braininahat

braininahat/brains-in-a-hat

Plugin Claude Code

AI agents for Claude Code — team orchestration with Obsidian memory and publication-quality figures.

braininahat/brains-in-a-hat

Plugin Claude Code

Publication-quality scientific visualization — ML architecture diagrams, TikZ rendering, Typst reports, and data plots following petarv/janosh visual principles.

braininahat/brains-in-a-hat

Agent

Use this agent to review figures for publication quality. Checks semantic color usage, dimensionality representation, mathematical notation, grid alignment, and adherence to petarv/janosh principles. Use after creating or modifying diagrams.

braininahat/brains-in-a-hat

Agent

Use this agent when the user asks to "draw an architecture diagram", "visualize this model", "create a figure for the paper", or describes a system they want diagrammed. Creates publication-quality diagrams using fletcher (architectural) or TikZ (dimensional) based on the description.

braininahat/brains-in-a-hat

Command

Create a publication-quality diagram from a description.

braininahat/brains-in-a-hat

Command

Compile all .tex and .typ figure files in a directory.

braininahat/brains-in-a-hat

Skill Claude CodeCodex

This skill should be used when the user asks to "create an architecture diagram", "draw a figure for the paper", "make a publication-quality diagram", "visualize the model architecture", "diagram the pipeline", "typst diagram", "fletcher diagram", or needs scientific figures in Typst following petarv/janosh visual…

braininahat/brains-in-a-hat

Skill Claude CodeCodex

This skill should be used when the user asks to "combine figures", "make a figure panel", "arrange subfigures", "create a composite figure", or needs to lay out multiple SVGs/PDFs into a grid for a paper figure.

braininahat/brains-in-a-hat

Skill Claude CodeCodex

This skill should be used when the user asks to "create a plot", "make a chart for the paper", "visualize metrics", "plot training curves", "render an ablation table as a figure", or needs matplotlib/plotly figures exported as SVG for embedding in Typst reports.

braininahat/brains-in-a-hat

Skill Claude CodeCodex

This skill should be used when the user wants to "render a TikZ diagram", "compile LaTeX to SVG", "create an architecture diagram", "draw a neural network figure", "convert .tex to SVG", "use PetarV diagrams", "use nntikz", or asks to draw any specific architecture (BiGRU, BiMamba, JEPA, KAN, CTC trellis, ST-GCN…

braininahat/brains-in-a-hat

Skill Claude CodeCodex

This skill should be used when the user asks to "create a report", "write a Typst report", "generate a research report", "make a PDF report", or needs a full document with mixed diagram types (fletcher + TikZ SVG). Provides report templates and the @local/diagrams integration pattern.

braininahat/brains-in-a-hat

Plugin Claude Code

5-agent Claude Code team with closed-loop self-improvement, Obsidian-synced external memory, multi-repo project constellations.

braininahat/brains-in-a-hat

Agent

On-demand design and blueprint teammate. Spawned when team-lead needs a system design, component contract, or architecture audit produced before Builder starts writing code. Wright produces a structured blueprint (interfaces, data-flow, dependency graph, invariants) and an architecture audit of existing code when…

braininahat/brains-in-a-hat

Agent

On-demand implementation teammate. Spawned by team-lead when there's a bounded, well-specified piece of code to write — feature work, refactors, tests, scripts. Replaces the entire previous domain-specialist fleet (packaging, devops, docs-writer, mlops, signal-processing, hardware-device, qt-qml) by reading the…

braininahat/brains-in-a-hat

Agent

On-demand reviewer with switchable lenses. Replaces the entire previous reviewer fleet (architect, ui-reviewer, ux-workflow, profiler, qa-engineer, system-designer, testing-strategy, data-schema) with a single agent that switches its review perspective by lens= parameter rather than spawning N specialists. Lenses…

braininahat/brains-in-a-hat

Agent

Vault-only storage and retrieval layer for the brains-in-a-hat memory system. Lazy-spawned the first time a cross-repo learning, a decision worth an ADR, a wiki concept, or a session-journal entry needs recording — or the first time team-lead needs a vault recall. Per-repo learnings and user preferences are NOT…

braininahat/brains-in-a-hat

Agent

On-demand research teammate. Spawned when team-lead needs information from outside the codebase — library documentation, API current state, framework comparisons, paper references, security advisories, version migration paths. Replaces the previous researcher + domain-expert agents. Scout's specialty is knowing when…

braininahat/brains-in-a-hat

Hook

Runs when you submit a prompt, before the agent sees it, running an inline shell check. From braininahat/brains-in-a-hat.

braininahat/brains-in-a-hat

Hook

Runs when a session starts, executing run-hook.cmd. From braininahat/brains-in-a-hat.

braininahat/brains-in-a-hat

Hook

Runs when a session ends, running an inline shell check. From braininahat/brains-in-a-hat.

braininahat/brains-in-a-hat

Hook

Runs before the context is compacted, running an inline shell check. From braininahat/brains-in-a-hat.

braininahat/brains-in-a-hat

Hook

Runs when a subagent starts, running an inline shell check (2 commands). From braininahat/brains-in-a-hat.

braininahat/brains-in-a-hat

Hook

Runs on the TeammateIdle event, running an inline shell check. From braininahat/brains-in-a-hat.

braininahat/brains-in-a-hat

Hook

Runs when a subagent finishes, running an inline shell check. From braininahat/brains-in-a-hat.