본문으로 건너뛰기
cccskills
무료GitHub에 공개

frd-writer

Write a Functional Requirements Document. Use when the user says "write an FRD", "functional requirements", "system requirements", "SRS", "what should the system do", "document the functional specs", "software requirements specification", "detailed requirements for engineering", "functional spec" - even if they don't explicitly say "FRD".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(2)

  • SKILL.md5.1 KB
  • references/requirements-attributes.md2.7 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Reference Files

  • references/requirements-attributes.md - Standard attributes for each requirement (ID, type, priority, status, source, rationale, fit criterion, dependencies). Read this in Step 3 when writing individual requirements.

Overview

Based on Software Requirements by Karl Wiegers & Joy Beatty - the modernized IEEE 830 SRS structure that organizes functional requirements by feature or use case, not by system component. Also draws on User Stories Applied by Mike Cohn for agile-format FRDs using the INVEST criteria (Independent, Negotiable, Valuable, Estimable, Small, Testable). The key insight from Wiegers: every functional requirement must have a rationale (why it exists) and a fit criterion (how you know it's satisfied). Requirements without these two attributes are wishes, not requirements.

Workflow

Step 1: Define the system context

Before writing requirements, establish what the system is:

SYSTEM NAME: [name]
PURPOSE: [one sentence]
USERS: [user roles and their primary goals]
ADJACENT SYSTEMS: [systems this integrates with]
SCOPE REFERENCE: [link to BRD or scope document]

Step 2: Organize by functional area

Group requirements by user-facing capability, not by technical layer:

FA-1: User Registration and Authentication
FA-2: Order Management
FA-3: Reporting and Analytics
FA-4: Notifications

Step 3: Write individual requirements

For each requirement, use the attributes from references/requirements-attributes.md:

ID: FR-[area]-[number] (e.g., FR-AUTH-001)
DESCRIPTION: The system shall [action] when [condition] so that [rationale].
PRIORITY: [Must / Should / Could - MoSCoW]
SOURCE: [stakeholder, BRD reference, or regulation]
FIT CRITERION: [measurable condition that proves this requirement is met]
DEPENDENCIES: [other requirements this depends on]

Example:

ID: FR-AUTH-001
DESCRIPTION: The system shall lock the account after 5 consecutive failed
login attempts so that brute-force attacks are mitigated.
PRIORITY: Must
SOURCE: Security team, ISO 27001 requirement
FIT CRITERION: Account is locked within 1 second of the 5th failed attempt.
Locked account cannot authenticate until unlocked by admin or timeout (30 min).
DEPENDENCIES: FR-AUTH-003 (account unlock process)

Step 4: Define non-functional requirements

For each quality attribute:

NFR-PERF-001: Page load time shall not exceed 2 seconds under 1000 concurrent users.
NFR-SEC-001: All PII shall be encrypted at rest (AES-256) and in transit (TLS 1.2+).
NFR-AVAIL-001: System uptime shall be 99.9% measured monthly, excluding planned maintenance.

Step 5: Document business rules

Rules that govern system behavior:

BR-001: [If condition, then action]
Example: If order total exceeds [threshold], require manager approval before processing.
Source: [policy document or stakeholder]

Step 6: Add a data requirements summary

List key data entities, their attributes, and CRUD operations (which functions create, read, update, or delete each entity).

Step 7: Assemble the FRD

# Functional Requirements Document: [System Name]
**Version:** [X.X]  **Status:** [Draft / Review / Approved]

## 1. System Context
## 2. Functional Requirements (by area)
## 3. Non-Functional Requirements
## 4. Business Rules
## 5. Data Requirements
## 6. Assumptions and Constraints
## 7. Traceability (to BRD objectives)
## 8. Approval

Anti-Patterns

1. Requirements without fit criteria Bad: "The system shall be fast." (How fast? For whom? Under what conditions?) Good: "Search results shall return within 500ms for queries against up to 1M records."

2. Solution-specific language in requirements Bad: "Use a PostgreSQL stored procedure to calculate totals." Good: "The system shall calculate order totals including tax and discount rules."

