agentleFS
Sign inStart free
AsiaOstrichAsiaOstrich/EngramGraph/.agents/skills/requirement-assistant/SKILL.md

requirement

Skill4 starsChanged 29 days agoMITView on GitHub

[UDS] Write user stories and requirements that satisfy the INVEST criteria. Use when: turning a feature idea into a user story, defining testable acceptance criteria, checking a backlog item for quality. Not for: full specification documents with design and delta operations — use /sdd; deciding whether the idea is right at all — use /brainstorm. Keywords: requirement, user story, INVEST, acceptance criteria, backlog refinement, 需求, 使用者故事, 驗收條件.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write well-structured user stories and requirements following INVEST criteria.

    line 15
  2. Distinctive:

    Write user story: - Follow the standard format | 遵循標準格式

    line 23
  3. Distinctive:

    Validate with INVEST: - Check quality criteria | 用 INVEST 驗證品質

    line 25
  4. Very specific:

    After /requirement completes, the AI assistant should suggest:

    line 69

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Requirement Assistant | 需求助手

Write well-structured user stories and requirements following INVEST criteria.

撰寫結構良好的使用者故事和需求文件，遵循 INVEST 準則。

Workflow | 工作流程

  1. Understand context - Gather feature information | 蒐集功能資訊
  2. Identify stakeholders - Who benefits from this feature? | 誰受益？
  3. Write user story - Follow the standard format | 遵循標準格式
  4. Define acceptance criteria - Specific, testable conditions | 定義可測試條件
  5. Validate with INVEST - Check quality criteria | 用 INVEST 驗證品質

User Story Format | 使用者故事格式

As a [role],
I want [feature],
So that [benefit].

### Acceptance Criteria

- [ ] Given [context], when [action], then [result]
- [ ] Given [context], when [action], then [result]

INVEST Criteria | INVEST 準則

CriterionDescription說明
IndependentCan be developed separately可獨立開發
NegotiableDetails can be discussed可協商細節
ValuableDelivers value to user提供使用者價值
EstimableCan estimate effort可估算工作量
SmallFits in one sprint適合單一迭代
TestableHas clear test criteria有明確測試標準

Quality Checklist | 品質檢查清單

  • User story follows "As a / I want / So that" format
  • At least 2 acceptance criteria defined
  • All 6 INVEST criteria satisfied
  • Edge cases and error scenarios considered
  • Out of scope items documented

Usage | 使用方式

/requirement                         - Interactive requirement wizard | 互動式需求精靈
/requirement user login              - Write requirement for feature | 為功能撰寫需求
/requirement "users can export data" - Based on description | 根據描述撰寫

Next Steps Guidance | 下一步引導

After /requirement completes, the AI assistant should suggest:

需求文件已完成。建議下一步 / Requirement document complete. Suggested next steps:

  • 執行 /sdd 建立規格文件 ⭐ Recommended / 推薦 — Create a specification document
  • 執行 /atdd 定義驗收測試 — Define acceptance tests
  • 執行 /brainstorm 進一步探索需求空間 — Explore the requirement space further

Reference | 參考

  • Requirement Completeness Checklist — Read it when checking a requirement is complete before it is accepted.
  • Requirement Writing Guide — Read it when writing a requirement from scratch.
  • Detailed guide: guide.md
  • Core standard: requirement-engineering.md

AI Agent Behavior | AI 代理行為

完整的 AI 行為定義請參閱對應的命令文件：/requirement

For complete AI agent behavior definition, see the corresponding command file: /requirement

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.

Check your setup, free