メニュー
Design before implementation. Use before any creative or constructive work (features, architecture, behavior changes) to transform vague ideas into validated designs.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/ActiveMemory/ctx --skill ctx-brainstormコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
SOC 職業分類に基づく
SKILL.md を表示中
| name | ctx-brainstorm |
| description | Design before implementation. Use before any creative or constructive work (features, architecture, behavior changes) to transform vague ideas into validated designs. |
Transform raw ideas into clear, validated designs through structured dialogue before any implementation begins.
.context/DECISIONS.md for
related past decisions; do not re-litigate settled choices/ctx-brainstorm
/ctx-brainstorm (new caching layer for the API)
/ctx-brainstorm (should we split the monolith?)
Design facilitator, not builder.
Slow down just enough to get it right.
Before asking questions:
.context/DECISIONS.md for related past decisionsDo not design yet.
Goal: shared clarity, not speed.
Rules:
Focus on:
Explicitly clarify or propose assumptions for:
If the user is unsure, propose reasonable defaults and mark them as assumptions.
Before proposing any design, pause and provide:
Understanding Summary (5-7 bullets):
Assumptions: list all explicitly.
Open Questions: list unresolved items.
Then ask:
"Does this accurately reflect your intent? Confirm or correct before we move to design."
Do NOT proceed until confirmed.
Once understanding is confirmed:
After the user picks an approach, pause for adversarial review before moving to detailed design.
Surface assumptions:
Identify failure modes:
Steel-man an alternative:
Gate question:
"These are the risks I see. Do they change your preference, or should we proceed with the chosen approach?"
Only move to detailed design after the user confirms. This is one gate, not a debate: if the user says "proceed," proceed.
Break into digestible sections. After each, ask:
"Does this look right so far?"
Cover as relevant:
Maintain a running log throughout:
| Decision | Alternatives | Rationale |
|---|---|---|
| ... | ... | ... |
Once validated, persist outputs:
# Record key decisions
ctx decision add "..." \
--session-id ID --branch BR --commit HASH \
--context "..." --rationale "..." --consequence "..."
Only after documentation, ask:
"Ready to begin implementation?"
If yes:
Understanding Summary:
- Building a cooldown mechanism for
ctx agenthooks- Prevents repetitive context injection on every tool use
- For Claude Code users running ctx in PreToolUse hooks
- Must be session-isolated (two sessions share no state)
- Non-goal: per-tool granularity (cooldown is global)
Assumptions: 10-minute default cooldown is reasonable.
Open Questions: none remaining.
Does this accurately reflect your intent?
Exit brainstorming mode only when:
.context/DECISIONS.mdIf any criterion is unmet, continue refinement.