3. Compound requirements Bad: "The system shall allow users to search orders, filter by date, and export to CSV." Good: Split into FR-ORD-010 (search), FR-ORD-011 (filter), FR-ORD-012 (export). Each independently testable.

4. Missing rationale Bad: "FR-AUTH-005: The system shall require passwords of at least 12 characters." Good: Same requirement with "so that [rationale]" - why 12? Policy? Regulation? Risk assessment?

Quality Checklist

  • System context defined (purpose, users, adjacent systems)
  • Requirements organized by functional area, not technical layer
  • Every requirement has ID, description, priority, source, and fit criterion
  • No compound requirements - each is independently testable (INVEST: Small, Testable)
  • Non-functional requirements are quantified
  • Business rules documented with source
  • Each requirement traces back to a BRD objective
  • Assumptions and constraints listed

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Rate any product, feature, or experience on the 11-star scale (Brian Chesky's Airbnb thought experiment). Use when user says "rate this experience", "11-star", "star rating", "experience audit", "how good is this", "experience rating", "product audit", "quality assessment", or wants to evaluate product quality and identify improvement paths. Also trigger when user wants to benchmark a feature, assess where a product stands, or map out what "great" looks like - even if they don't explicitly say "11-star".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

qa-aman/claude-skills212026년 10월 19일 업데이트

Generate A/B copy variants grounded in Eugene Schwartz's awareness and market-sophistication stages and John Caples' tested-headline discipline. Every variant declares its angle, the awareness stage it targets, and a falsifiable hypothesis, and the skill recommends which pair to test first and what delta counts as signal. Use when the user says "A/B test this", "write variants", "give me options", "test different angles", "copy variants", "ab copy", "test this headline", "multiple versions", "which version is better", or wants to test copy before publishing. For reviewing copy that already exists, see copy-review. For sample size and stopping rules, see growth-experiment. For diagnosing a page rather than its words, see page-cro. For full paid ad sets by platform, see ad-campaign-writer.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

qa-aman/claude-skills212026년 10월 19일 업데이트

Design statistically rigorous experiments to test data science hypotheses. Use when the user says "design an A/B test", "run an experiment", "test this hypothesis", "is this difference significant", "how many samples do I need", "randomized controlled trial", "causal inference", "uplift test", "holdout group", "significance test", "power calculation", "avoid p-hacking", or needs to determine whether an observed effect is real before making a product or model decision. For lean build-measure-learn product experiments without the statistics, use experiment-design instead.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

qa-aman/claude-skills212026년 10월 19일 업데이트

Write measurable acceptance criteria for requirements or user stories. Use when the user says "write acceptance criteria", "definition of done", "how do we test this", "fit criteria", "given when then", "Gherkin scenarios", "what does done look like", "testable conditions", "how will we know this works" - even if they don't explicitly say "acceptance criteria".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

qa-aman/claude-skills212026년 10월 19일 업데이트

Build a strategic account plan for winning, retaining, or expanding a named account. Use when the user says "build an account plan", "strategic account planning", "how do I grow this account", "account expansion strategy", "whitespace analysis", "QBR prep", "key account review", "map the stakeholders in this account", "land and expand plan", "how do I break into [company]", or wants a structured strategy for a specific account.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

qa-aman/claude-skills212026년 10월 19일 업데이트

Write paid ad copy for LinkedIn, Google, Meta, and YouTube. Produces multiple variants per platform, each targeting a different Eugene Schwartz awareness level and Cialdini persuasion principle. Use when the user asks for ad copy, ad variants, "write LinkedIn ads", Google ads, Meta ads, paid social copy, ad headlines, or wants creative for a paid campaign. Reads brand voice, ICP, and positioning from knowledge/. For organic social posts, see linkedin-post or social-calendar. For the landing page the ad points at, see landing-page-writer. For testing variants, see ab-copy-writer.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

qa-aman/claude-skills212026년 10월 19일 업데이트

qa-aman의 스킬 모두 보기

이 스킬의 문제 신고