本文へ移動
cccskills
無料GitHub で公開

srs-generator

Generate IEEE 830 SRS from raw requirements. Use when the user says "write SRS", "generate requirements doc", "analyze requirements", "I have raw requirements from a client", or pastes a client email/chat/PRD.

インストール方法を見る

含まれるファイル(4)

  • SKILL.md5.3 KB
  • agents/openai.yaml219 B
  • references/gap-detection-guide.md10.7 KB
  • references/srs-template.md8.7 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

srs-generator — IEEE 830 SRS from Raw Requirements

Pipeline: Brainstorm → Receive → Extract → Gap Scan → Clarify (P1 → P2 → P3) → Generate → Review Gate → Save

Reference files (load before starting):

  • .codex/skills/srs-generator/references/srs-template.md
  • .codex/skills/srs-generator/references/gap-detection-guide.md

Context files (load if present — created by .codex/scripts/init_project.py):

  • projects/{name}/_context/vision.md → pre-fills §1.2 Scope and §2.1
  • projects/{name}/_context/features.md → pre-fills §2.2 and IN/OUT table
  • projects/{name}/_context/tech_stack.md → pre-fills §3.5 Design Constraints
  • projects/{name}/_context/glossary.md → pre-fills Appendix A
  • projects/{name}/_context/quality_standards.md → pre-fills §3.3–§3.6 NFR

If context files exist: skip Brainstorm Gate questions already answered there.


Brainstorm Gate — Understand Context First

Do NOT ask for raw requirements yet. First understand project context.

Ask these 3 questions in one batch:

  1. System type: Web app / Mobile app / API / Internal tool / SaaS / Desktop / Other?
  2. Primary users: Who will use this system? (end customers, internal staff, admins, B2B clients…)
  3. Core problem: What problem does this system solve? (1–2 sentences)

Wait for answers. Use responses to seed §2.1 Product Perspective, §2.3 User Characteristics, and §1.2 Scope.

After receiving answers, prompt:

Context noted. Now paste your raw requirements — any format works:
client email, bullet list, chat transcript, PRD draft.

Wait for raw input, then proceed to Step 0.


Step 0 — Receive Input

Read full input silently. Emit:

Input received: ~{N} words | type: [email prose | bullet list | partial PRD | mixed]

Step 1 — Extract & Classify

Output structured block:

  • Actors — named and implied stakeholders. Tag undefined: [GLOSSARY-GAP: {actor}]
  • Features — FR-01, FR-02… in "Subject can do X" form. Note strategy: prose / bullets / PRD
  • Constraints — verbatim fragments only (tech stack, deadline, compliance, budget)
  • Out-of-Scope signals — explicit exclusions. If absent: [CONTEXT-GAP: no out-of-scope boundary stated]

Append [Source: {location}] to every item.


Step 2 — Gap Scan

Load .codex/skills/srs-generator/references/gap-detection-guide.md. Run all 7 patterns. Output:

#PriorityPatternVerbatim fragment / missing element

Zero gaps → state explicitly, jump to SRS Generation.


Step 3 — Round 1 Clarification (P1 — Blockers)

If P1 gaps exist, ask the user with ≤7 questions. Label:

Round 1 of 3 — Scope & Actors (P1 — must resolve before writing SRS)

On receipt: integrate, mark resolved gaps. Unanswered P1 → [CONTEXT-GAP: {desc}] → Appendix B. Block only if zero actors AND zero scope remain. Then proceed to Round 2.


Step 4 — Round 2 Clarification (P2 — Functional Details)

If P2 gaps remain, ask the user with ≤7 questions. Label:

Round 2 of 3 — Functional Details (P2)

Unanswered → log assumed default in SRS and Appendix B. Then proceed to Round 3.


Step 5 — Round 3 Clarification (P3 — Optional)

Ask the user with ≤7 questions. Label:

Round 3 of 3 — Non-Functional & Secondary Details (P3 — optional)
Reply 'skip' to use [TBD] placeholders.

On "skip": mark all P3 gaps [TBD: {condition} | owner: {role} | resolve-by: sprint planning]. Proceed to SRS Generation.


SRS Generation

Populate .codex/skills/srs-generator/references/srs-template.md with all gathered information.

§1.2 Scope — mandatory IN / OUT table for every feature area.

§3.2 Functional Requirements — each FR block:

FR-NN [Essential|Conditional|Optional]
Requirement:  The system shall {verb} {object} when {condition}.
Actor:        {role}
Precondition: {state}
Given:        {context}
When:         {trigger — exactly one}
Then:         {externally observable outcome}
Source:       [{location}]

Non-observable "Then" → [VERIFIABILITY-FAIL: FR-NN] → Appendix B

§3.3–§3.6 NFR — Quality Attribute Scenario (ISO/IEC 25023):

NFR-NN [{ISO/IEC 25010 characteristic}]
Source / Stimulus / Environment / Artifact / Response / Response Measure: {numeric}

After populating, run IEEE 830 quality checklist from gap-detection-guide.md. Output verdict:

  • COMPLIANT — all sections present, Appendix B empty
  • PARTIALLY COMPLIANT — sections present, Appendix B has open items
  • NON-COMPLIANT — required sections missing

Human Review Gate

Review complete. SRS is {verdict}.
Open issues: {count} (see Appendix B).
Proceed to save? [Y / n]

Wait for explicit confirmation before writing any file.


Save & Report

  1. Derive slug from §1.2 product name (lowercase, hyphenated). Fallback: ask user.
  2. Path: docs/srs-{slug}-{YYYYMMDD}.md
  3. Echo absolute path, wait for confirmation.
  4. Create docs/ if absent, write file, confirm: "Saved ✓ {absolute_path}"

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

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.

日本語の概要は準備中です。原文の説明を表示しています。

DangQuangSE/team-development-skills192026年10月9日 更新

caveman

無料

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.

日本語の概要は準備中です。原文の説明を表示しています。

DangQuangSE/team-development-skills192026年10月9日 更新

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.

日本語の概要は準備中です。原文の説明を表示しています。

DangQuangSE/team-development-skills192026年10月9日 更新

ck-cook

無料

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.

日本語の概要は準備中です。原文の説明を表示しています。

DangQuangSE/team-development-skills192026年10月9日 更新

ck-fix

無料

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).

日本語の概要は準備中です。原文の説明を表示しています。

DangQuangSE/team-development-skills192026年10月9日 更新

ck-plan

無料

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.

日本語の概要は準備中です。原文の説明を表示しています。

DangQuangSE/team-development-skills192026年10月9日 更新

DangQuangSE のスキルをすべて見る

このスキルの問題を報告する