brahma-bhaga
Creation and genesis — generative ideation from void, structured emergence from ambiguity, and the discipline of bringing new patterns into existence. Maps Brahma's creative power to AI reasoning: transforming cleared space into coherent new structures, seeding possibilities, and nurturing nascent ideas through their fragile early stages. Use after shiva-bhaga dissolution has cleared stale patterns, when facing a genuinely novel problem with no obvious template, or when incremental modification has reached its limits and a fresh design is needed.
Best use case
brahma-bhaga is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Creation and genesis — generative ideation from void, structured emergence from ambiguity, and the discipline of bringing new patterns into existence. Maps Brahma's creative power to AI reasoning: transforming cleared space into coherent new structures, seeding possibilities, and nurturing nascent ideas through their fragile early stages. Use after shiva-bhaga dissolution has cleared stale patterns, when facing a genuinely novel problem with no obvious template, or when incremental modification has reached its limits and a fresh design is needed.
Teams using brahma-bhaga should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/brahma-bhaga/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How brahma-bhaga Compares
| Feature / Agent | brahma-bhaga | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Creation and genesis — generative ideation from void, structured emergence from ambiguity, and the discipline of bringing new patterns into existence. Maps Brahma's creative power to AI reasoning: transforming cleared space into coherent new structures, seeding possibilities, and nurturing nascent ideas through their fragile early stages. Use after shiva-bhaga dissolution has cleared stale patterns, when facing a genuinely novel problem with no obvious template, or when incremental modification has reached its limits and a fresh design is needed.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Brahma Bhaga Generative creation from void or ambiguity — structured emergence of new patterns, approaches, and solutions where none existed before. ## When to Use - After `shiva-bhaga` dissolution has cleared stale patterns and created space - Facing a genuinely novel problem with no obvious template or precedent - The user's request requires invention rather than retrieval or adaptation - Multiple possible approaches exist and none has been chosen — the creative act is the choice itself - A blank slate: new file, new project, new architecture, new approach - When incremental modification has reached its limits and a fresh design is needed ## Inputs - **Required**: The creative goal or void to fill (available from conversation context) - **Optional**: Constraints that bound the creation (user requirements, technical limitations) - **Optional**: Seeds — fragments, inspirations, or partial ideas that inform the creation - **Optional**: What was dissolved (`shiva-bhaga` output) — understanding what failed guides what to create ## Procedure ### Step 1: Survey the Void Before creating, understand the 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, which are often implicit 2. Note the degrees of freedom: these are where genuine creation happens 3. Identify seeds without committing to them — they inform, not dictate **Got:** A clear picture of the creative space: bounded by constraints, informed by seeds, and opened by degrees of freedom. **If fail:** If the space feels fully constrained (no degrees of freedom), re-examine — often constraints that seem fixed are preferences. Ask the user if needed. ### Step 2: Generate — Divergent Exploration Produce multiple possibilities without evaluating them. 1. Generate at least three distinct approaches to filling the creative space 2. Each approach should be genuinely different — not variations on a theme 3. For each approach, capture: - The core idea in one sentence - How it satisfies the constraints - What makes it distinct from the others - What it sacrifices or trades off 4. Include at least one approach that feels unconventional or risky 5. Do not evaluate yet — generation and evaluation are separate phases **Got:** Three or more genuinely distinct approaches, each with a clear identity and trade-off profile. **If fail:** If all approaches feel similar, the generation was too narrow. Return to Step 1 and look for unexplored degrees of freedom. Alternatively, invert a constraint: "What if I did the opposite of the obvious approach?" ### Step 3: Evaluate — Convergent Selection Assess the generated approaches against the creative space. 1. For each approach, assess: - **Constraint satisfaction**: Does it meet all non-negotiable requirements? - **Elegance**: Is it the simplest solution that works? - **Resilience**: Will it survive future perturbation? - **Integration**: Does it fit naturally with the surrounding context? - **Novelty**: Does it bring something genuinely new, or merely rearrange the old? 2. Eliminate approaches that violate hard constraints 3. Among remaining approaches, choose based on the user's implicit values (simplicity? thoroughness? creativity?) 4. If two approaches are equally strong, present both to the user with trade-offs clearly stated **Got:** A single chosen approach (or a clearly framed choice for the user) with articulated reasoning. **If fail:** If no approach satisfies all constraints, the constraints may be contradictory. Surface the contradiction to the user rather than forcing a creation that compromises on fundamentals. ### Step 4: Manifest — Bring into Form Execute the chosen approach, giving it concrete form. 1. Begin with the skeleton: the minimal structure that embodies the core idea 2. Build outward from the core, adding detail as needed 3. At each step, check: "Is this addition serving the core idea or diluting it?" 4. Resist the urge to over-elaborate — creation is complete when nothing more can be removed 5. Name what was created: a clear, descriptive identifier that captures its essence **Got:** A concrete creation that embodies the chosen approach — code, plan, structure, or design that exists where void existed before. **If fail:** If the manifestation diverges from the chosen approach, pause and re-read Step 3's selection. Drift during manifestation often indicates the selection was not fully committed to. Either recommit or re-select. ### Step 5: Nurture — Protect the Nascent Creation New creations are fragile. Protect them through their early stages. 1. Test the creation against its constraints — does it work as intended? 2. Identify the weakest point — where is it most likely to break? 3. Strengthen the weakest point without over-engineering 4. Hand off to `vishnu-bhaga` for ongoing preservation if the creation will persist 5. Document the creative choices made: what was chosen, what was rejected, and why **Got:** A creation that is tested, documented, and ready for sustained use. **If fail:** If the creation fails its first test, assess whether the failure is in the creation or the test. If the creation is fundamentally flawed, return to Step 2 with the failure as a new anti-pattern seed. ## Validation - [ ] The creative space was surveyed before generating ideas - [ ] At least three genuinely distinct approaches were generated - [ ] Selection was based on explicit criteria, not default instinct - [ ] The creation was manifested starting from its core, building outward - [ ] The creation was tested against its constraints - [ ] Creative choices were 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 the space is cluttered - **Single-option generation**: Generating one approach and then evaluating it is not creation — it is executing the first idea. True creation requires divergent options - **Novelty for its own sake**: Creating something unconventional when a simple standard approach would serve better. Novelty is a tool, not a goal - **Perfectionist manifestation**: Polishing endlessly rather than shipping a working creation. A complete imperfect creation outperforms an incomplete perfect one - **Unprotected creation**: Manifesting something new and immediately moving on without testing or documentation leaves the creation vulnerable ## Related Skills - `shiva-bhaga` — destruction creates the void that 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` — when creation requires knowledge not yet held, learning precedes generation - `adapt-architecture` — the morphic equivalent for creating new architectural patterns from existing systems
Related Skills
vishnu-bhaga
Preservation and sustenance — maintaining working state under perturbation, memory anchoring, consistency enforcement, and protective stabilization. Maps Vishnu's sustaining presence to AI reasoning: holding what works steady, anchoring verified knowledge against drift, and ensuring continuity through change. Use when a working approach is at risk from scope creep, when context drift threatens verified knowledge, after shiva-bhaga dissolution to protect what survived, when a long session risks losing earlier decisions through context compression, or before making changes to a currently functioning system.
