Engineering Task Decomposer Agent Skill

Deconstructs complex software engineering requirements into executable, verifiable, and backend-agnostic task packages (TP-XXX).

Context cost
18.6k tokensestimated from the bundle, loaded when it triggers
Bundle
15 files · 74.6 kBtext throughout, nothing executable
Licence
Apache-2.0the author’s own terms
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

Use when 用户需要把复杂需求拆成可执行、可验证、可交接的工程任务包,或需要校验、审查、汇总已有 TP-XXX 任务包。该 Skill 只负责任务建模与质量门禁,不负责选择模型、分配推理强度或绑定具体 Agent 后端。

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

productivity

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md6.4 kB · preview
--- name: engineering-task-decomposer ---
6# 工程化 Agent 任务拆解器
7
8把本 Skill 视为一个**后端无关的任务编译器**:把复杂需求编译成边界清楚、输入闭合、可独立验证的任务包,再交给人工分发或任意兼容执行后端。
9
10## 核心原则
11
121. **先判断是否值得拆。**不要为了形式把简单任务工程化。
132. **默认按纵向切片拆。**一个 TP 优先形成可观察、可验证的小闭环,而不是长期按“数据层 / API / UI / 测试”水平分层。
143. **任务包是执行合同,不是项目百科。**只写执行该 TP 必须知道的事实、边界和验收。
154. **单一事实来源。**同一事实不要在多个文件中重复维护;派生视图不得反过来成为权威状态。
165. **按需加载规则。**拆解阶段不提前加载 Reviewer、Aggregator、执行后端或模型路由规则。
176. **证据优先。**任务必须有客观验收方式;“看起来没问题”“执行者说完成了”不是证据。
187. **风险自适应。**独立 Reviewer、worktree、完整状态机、最终完整性清单等重机制只在风险和协作复杂度足够高时启用。
198. **不包含模型分配。**本 Skill 不生成模型推荐、推理强度推荐、模型事实快照或 Token 路由文件。
20
21## 复杂度分级门禁
22
23开始拆解前先选择最轻且足够安全的级别:
24
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md289 words
Files15
LicenceApache-2.0
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈40
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
18,610
on trigger
The instruction body and 14 supporting files, read only when the skill fires.
9.3%
of a 200k window
Ten skills this size would take about 93% of the window before you open a file.
050k100k150k200k context window

18.6k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

15 files, 74.6 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in. 1 file of its source is not in the download — listed after these, with why.

  • SKILL.md6.4 kB
  • LICENSE11.4 kB
  • README.md2.9 kB
  • agents/openai.yaml0.4 kB
  • references/AGGREGATOR_PROMPT.md4.0 kB
  • references/REVIEWER_PROMPT.md3.1 kB
  • references/VALIDATION_RULES.md6.0 kB
  • references/task-package.schema.json6.9 kB
  • references/任务包标准模板.md5.4 kB
  • references/任务状态机与转换规则.md4.1 kB
  • references/工程化拆解提示词.txt11.3 kB
  • skills/aggregate-agent-results/SKILL.md2.2 kB
  • skills/decompose-project/SKILL.md5.3 kB
  • skills/review-task-package/SKILL.md2.1 kB
  • skills/validate-task-package/SKILL.md3.1 kB

Not in the download

Not carried is a type a skill download does not hold. Take it from its source.

  • .gitignorenot carried
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the download is 15 files — not the whole of its source: 1 file is left out. It is listed under the files, with why. The Apache-2.0 licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Engineering Task Decomposer · 18.6k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/engineering-task-decomposer/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/engineering-task-decomposer" ] && { [ ! -e .claude/skills/engineering-task-decomposer ] || { mv .claude/skills/engineering-task-decomposer "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/engineering-task-decomposer" .claude/skills/ && echo "Installed .claude/skills/engineering-task-decomposer"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add ganymede5757/engineering-task-decomposer

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/engineering-task-decomposer/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/engineering-task-decomposer/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/engineering-task-decomposer" ] && { [ ! -e ~/.claude/skills/engineering-task-decomposer ] || { mv ~/.claude/skills/engineering-task-decomposer "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/engineering-task-decomposer" ~/.claude/skills/ && echo "Installed ~/.claude/skills/engineering-task-decomposer" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/engineering-task-decomposer/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. Not in this download: 1 file of its source (which one, and why). Take it from its source.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referenceganymede5757/engineering-task-decomposer

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Publisher
Servers0
Claim this skill