By nielspac177
Write or scaffold one ~30-40pp LaTeX volume of a line-by-line neuroimaging-codebase teaching book (FreeSurfer, FSL, SPM, AFNI, ITK, ANTs, niivue, and more), quoting every listing verbatim from a local clone at real file:line numbers.
A Claude Code plugin that packages the internals-book-volume skill: a workflow for
writing one volume at a time of a line-by-line, beginner-friendly teaching book about a
real open-source neuroimaging codebase (FreeSurfer, FSL, SPM, AFNI, ITK, ANTs, niivue,
and the rest of the program). Each volume is a ~30–40pp A4 LaTeX PDF that walks through a
representative program function by function, quoting every listing verbatim from a
local git clone with real file:line numbers, and teaching the underlying language
(C, C++, Python, MATLAB, R, TypeScript) from scratch.
plugins/internals-book-volume/
├── .claude-plugin/plugin.json # plugin manifest
├── skills/internals-book-volume/ # the skill (SKILL.md + assets/ + reference/)
└── commands/internals-book-volume.md # the /internals-book-volume slash command
SERIES.md + shared preamble.tex), write the next ☐
volume against the real clone, grep a LaTeX-pitfalls checklist, build with pdflatex
twice, and flip the volume's status in the roadmaps./internals-book-volume [series] invokes the skill explicitly.From inside Claude Code, add this repo as a plugin marketplace and install:
/plugin marketplace add <your-github-user>/<this-repo>
/plugin install internals-book-volume@neuroimaging-internals
(Or, for local testing before pushing: /plugin marketplace add /Volumes/Niels_mac/Cpp_imaging/internals-book-volume-plugin.)
The skill is a plain folder, so you can also just drop it straight into your skills dir:
git clone <this-repo> /tmp/nbi
cp -R /tmp/nbi/plugins/internals-book-volume/skills/internals-book-volume \
~/.claude/skills/internals-book-volume
MCP has no "skill" primitive, so the skill can't be an MCP skill. Instead, the bundled
server at plugins/internals-book-volume/mcp/server.py exposes the same content through
MCP primitives, for use from any MCP client (Claude Desktop, IDEs, etc.):
internals_book_volume (optional series argument) that injects the full
workflow, andinternals://preamble, internals://main-template,
internals://conventions, internals://latex-pitfalls, internals://skill — serving
the template and reference files verbatim.It runs via uv with inline (PEP 723) dependencies, so no
manual install is needed. Self-check:
uv run --script plugins/internals-book-volume/mcp/server.py --selfcheck
Register in Claude Code (user scope, absolute path):
claude mcp add internals-book-volume -s user -- \
uv run --script /abs/path/to/plugins/internals-book-volume/mcp/server.py
Or project scope — open this repo as your project and Claude Code picks up the
included .mcp.json automatically.
Claude Desktop — add to claude_desktop_config.json:
{
"mcpServers": {
"internals-book-volume": {
"command": "uv",
"args": ["run", "--script", "/abs/path/to/plugins/internals-book-volume/mcp/server.py"]
}
}
}
Requires uv on PATH.
pdflatex) with the tcolorbox, tikz, listings, fancyhdr,
titlesec, and microtype packages.git (for the shallow source clones)./Volumes/Niels_mac/Cpp_imaging; adjust paths in the
skill if you relocate it.Choose one (e.g. MIT) before publishing.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub nielspac177/internals-book-volume --plugin internals-book-volumeComprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Write feature specs, plan roadmaps, and synthesize user research faster. Keep stakeholders updated and stay ahead of the competitive landscape.