Back to Skills

brahma-bhaga

pjt222
Updated 6 days ago
18 views
17
2
17
View on GitHub
Metaaidesign

About

The `brahma-bhaga` skill is for generative ideation, creating coherent new structures and patterns from ambiguity or cleared conceptual space. It seeds possibilities and nurtures nascent ideas, applying Brahma's creative power to AI reasoning. Use it after a dissolution phase or when facing a novel problem where incremental changes are insufficient and a fresh design is needed.

Quick Install

Claude Code

Recommended
Primary
npx skills add pjt222/agent-almanac -a claude-code
Plugin CommandAlternative
/plugin add https://github.com/pjt222/agent-almanac
Git CloneAlternative
git clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/brahma-bhaga

Copy and paste this command in Claude Code to install this skill

Documentation

梵天之分

自虛或模糊之生——新模、法、解之結構化湧現,前所未有者。

用時

  • shiva-bhaga 溶盡陳模,空已闢
  • 遇真新之題而無明範或先例
  • 用者之請須創而非索或改
  • 諸法皆可而未擇——創之行即擇本身
  • 白板:新檔、新項、新架、新法
  • 增改已至其限而須新設

  • 必要:創之旨或待填之虛(對話脈絡可得)
  • 可選:限(用者要求、技術限制)
  • 可選:種子——碎片、啟示、或半念供創
  • 可選:所溶者(shiva-bhaga 之出)——知昔何敗引今何創

第一步:察虛

創之前,識可創之空。

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. 實繪諸維——尤其限,常為隱
  2. 記由之度:真創生於此
  3. 識種子而不拘之——其供而不命

得: 創之空清象:限為界、種為供、由度為開。

敗則: 若空似全限(無由度),重察——似定之限常實為好。若須,問用者。

第二步:生——發散探索

生諸可而未評。

  1. 至少生三具別之法以填創空
  2. 各法宜真異——非同題之變
  3. 各法記:
    • 核念一句
    • 如何合限
    • 異於他法之處
    • 捨與換
  4. 含至少一不常或冒險之法
  5. 勿評——生與評為別階

得: 三或多真異之法,各有清身與捨換之貌。

敗則: 若諸法皆似,生太狹。返第一步尋未探之由度。或反一限:「若反明法何如?」

第三步:評——收斂擇

評所生之法於創空。

  1. 各法評:
    • 限合:合諸硬要求乎?
    • :為成之最簡乎?
    • :能歷後擾乎?
    • :自然合周脈乎?
    • :帶真新乎,抑只排舊?
  2. 刪犯硬限者
  3. 餘法中依用者隱值擇(簡?徹?創?)
  4. 若二法等強,並呈用者,明列捨換

得: 一擇之法(或為用者明框之擇),附清理。

敗則: 若無法合諸限,限或相悖。浮悖於用者而非強創折中於根本。

第四步:成——予以形

行所擇之法,賦之具體形。

  1. 始於骨架:體核念之最簡結構
  2. 自核外建,須處增詳
  3. 各步察:「此增助核念乎,抑稀之?」
  4. 拒過繁——創成於不可復減
  5. 名所創:清述之識,捕其本質

得: 具體之創,體所擇之法——碼、計、構、或設,存於昔虛之處。

敗則: 若成偏離所擇之法,頓而重讀第三步之擇。成中之偏常示擇未全決。或重決或重擇。

第五步:養——護新生之創

新創脆。護其早階。

  1. 驗創於限——如意行乎?
  2. 識最弱處——何處最易破?
  3. 強最弱處而不過工
  4. 若創將持,交於 vishnu-bhaga 以續保
  5. 錄創之擇:所擇、所棄、與由

得: 已驗、已錄、備持久用之創。

敗則: 若創首試敗,察敗在創抑在試。若創根本有瑕,返第二步以敗為新反模種。

  • 生念之前已察創空
  • 至少三真異之法已生
  • 擇依明準,非默直覺
  • 創自核始成,外建之
  • 創已驗於限
  • 創之擇已錄備後用

  • 未清先創:無前溶而創生新模染於舊。空雜者宜先行 shiva-bhaga
  • 單選之生:生一法而評之非創——乃執首念。真創須發散之選
  • 為新而新:當簡標法可更善時而造不常之物。新為工具,非目
  • 完美成:拋光不止而不交可行之創。全不完之創勝於不完之全
  • 未護之創:成新即去而不驗不錄,留創於脆

  • shiva-bhaga — 滅生梵天所填之虛;溶先於創
  • vishnu-bhaga — 保持梵天所創;自創交於保
  • intrinsic — 創之參惠於自發之動;創盛於流
  • learn — 創須未持之知時,學先於生
  • adapt-architecture — 自現系生新架模式之 morphic 對照

GitHub Repository

pjt222/agent-almanac
Path: i18n/wenyan/skills/brahma-bhaga
0
agentsagentskillsai-assisted-developmentclaude-codeskillsteams

Related Skills

content-collections

Meta

This skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.

View skill

polymarket

Meta

This skill enables developers to build applications with the Polymarket prediction markets platform, including API integration for trading and market data. It also provides real-time data streaming via WebSocket to monitor live trades and market activity. Use it for implementing trading strategies or creating tools that process live market updates.

View skill

creating-opencode-plugins

Meta

This skill helps developers create OpenCode plugins that hook into 25+ event types like commands, files, and LSP operations. It provides the plugin structure, event API specifications, and implementation patterns for JavaScript/TypeScript modules. Use it when you need to intercept, monitor, or extend the OpenCode AI assistant's lifecycle with custom event-driven logic.

View skill

sglang

Meta

SGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.

View skill