agentleFS
alisuleymantopuzalisuleymantopuz/urdesigner/skills/story/SKILL.md

story

Skill0 starsChanged 5 months agoMITView on GitHub

Decompose an epic into user stories with Given/When/Then acceptance criteria, Definition of Done, technical notes grounded in the codebase, and readiness flags.

15 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use story-deslop, story-long-write and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • XiaoyangySkill

    story-deslop

    网文去AI味。检测并清除文本中的AI写作痕迹,让文字回归自然、非模板化。触发方式:/story-deslop、/去AI味、「去AI味」「这篇太AI了」「网文去AI味」。

    Also in 5 projects that use this

  • XiaoyangySkill

    story-long-write

    长篇网文写作方法论与 novel-studio pipeline 适配器。用于把长篇开书、大纲、日更、续写、重写等需求整理为 pipeline 输入;在 novel-studio 内禁止直接生成正文。触发方式:/story-long-write、/写长篇、「帮我开书」「写大纲」「日更」「续写」「继续写」「修改第X章」「回炉」「重写第X章」。

    Also in 5 projects that use this

  • worldwondererSkill

    story-cover

    小说封面生成与提示词设计。根据书名、作者名和题材构建封面提示词;用户只要提示词时不生图,要求封面图时调用 GPT-Image-2,Codex CLI 优先使用内置 ImageGen。触发方式:/story-cover、/封面、「帮我做个封面」「生成封面图」「封面提示词」「封面设计」。

    Also in 4 projects that use this

  • worldwondererSkill

    story-import

    逆向导入已有小说。将已写好的小说(半成品或完本)反向解析为标准项目目录结构,兼容 story-long-write / story-short-write 后续写作流程;内部复用 story-long-analyze / story-short-analyze 的拆解管道,按篇幅自动分流。触发方式:/story-import、「导入小说」「反向解析」「导入」「把我的书导进来」。

    Also in 4 projects that use this

  • marketcallsSkill

    story-setup

    Set up the story-telling environment. Checks Node, installs dependencies, creates .env from the template, verifies the Sarvam, fal and OpenAI keys, and confirms all Remotion packages are on one version.

    Also in 5 projects that use this

  • badgidsSkill

    story-review

    Diagnose existing prose at a chosen editorial level, from whole-story and developmental problems through scene, line, copy, and proof passes, without rewriting until the diagnosis is accepted.

    Also in 5 projects that use this

  • +2 more from Xiaoyangy
  • +3 more from worldwonderer

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 6 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    3–8 stories per epic: If you need more, the epic should be split first.

    line 16
  2. Distinctive:

    Read CLAUDE.md if it exists.

    line 22
  3. Distinctive:

    Ask the user which epic to break down.

    line 24
  4. Distinctive:

    Read the relevant codebase areas this epic touches — the components, services, models, and tests that will be affected.

    line 25
  5. Distinctive:

    If a story fails any criterion, note it explicitly under the story and reshape it.

    line 48
  6. Very specific:

    If NEEDS_CLARIFICATION: state the specific question that blocks this story.

    line 91
  7. Very specific:

    If NEEDS_SPIKE: state what must be learned and approximately how long the spike should be.

    line 92
  8. Distinctive:

    After producing the complete story breakdown, save it to the project:

    line 113
  9. Very specific:

    Create docs/stories/ if it doesn't exist.

    line 115
  10. Very specific:

    Write the full output to: docs/stories/YYYY-MM-DD-{slug}.md using today's actual date.

    line 117

“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/story — Story Breakdown

You are running the urdesigner /story skill. Your job is to break a single epic into user stories — each independently workable, testable, and sized for a single sprint.

Ground rules

  • Planning only. You will not write, modify, or suggest code changes.
  • Code-grounded only. Technical notes must reference actual code you've read — never invent implementation details.
  • Honest readiness. Flag any story that can't be started without a spike or external decision.
  • 3–8 stories per epic. If you need more, the epic should be split first.

Step 1 — Gather context

  1. Read CLAUDE.md if it exists.
  2. Read STRATEGY.md if it exists.
  3. Ask the user which epic to break down. Read the full epic description carefully.
  4. Read the relevant codebase areas this epic touches — the components, services, models, and tests that will be affected.

Step 2 — Shape the stories

User story format

As a [specific role], I want [concrete goal], so that [meaningful benefit].

Rules for the role:

  • Be specific. Not "user" — use "account owner", "API consumer", "support agent", "guest visitor".
  • The role should determine what permissions and UI state the story is written against.

INVEST checklist (apply to each story)

  • Independent: Can be worked without waiting for another story in the same epic.
  • Negotiable: The how is flexible; the what is clear.
  • Valuable: Delivers observable value to the user or the system.
  • Estimable: A senior engineer can estimate it in 1–5 days.
  • Small: Fits within a sprint.
  • Testable: Acceptance criteria are binary — pass or fail.

If a story fails any criterion, note it explicitly under the story and reshape it.


Step 3 — Output

Produce 3–8 stories using this format:


Stories: [Epic Name]

Epic: [Epic name and one-sentence scope] Files reviewed: [list key files read]


Story 1: [Short name]

As a [role], I want [goal], so that [benefit].

Acceptance Criteria

  • Given [context], when [action], then [outcome]
  • Given [context], when [action], then [outcome]
  • Given [invalid/error state], when [action], then [error handling outcome]

Definition of Done

  • Code reviewed and merged to main
  • Unit/integration tests written and passing
  • No regression in existing tests
  • [Any story-specific criteria: feature flag, docs update, etc.]

Technical Notes Brief, specific notes about relevant code — cite file paths or function names you've actually read. Omit this section if you have no relevant code evidence.

Dependencies

  • Depends on: Story N / none
  • Blocking: Story N / none

Status: READY / NEEDS_CLARIFICATION / NEEDS_SPIKE

If NEEDS_CLARIFICATION: state the specific question that blocks this story. If NEEDS_SPIKE: state what must be learned and approximately how long the spike should be.


[Repeat for each story]


Deferred Backlog

Stories that were considered but not included, with rationale:

  • [Story idea]: deferred because [reason — scope, dependency, uncertainty]

Questions for the team

Any open questions that apply across multiple stories in this epic.


Save artifact

After producing the complete story breakdown, save it to the project:

  1. Create docs/stories/ if it doesn't exist.
  2. Derive a kebab-case slug from the epic name (e.g. "Epic 2: Payments" → epic-2-payments).
  3. Write the full output to: docs/stories/YYYY-MM-DD-{slug}.md using today's actual date.
  4. Tell the user the exact path where it was saved.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.