Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Lion-1209/Lion-Skills --skill task-breakdowngit clone --depth 1 https://github.com/Lion-1209/Lion-SkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/lion-1209/lion-skills/task-breakdown)<a href="https://agentmods.dev/skills/lion-1209/lion-skills/task-breakdown"><img src="https://agentmods.dev/badge/skills/lion-1209/lion-skills/task-breakdown/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lion-1209/lion-skills/task-breakdown"><img src="https://agentmods.dev/badge/skills/lion-1209/lion-skills/task-breakdown.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00018 | $0.03248 |
| Opus 5 | $0.00009 | $0.01624 |
| Sonnet 5 | $0.00004 | $0.00650 |
| Haiku 4.5 | $0.00002 | $0.00325 |
Grade A, and why
task-breakdown scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to task-breakdown — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Breakdown
概述
把一个需求拆成"今天就能动手、做完就能验证"的小任务。核心:每个任务是一次端到端的价值交付,而不是一层架构的横切——前者让你随时有可验证的进展,后者让你做到最后才看见东西跑起来。
何时使用
- 拿到一个需求/用户故事,要转成开发任务
- 面对一个大需求,不知从何下手
- 已有任务清单,想审查拆得对不对
- 要排开发顺序和依赖关系
不该用:需求本身已经是一个明确的小改动(直接做);纯调研性命题(用 spike 流程,见下文)。
与相邻 skill 的衔接:task-breakdown 在"写 spec → 拆任务 → 执行"流水线的中间。理想入口是拿到一份定稿的 spec(用 spec-writing 产出)——方案决策已定,拆出的任务才有稳固依据;只有模糊需求时,先澄清/写 spec 再拆,否则任务建立在假设沙地上。
核心内容
先判断任务大小
不是所有需求都该拆,也不是越细越好。拿到需求先问两个方向:
- 拆不够:它能不能在一次提交里端到端做完、且做完就能验证?能 → 别拆,直接做;不能 → 用下面的流程拆。
- 拆过细:清单里有没有一堆"半小时以内的微步骤"(如"建表"和"加字段"分开、"写接口"和"加路由"分开)?有 → 合并回可独立验证的粒度。每个任务都有管理开销(上下文切换、状态追踪),碎任务的成本会淹没价值。
过度拆分比不拆还糟。粒度的尺子:一个任务做完后,能独立验证、独立合并、独立回滚——到这个粒度就停,再大不好做、再小是浪费。
澄清未知
模糊需求直接拆,会拆出一堆基于错误假设的任务。拆之前先把"会影响切片方式的未知"问清楚,不要凭猜往下走。典型该问的:
- 范围边界:哪些在 scope 内、哪些不在?("支持邮件通知"——只发交易邮件还是也发营销?)
- 规模/量级:影响技术选型和切片顺序(日活 100 vs 100 万,缓存策略天差地别)
- 完成标准:怎样算"做完了"?(性能要求、合规要求、可观测性要求)
- 已知约束:必须用的技术、不能动的部分、截止时间
分优先级问,别一次性甩给用户。未知通常很多,一次列十几条会淹没用户。按"是否阻塞第一刀"分两类:
- 阻塞项(不答就没法切第一片)——先问。例:通知系统"发什么类型、给谁发"不答,第一刀都没法落。
- 非阻塞项(先用合理默认假设推进,遇到再问)——后问或直接用假设。例:通知系统"是否多语言"——先用"只做中文"的假设推进,等做到模板那片再确认。
问的方式:把你的假设显式写出来让用户确认("我假设 X,不对就纠正我"),而不是连环追问——前者用户一句话就能校正方向,后者消耗耐心。每条最好带一句"为什么问"(这个未知如何影响切片),并在意控量(一次别超 6-8 条);spec-writing 的"澄清问题怎么问"对此有更细的展开,可参考。
反例:用户说"做个通知系统",你直接拆成"建表/写 API/写 UI"——所有切片都建立在"通知是什么、发给谁、怎么算成功"都未定义的沙地上。
选切片方向:垂直切片,别横切
这是拆任务最关键的决策。有两种切法:
- 横切层(糟糕的默认):按架构层切——"先建数据库表 → 再写后端 API → 再写前端 → 最后联调"。直觉上像"循序渐进",实则把价值验证堆到最后:你做完前 3 个任务,什么可运行的东西都没有,直到联调那一刻才暴露所有集成错误。
- 垂直切片(推荐):按端到端的价值切——"邮件通知:从 DB 读用户 → 调邮件服务发送 → 用户能在收件箱看到"。每个切片自己走完所有层,做完就有一个可验证的、跑通的功能增量。
为什么垂直切片更优:
- 早验证:第一个切片做完就能演示,错也错得早、错得便宜。
- 早集成:集成风险被摊到每个切片,而不是堆到最后爆炸。
- 进度可见:完成 N 个切片 = N 个可演示功能,而不是"后端 80% 完成"这种无法验证的进度。
一个完整的垂直切片长这样:选一个最小但真实的数据 → 走通它的 DB schema + API + 业务逻辑 + UI + 测试。第一片可以很糙(hardcode 数据、丑 UI),但要端到端跑通。
重构/迁移场景:价值换成"风险消化",切片换成"渐进可回滚"。上面定义的切片是"新功能语言"(DB+API+UI+测试、用户可演示的价值)。但重构、迁移、框架升级、性能改造这类任务没有用户可感知的新价值——用户看不到"项目变成了 TS"或"换了状态管理库"。这时机械套用"垂直切片"会卡壳,但别因此退化成横切。
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 135 lines · 18 tokens per session scan A 3d0ea591b2ab
task-breakdown is a skill published in the GitHub repository Lion-1209/Lion-Skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 3,248 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to task-breakdown, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
cosmosdb-datamodeling
Step-by-step guide for capturing key application requirements for NoSQL use-case and produce Azure Cosmos DB Data NoSQL Model design using best practices and common patterns, artifactsproduced: "cosmosdbrequirements.md" file and "cosmosdbdatamodel.md" file.
geofeed-tuner
Use this skill whenever the user mentions IP geolocation feeds, RFC 8805, geofeeds, or wants help creating, tuning, validating, or publishing a self-published IP geolocation feed in CSV format. Intended user audience is a network operator, ISP, mobile carrier, cloud provider, hosting company, IXP, or satellite…
arize-evaluator
INVOKE THIS SKILL for LLM-as-judge evaluation workflows on Arize: creating/updating evaluators, running evaluations on spans or experiments, tasks, trigger-run, column mapping, and continuous monitoring. Use when the user says: create an evaluator, LLM judge, hallucination/faithfulness/correctness/relevance, run eval…
copilot-cli-quickstart
Use this skill when someone wants to learn GitHub Copilot CLI from scratch. Offers interactive step-by-step tutorials with separate Developer and Non-Developer tracks, plus on-demand Q&A. Just say "start tutorial" or ask a question! Note: This skill targets GitHub Copilot CLI specifically and uses CLI-specific tools…
fireworks-tech-graph
A generator for technical diagrams that exports them as SVG and PNG images. It is intended for architecture, data-flow, flowchart, sequence, agent, memory, and concept-map diagrams.
adobe-illustrator-scripting
Write, debug, and optimize Adobe Illustrator automation scripts using ExtendScript (JavaScript/JSX). Use when creating or modifying scripts that manipulate documents, layers, paths, text frames, colors, symbols, artboards, or any Illustrator DOM objects. Covers the complete JavaScript object model, coordinate system…