shiva-bhaga
Destruction and dissolution — controlled dismantling of stale patterns, context purging, assumption clearing, and dead-code elimination. Maps Shiva's transformative destruction to AI reasoning: identifying what must end so something better can begin, dissolving attachment to outdated approaches, and creating space through intentional release. Use when context has accumulated stale assumptions, when a failed approach needs to be discarded rather than patched, when dead code or zombie tasks are creating noise, or before a major pivot where clearing must precede creation.
skill-name-here
One to three sentences describing what this skill accomplishes, followed by key activation triggers. This field is the primary mechanism agents use to decide whether to activate the skill — it is read during discovery before the full body is loaded. Start with a verb. Include the most important "when to use" conditions inline. Max 1024 characters.
write-vignette
Create R package vignettes using R Markdown or Quarto. Covers vignette setup, YAML configuration, code chunk options, building and testing, and CRAN requirements for vignettes. Use when adding a Getting Started tutorial, documenting complex workflows spanning multiple functions, creating domain-specific guides, or when CRAN submission requires user-facing documentation beyond function help pages.
write-validation-documentation
Write IQ/OQ/PQ validation documentation for computerized systems in regulated environments. Covers protocols, reports, test scripts, deviation handling, and approval workflows. Use when validating R or other software for regulated use, preparing for a regulatory audit, documenting qualification of computing environments, or creating and updating validation protocols and reports for new or re-qualified systems.
write-testthat-tests
Write comprehensive testthat (edition 3) tests for R package functions. Covers test organization, expectations, fixtures, mocking, snapshot tests, parameterized tests, and achieving high coverage. Use when adding tests for new package functions, increasing test coverage for existing code, writing regression tests for bug fixes, or setting up test infrastructure for a package that lacks it.
write-standard-operating-procedure
Write a GxP-compliant Standard Operating Procedure (SOP). Covers regulatory SOP template structure (purpose, scope, definitions, responsibilities, procedure, references, revision history), approval workflow design, periodic review scheduling, and operational procedures for system use. Use when a new validated system requires operational procedures, when existing informal procedures need formalisation, when an audit finding cites missing procedures, when a change control triggers SOP updates, or when periodic review identifies outdated procedural content.
write-roxygen-docs
Write roxygen2 documentation for R package functions, datasets, and classes. Covers all standard tags, cross-references, examples, and generating NAMESPACE entries. Follows tidyverse documentation style. Use when adding documentation to new exported functions, documenting internal helpers or datasets, documenting S3/S4/R6 classes and methods, or fixing documentation-related R CMD check notes.
write-incident-runbook
Create structured incident runbooks with diagnostic steps, resolution procedures, escalation paths, and communication templates for effective incident response. Use when documenting response procedures for recurring alerts, standardizing incident response across an on-call rotation, reducing MTTR with clear diagnostic steps, creating training materials for new team members, or linking alert annotations directly to resolution procedures.
write-helm-chart
Create production-ready Helm charts for Kubernetes application deployment with templating, values management, chart dependencies, hooks, and testing. Covers chart structure, Go template syntax, values.yaml design, chart repositories, versioning, and best practices for maintainable and reusable charts. Use when packaging a Kubernetes application for repeatable deployments, parameterizing manifests for multiple environments, managing complex multi-component applications with dependencies, or standardizing deployment practices with versioned rollback capability across teams.
write-continue-here
Write a CONTINUE_HERE.md file capturing current session state so a fresh Claude Code session can pick up where this one left off. Covers assessing recent work, structuring the continuation file with objective, completed, in-progress, next-steps, and context sections, and verifying the file is actionable. Use when ending a session with unfinished work, handing off context between sessions, or preserving task state that git alone cannot capture.
write-claude-md
Create an effective CLAUDE.md file that provides project-specific instructions to AI coding assistants. Covers structure, common sections, do/don't patterns, and integration with MCP servers and agent definitions. Use when starting a new project where AI assistants will be used, improving AI behavior on an existing project, documenting project conventions and constraints, or integrating MCP servers or agent definitions into a project workflow.