スキル一覧に戻る

brahma-bhaga

pjt222
更新日 2 days ago
8 閲覧
17
2
17
GitHubで表示
メタaidesign

について

このスキルは、あいまいな状態から創造的な発想を生み出し、体系的な創造を可能にします。それは、古くなった概念を整理した後や、既存のテンプレートが存在しない新たな問題に直面した際に使用するように設計されています。その中核的な能力は、萌芽的なアイデアを初期段階から育成・促進し、新たなデザインアプローチを提供することにあります。

クイックインストール

Claude Code

推奨
メイン
npx skills add pjt222/agent-almanac -a claude-code
プラグインコマンド代替
/plugin add https://github.com/pjt222/agent-almanac
Git クローン代替
git clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/brahma-bhaga

このコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします

ドキュメント

Brahma Bhaga

Generative creation from void or ambiguity — structured emergence of new patterns, approaches, solutions where none existed before.

When Use

  • After shiva-bhaga dissolution cleared stale patterns, created space
  • Facing genuinely novel problem — no obvious template or precedent
  • User's request requires invention rather than retrieval or adaptation
  • Multiple approaches exist, none chosen — creative act is the choice itself
  • Blank slate: new file, new project, new architecture, new approach
  • Incremental modification has reached limits — fresh design needed

Inputs

  • Required: Creative goal or void to fill (from conversation context)
  • Optional: Constraints bounding creation (user requirements, technical limitations)
  • Optional: Seeds — fragments, inspirations, partial ideas informing creation
  • Optional: What was dissolved (shiva-bhaga output) — understanding what failed guides what to create

Steps

Step 1: Survey the Void

Before creating, understand space available for creation.

Creative Space Assessment:
+---------------------+---------------------------+------------------------+
| Dimension           | Questions                 | Determines             |
+---------------------+---------------------------+------------------------+
| Constraints         | What MUST the creation    | The boundary within    |
|                     | satisfy? What is non-     | which creativity       |
|                     | negotiable?               | operates               |
+---------------------+---------------------------+------------------------+
| Freedom             | What is NOT specified?     | The degrees of freedom |
|                     | Where does the user leave | available for creative |
|                     | room for creative choice? | choice                 |
+---------------------+---------------------------+------------------------+
| Seeds               | What fragments, partial   | The starting material  |
|                     | ideas, or inspirations    | that informs but does  |
|                     | already exist?            | not dictate            |
+---------------------+---------------------------+------------------------+
| Anti-patterns       | What was tried before and | The space to avoid —   |
|                     | failed? What approaches   | creation that repeats  |
|                     | were dissolved?           | dissolved patterns     |
+---------------------+---------------------------+------------------------+
| Context             | What exists around the    | The environment the    |
|                     | void? What must the       | creation must fit      |
|                     | creation integrate with?  | into                   |
+---------------------+---------------------------+------------------------+
  1. Map each dimension honestly — especially constraints, often implicit
  2. Note degrees of freedom: where genuine creation happens
  3. Identify seeds without committing to them — they inform, not dictate

Got: Clear picture of creative space: bounded by constraints, informed by seeds, opened by degrees of freedom.

If fail: Space feels fully constrained (no degrees of freedom)? Re-examine — constraints that seem fixed are often preferences. Ask user if needed.

Step 2: Generate — Divergent Exploration

Produce multiple possibilities without evaluating.

  1. Generate at least three distinct approaches to fill creative space
  2. Each approach genuinely different — not variations on a theme
  3. For each approach, capture:
    • Core idea in one sentence
    • How it satisfies constraints
    • What makes it distinct from others
    • What it sacrifices or trades off
  4. Include at least one unconventional or risky approach
  5. Do not evaluate yet — generation and evaluation are separate phases

Got: Three or more genuinely distinct approaches, each with clear identity and trade-off profile.

If fail: All approaches feel similar? Generation too narrow. Return to Step 1, look for unexplored degrees of freedom. Alternatively, invert a constraint: "What if opposite of the obvious approach?"

Step 3: Evaluate — Convergent Selection

Assess generated approaches vs creative space.

  1. For each approach, assess:
    • Constraint satisfaction: Meets all non-negotiable requirements?
    • Elegance: Simplest solution that works?
    • Resilience: Survives future perturbation?
    • Integration: Fits naturally with surrounding context?
    • Novelty: Brings something genuinely new, or merely rearranges old?
  2. Eliminate approaches violating hard constraints
  3. Among remaining approaches, choose from user's implicit values (simplicity? thoroughness? creativity?)
  4. Two approaches equally strong? Present both to user with trade-offs clearly stated

Got: Single chosen approach (or clearly framed choice for user) with articulated reasoning.

If fail: No approach satisfies all constraints? Constraints may be contradictory. Surface contradiction to user rather than forcing creation that compromises fundamentals.

