本文へ移動
cccskills
無料GitHub で公開

sr-brainstorm

Phase 1 of the SRS workflow. User gives a project topic → AI runs a deep, categorized brainstorm (5 mandatory rounds) to fully understand actors, features, scope boundary, tech constraints, and business rules before writing anything.

インストール方法を見る

含まれるファイル(2)

  • SKILL.md4.5 KB
  • agents/openai.yaml217 B

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。

sr-brainstorm

Goal: fully understand the project before a single word of spec is written. Do NOT write spec, plan, or SRS in this session.


Step 0 — Topic Intake

Receive topic from user. Do NOT ask questions yet.

Identify:

  • Domain (e-commerce | healthcare | fintech | SaaS | internal tool | mobile | other)
  • Scale signals (MVP | startup | enterprise | unknown)
  • Any constraints already mentioned

Echo back:

Topic:   {topic}
Domain:  {domain}
Scale:   {scale}
Slug:    {kebab-case name for projects/{slug}/}

Confirm slug with user before proceeding. If topic is too vague to form a slug, ask.


Step 1 — Load Domain Questions

Load .codex/skills/srs-workflow/references/brainstorm-guide.md. Select the question bank matching the detected domain.


Step 2 — Round 1: Actors & Users

Ask the user with concrete role options (not open-ended).

Ask about:

  • Primary end users (with examples from the domain)
  • Secondary users / supporting roles
  • Admin / back-office roles
  • External systems / third-party integrations

Wait for answer. Record each confirmed actor as:

[ACTOR] {name}: {description} | access level: {read/write/admin}

Step 3 — Round 2: Core Features

Ask the user. Present a feature checklist derived from domain + topic.

For each feature cluster offer sub-options. Example for e-commerce:

  • Authentication: (A) email+password (B) OAuth (C) both (D) SSO enterprise
  • Catalogue: (A) simple products (B) configurable SKUs (C) bundles (D) subscriptions

Mark each selection as [CONFIRMED]. Infer likely missing features — ask to confirm or reject.

Wait for answer.


Step 4 — Round 3: Scope Boundary

Ask the user. Present a two-column table:

IN Scope (proposed)OUT Scope (proposed)
{feature A}{feature X}

Ask user to move items between columns or add new ones.

HARD BLOCK: Do not proceed without explicit in/out boundary confirmed by user.

Wait for answer.


Step 5 — Round 4: Technical Constraints

Ask the user:

  • Tech stack (present common options for the domain)
  • Hosting (cloud provider / on-premise / hybrid)
  • Existing systems to integrate (with yes/no options)
  • Security & compliance (GDPR | HIPAA | PCI-DSS | SOC2 | none)
  • Performance targets (show numeric examples: < 200ms | < 500ms | < 1s)
  • Timeline / budget signals

Wait for answer.


Step 6 — Round 5: Business Rules & Edge Cases

Ask the user:

  • Roles and permissions model (RBAC | ABAC | simple owner/member | custom)
  • Data ownership and retention rules
  • Key failure scenarios the system must handle gracefully
  • Pricing / billing logic (if applicable)
  • Regulatory requirements beyond what's already captured

Wait for answer.


Step 7 — Completeness Check

After Round 5, self-check against this list. Any gap = add a follow-up question NOW:

  • Every actor has name + description + access level
  • Every feature in IN scope has been confirmed (not just inferred)
  • OUT scope list is explicit (minimum 3 items)
  • At least one numeric NFR target per: Performance / Availability / Security
  • At least one business rule per feature cluster
  • Compliance requirements stated (even if "none")
  • Integration points listed (even if "none")

If ANY box is unchecked: ask a targeted follow-up round before proceeding.


Step 8 — Save Brainstorm Output

Write projects/{slug}/brainstorm.md:

# Brainstorm: {project name}
Date: {date}

## Topic
{user's original topic verbatim}

## Domain / Scale
{domain} / {scale}

## Actors
{list with [ACTOR] entries}

## Confirmed Features (IN Scope)
{confirmed list}

## OUT of Scope
{explicit list}

## Technical Constraints
{answers from Round 4}

## Business Rules
{answers from Round 5}

## NFR Baselines
{confirmed numeric targets, or [TBD] with context}

## Open Items
{anything still unresolved — will become [TBD] tags in spec}

Step 9 — Handoff

Output:

Brainstorm complete.

Project: {name}   Slug: {slug}
Actors:  {count}
Features confirmed (IN scope): {count}
OUT scope items: {count}
Open items: {count}

Saved: projects/{slug}/brainstorm.md

Next: $sr-spec → writes the full spec from this brainstorm

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