criteria

  • Directories .specs/tasks/draft/, .specs/tasks/todo/, .specs/tasks/in-progress/, .specs/tasks/done/ exist
  • Task file created in .specs/tasks/draft/ with correct naming convention (<name>.<type>.md)
  • File name is unique across all status folders (no overwriting existing files)
  • Depends on section is correct if dependencies are provided
  • Title starts with action verb (Add, Fix, Implement, Update, Remove, Refactor)
  • Type is correctly classified and reflected in file extension (.feature.md, .bug.md, .refactor.md, .test.md, .docs.md, .chore.md, .ci.md)
  • Original user input preserved in "Initial User Prompt" section
  • Description is empty placeholder // Will be filled in future stages by business analyst

Examples

Test task (.specs/tasks/draft/add-unit-tests-auth.test.md):

---
title: Add unit tests for auth module
---

## Initial User Prompt

add tests for auth

## Description

// Will be filled in future stages by business analyst

Bug with context (.specs/tasks/draft/fix-login-timeout.bug.md):

---
title: Fix login timeout on slow connections
---

## Initial User Prompt

users getting 504 errors on slow wifi

## Description

// Will be filled in future stages by business analyst

Feature request (.specs/tasks/draft/implement-dark-mode.feature.md):

---
title: Implement dark mode toggle
---

## Initial User Prompt

add dark mode to settings page

## Description

// Will be filled in future stages by business analyst

FAQ

What does the add-task skill do?

creates draft task file in .specs/tasks/draft/ with original user intent

How do I install add-task?

Run npx skills add https://github.com/neolabhq/context-engineering-kit --skill add-task in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/add-task/ (personal) or .claude/skills/add-task/ (project).

Which AI agents can use add-task?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is add-task safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains add-task?

It is published by neolabhq in neolabhq/context-engineering-kit. It has 1,227 recorded installs.

More from neolabhq/context-engineering-kit

View all →

prompt-engineering

neolabhq/context-engineering-kit

Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates.

AI & Agents1.4K installs

context-engineering

neolabhq/context-engineering-kit

Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.

AI & Agents1.4K installs

thought-based-reasoning

neolabhq/context-engineering-kit

Use when tackling complex reasoning tasks requiring step-by-step logic, multi-step arithmetic, commonsense reasoning, symbolic manipulation, or problems where simple prompting fails - provides comprehensive guide to Chain-of-Thought and related prompting techniques (Zero-shot CoT, Self-Consistency, Tree of Thoughts, Least-to-Most, ReAct, PAL, Reflexion) with templates, decision matrices, and research-backed patterns

Frontend & Design1.4K installs

reflect

neolabhq/context-engineering-kit

Reflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity triage and verification

1.4K installs

write-concisely

neolabhq/context-engineering-kit

Apply writing rules to any documentation that humans will read. Makes your writing clearer, stronger, and more professional.

Docs & Writing1.3K installs

kaizen

neolabhq/context-engineering-kit

Use when Code implementation and refactoring, architecturing or designing systems, process and workflow improvements, error handling and validation. Provide tehniquest to avoid over-engineering and apply iterative improvements.

Popular productivity & automation skills

View category →

agent-browser

vercel-labs/agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

OfficialProductivity & Automation1.3M installs

lark-doc

open.feishu.cn

飞书云文档(Docx / Wiki)内容操作:读取、创建、编辑文档,插入或下载图片附件,以及操作思维笔记。用户提供文档 URL/token(包括 doubao.com 的 /docx/、/wiki/)时使用;按 URL 路径/token 而非域名路由;/page/ 是妙搭应用,非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive;随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。

lark-base

open.feishu.cn

飞书多维表格(Base)操作:建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式(BaseApp/AppMode 页面与组件)、Workspace 目录、workflow、角色权限、模板中心(多维表格模板分类/列表/搜索);遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps;文件导入/导出转 lark-drive,认证/授权转 lark-shared。

lark-drive

open.feishu.cn

飞书云空间(云盘/云存储):管理 Drive 文件和文件夹,包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签(secure labels)和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题,或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用;doubao.com 云空间 URL/token 也按资源路径和 token 路由,不回退 WebFetch。不负责:文档内容编辑(走 lark-doc)、表格/Base 表内数据操作(走 lark-sheets/lark-base)、知识空间节点/成员管理(走 lark-wiki)、原生 Markdown 文件读写/patch/diff(走 lark-markdown)。

lark-shared

open.feishu.cn

Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.

lark-im

open.feishu.cn

飞书即时通讯:收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片(Interactive Card)、监听卡片按钮回调(card.action.trigger)。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶(添加/移除/查询置顶会话)、管理标签数据、处理卡片回调时使用。