brahma-bhaga
About
This skill enables generative ideation and structured creation from ambiguity, transforming cleared space into coherent new patterns. It is designed for use after clearing stale concepts or when facing novel problems without existing templates. Its core capability is to seed and nurture nascent ideas through their early stages, providing a fresh design approach.
Quick Install
Claude Code
Recommendednpx skills add pjt222/agent-almanac -a claude-code/plugin add https://github.com/pjt222/agent-almanacgit clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/brahma-bhagaCopy and paste this command in Claude Code to install this skill
Documentation
Brahma Bhaga
Generative creation from void or ambiguity — structured emergence of new patterns, approaches, solutions where none existed before.
When Use
- After
shiva-bhagadissolution 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-bhagaoutput) — 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 |
+---------------------+---------------------------+------------------------+
- Map each dimension honestly — especially constraints, often implicit
- Note degrees of freedom: where genuine creation happens
- 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.
- Generate at least three distinct approaches to fill creative space
- Each approach genuinely different — not variations on a theme
- 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
- Include at least one unconventional or risky approach
- 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.
- 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?
- Eliminate approaches violating hard constraints
- Among remaining approaches, choose from user's implicit values (simplicity? thoroughness? creativity?)
- 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.
- Begin with skeleton: minimal structure embodying core idea
- Build outward from core, adding detail as needed
- At each step, check: "Does this addition serve core idea or dilute it?"
- Resist urge to over-elaborate — creation complete when nothing more can be removed
- 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.
- Test creation vs its constraints — works as intended?
- Identify weakest point — where most likely to break?
- Strengthen weakest point without over-engineering
- Hand off to
vishnu-bhagafor ongoing preservation if creation will persist - 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-bhagafirst 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 creationvishnu-bhaga— preservation sustains what Brahma creates; handoff from creation to maintenanceintrinsic— creative engagement benefits from autonomous motivation; creation thrives in flowlearn— creation requiring knowledge not yet held? Learning precedes generationadapt-architecture— morphic equivalent for creating new architectural patterns from existing systems
GitHub Repository
Related Skills
content-collections
MetaThis 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.
polymarket
MetaThis 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.
creating-opencode-plugins
MetaThis 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.
sglang
MetaSGLang 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.