Step 4: Manifest — Bring into Form

Execute chosen approach, give concrete form.

  1. Begin with skeleton: minimal structure embodying core idea
  2. Build outward from core, adding detail as needed
  3. At each step, check: "Does this addition serve core idea or dilute it?"
  4. Resist urge to over-elaborate — creation complete when nothing more can be removed
  5. Name what was created: clear, descriptive identifier capturing its essence

Got: Concrete creation embodying chosen approach — code, plan, structure, or design existing where void was before.

If fail: Manifestation diverges from chosen approach? Pause, re-read Step 3's selection. Drift during manifestation often signals selection not fully committed to. Either recommit or re-select.

Step 5: Nurture — Protect the Nascent Creation

New creations fragile. Protect them through early stages.

  1. Test creation vs its constraints — works as intended?
  2. Identify weakest point — where most likely to break?
  3. Strengthen weakest point without over-engineering
  4. Hand off to vishnu-bhaga for ongoing preservation if creation will persist
  5. Document creative choices made: what was chosen, what was rejected, why

Got: Creation tested, documented, ready for sustained use.

If fail: Creation fails first test? Assess whether failure is in creation or test. Creation fundamentally flawed? Return to Step 2 with failure as new anti-pattern seed.

Checks

  • Creative space surveyed before generating ideas
  • At least three genuinely distinct approaches generated
  • Selection based on explicit criteria, not default instinct
  • Creation manifested starting from core, building outward
  • Creation tested vs its constraints
  • Creative choices documented for future reference

Pitfalls

  • Creating before clearing: Attempting creation without prior dissolution produces new patterns contaminated by old ones. Run shiva-bhaga first if space is cluttered
  • Single-option generation: Generating one approach then evaluating it is not creation — it's executing first idea. True creation requires divergent options
  • Novelty for its own sake: Creating something unconventional when simple standard approach would serve better. Novelty is tool, not goal
  • Perfectionist manifestation: Polishing endlessly rather than shipping working creation. Complete imperfect creation outperforms incomplete perfect one
  • Unprotected creation: Manifesting something new and immediately moving on without testing or documentation leaves creation vulnerable

See Also

  • shiva-bhaga — destruction creates void Brahma fills; dissolution precedes creation
  • vishnu-bhaga — preservation sustains what Brahma creates; handoff from creation to maintenance
  • intrinsic — creative engagement benefits from autonomous motivation; creation thrives in flow
  • learn — creation requiring knowledge not yet held? Learning precedes generation
  • adapt-architecture — morphic equivalent for creating new architectural patterns from existing systems

GitHub リポジトリ

pjt222/agent-almanac
パス: i18n/caveman/skills/brahma-bhaga
0
agentsagentskillsai-assisted-developmentclaude-codeskillsteams

関連スキル

content-collections

メタ

このスキルは、Content Collections(Markdown/MDXファイルを型安全なデータコレクションに変換するTypeScriptファーストのツール)の本番環境でテストされた設定を提供します。Zodバリデーションによる型安全性を実現し、ブログ、ドキュメントサイト、コンテンツ重視のVite + Reactアプリケーション構築時にご利用ください。Viteプラグインの設定、MDXコンパイルから、デプロイ最適化、スキーマバリデーションまで、すべてを網羅しています。

スキルを見る

polymarket

メタ

このスキルは、開発者がPolymarket予測市場プラットフォームを活用したアプリケーション構築を可能にします。API統合による取引や市場データの取得に加え、WebSocketを介したリアルタイムデータストリーミングにより、ライブ取引や市場活動を監視できます。取引戦略の実装や、ライブ市場更新を処理するツールの作成にご利用ください。

スキルを見る

creating-opencode-plugins

メタ

このスキルは、開発者がコマンド、ファイル、LSP操作など25種類以上のイベントタイプにフックするOpenCodeプラグインを作成することを支援します。JavaScript/TypeScriptモジュール向けに、プラグイン構造、イベントAPI仕様、および実装パターンを提供します。カスタムイベント駆動ロジックでOpenCode AIアシスタントのライフサイクルをインターセプト、監視、または拡張する必要がある場合にご利用ください。

スキルを見る

sglang

メタ

SGLangは、高性能なLLMサービングフレームワークであり、RadixAttentionプレフィックスキャッシュを活用したJSON、正規表現、エージェントワークフロー向けの高速で構造化された生成を特長とします。特にプレフィックスが繰り返されるタスクにおいて、大幅に高速な推論を実現し、複雑な構造化出力やマルチターン対話に最適です。制約付きデコードが必要な場合や、広範なプレフィックス共有を伴うアプリケーションを構築する場合は、vLLMなどの代替案ではなくSGLangを選択してください。

スキルを見る