본문으로 건너뛰기
cccskills
무료GitHub에 공개

sr:generate

Phase 6 of the SRS workflow. Reads approved plan files and generates a complete IEEE 830-compliant SRS — one file per section, no word limit. A full SRS may span 300+ pages across all files.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(1)

  • SKILL.md4.6 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

sr:generate

Goal: produce a complete, publication-ready IEEE 830 SRS. No word limit. Each section file must be fully written — no placeholders, no summaries, no "see plan for details."


Step 0 — Identify Project & Gate

AskUserQuestion: "Which project to generate SRS for? (slug)"

Read all files in projects/{slug}/plan/. If plan files don't exist or are incomplete: tell user to run /sr:plan first.

Run the readiness gate before writing anything:

python .claude/scripts/plan_validator.py --dir projects/{slug}/plan/
  • BLOCKED (ERRORs found, e.g. missing file, FR numbering gap, missing "shall" clause, bad priority tag): stop here. List the ERRORs and tell the user to fix them via /sr:plan before retrying /sr:generate.
  • READY WITH WARNINGS (e.g. unresolved [NEEDS USER INPUT] not yet logged in appendix-b-open-issues.md): show the warnings and ask the user to confirm proceeding anyway, or go back to /sr:plan to resolve them.
  • READY: proceed to Step 1.

Load .claude/skills/srs-generator/references/srs-template.md.


Step 1 — Generate Section Files

Create files under projects/{slug}/srs/. Write each file completely before moving to the next. Follow srs-template.md formatting for each section.

File order:

srs/
  01-introduction.md
  02-overall-description.md
  03-01-external-interfaces.md
  03-02-functional-requirements.md
  03-03-performance.md
  03-04-database.md
  03-05-design-constraints.md
  03-06-system-attributes.md
  03-07-other-requirements.md
  appendix-a-glossary.md
  appendix-b-open-issues.md

FR Format (mandatory for every FR in 03-02)

#### FR-NN [Essential|Conditional|Optional]

**Requirement:** The system shall {precise verb} {object} when {condition}.

| Field | Value |
|-------|-------|
| Actor | {who triggers this} |
| Precondition | {system state before} |
| Trigger | {what causes it} |
| Source | {brainstorm round / business rule / regulatory} |

**Acceptance Criteria (GWT):**
- **Given** {system state}
- **When** {actor action or event}
- **Then** {expected system response — measurable}
- **And** {additional assertions if needed}

Rules:

  • FR-IDs continue sequentially across the entire file — no resets
  • Every FR must have: shall clause + all table fields + full GWT
  • No "TBD" in Requirement lines — if a requirement is unclear, it should not be in the SRS yet (surface it in appendix-b-open-issues.md instead)

NFR Format (mandatory for every NFR in 03-03 and 03-06)

ISO/IEC 25023 Quality Attribute Scenario format:

#### NFR-NN — {ISO 25010 Characteristic}: {Sub-characteristic}

| Field | Value |
|-------|-------|
| Source of Stimulus | {who/what triggers the scenario} |
| Stimulus | {the event} |
| Environment | {system state at time of event} |
| Artifact | {which part of the system} |
| Response | {what the system does} |
| Response Measure | {numeric threshold — e.g., ≤ 500ms at 95th percentile} |

Rule: Response Measure must be numeric. No adjectives ("fast", "good", "acceptable"). If genuinely unknown: [TBD: {what data is needed} | owner: {role} | resolve-by: {milestone}]


Step 2 — Generate Master Index

Write projects/{slug}/srs/00-master-index.md:

# SRS Master Index — {Project Name}
Version: 1.0   Date: {date}   Status: DRAFT

## Document Map
| File | Section | Description | Word count (est.) |
|------|---------|-------------|-----------------|
...

## FR Summary
Total FRs: {n}
- Essential: {n}
- Conditional: {n}
- Optional: {n}

## NFR Summary
Total NFRs: {n} ({n} confirmed / {n} [TBD])

## Open Items
{count} items in appendix-b-open-issues.md requiring resolution before FINAL status.

Step 3 — Handoff

Run python .claude/scripts/srs_validator.py --dir projects/{slug}/srs/ --stats and use its counts below (don't recount a 300+ page document by hand).

Output:

SRS generation complete.

Location: projects/{slug}/srs/
Files: 11 section files + 00-master-index.md
FRs:  {total} ({Essential}/{Conditional}/{Optional})
NFRs: {total} ({confirmed} confirmed / {TBD} [TBD])

Next: /sr:validate → validates SRS against IEEE 830-1998

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

Build robust backend systems — APIs (REST, GraphQL, gRPC), authentication (OAuth 2.1, JWT), databases, performance optimization, security (OWASP Top 10), scalability patterns (microservices, caching, sharding), and testing. Use when designing APIs, implementing auth, optimizing queries, handling security vulnerabilities, building microservices, or developing production-ready backend systems.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

DangQuangSE/team-development-skills192026년 10월 19일 업데이트

caveman

무료

Terse output mode — strips filler/articles/hedging, ~75% token reduction. Activate whenever: context is filling up, user says be brief/terse/caveman/less tokens, or CAVEMAN_TRIGGERED appears in context. Persists every response until CAVEMAN_RELEASED or user says stop/normal mode.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

DangQuangSE/team-development-skills192026년 10월 19일 업데이트

Explore and debate solutions before writing code. Use when the user poses a design question, asks "how should I approach X", wants to think through options before committing, or says anything like "let's brainstorm", "what's the best way to...", "I'm not sure how to tackle this", or "should I use X or Y". Always runs before /ck:plan for novel or ambiguous features. No code is written — only: explore → clarify → spec → report.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

DangQuangSE/team-development-skills192026년 10월 19일 업데이트

ck-cook

무료

Implement a feature phase by phase from a phased JSON master or Markdown plan. Before each phase, confirm whether to create/run unit tests and whether to run ck:quality, unless explicit flags supply those choices. Supports token-budgeted execution, resumable state, and TDD handoff to ck:test.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

DangQuangSE/team-development-skills192026년 10월 19일 업데이트

ck-fix

무료

Fix a bug using Scout → Diagnose → Fix → Review → Finalize. Use when the user pastes an error message, stack trace, or test failure, or says "fix this bug", "something's broken", "tests are failing", "I'm getting an error". Also accepts `--from-quality <report>` or `--from-test <report>` to fix exactly the findings/failures a report lists. Modes (pick one): --fast (trivial errors — lint, type, build — skip scout and review), --hard (mandatory review, no auto-approve).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

DangQuangSE/team-development-skills192026년 10월 19일 업데이트

ck-plan

무료

Plan a feature or system before implementation. Use when the user says "plan this", "I want to build X", "how do I implement Y", or when /ck:brainstorm produces a spec.md. Always run before /ck:cook. Modes (pick one): --fast (simple, single-file), --hard (research + red-team + validate). Composable flag (combine with any mode): --tdd — propagates into the cook pipeline. Every phase gets Design Constraints and Quality/Testing State; ck:cook confirms optional test and quality checks per phase.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

DangQuangSE/team-development-skills192026년 10월 19일 업데이트

DangQuangSE의 스킬 모두 보기

이 스킬의 문제 신고