explainer plugin
Five-skill plugin that writes explanations for one reader and checks figures and diagrams by running code, not model memory.
- 461 ★ on the repository
- Last commit
Extended access
Why this level
- Verification scripts run Node and a Playwright browser over your documents, and dependencies install through npm.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add plugins/explainerDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Verification scripts run Node and a Playwright browser over your documents, and dependencies install through npm.
This is third-party code. Review the repository files before installing.
What it does
The `explainer` plugin for Claude Code bundles five skills for explaining concepts from an AI to a person. `explainer` writes a short course for one specific reader: a persona fixes what that reader already knows, so only new material reaches the text. `explainer-book` builds a chaptered course and checks learning objectives, concept order and reading time. `first-reader` runs a draft past simulated readers one paragraph at a time and notes where they drop off; it does not rewrite. `d2-diagram` and `d2-slides` draw D2 diagrams and build slides from one Markdown file. Quoted command output is re-run from `checks.json`, and diagrams are checked by `figure-check.mjs`.
Who it is for. Developers and technical writers whose agent drafts an explainer or learning material and who cannot hand-check every claim.
Good fit when
- A crash course on an unfamiliar topic is needed for one colleague.
- A draft article should be read through a reader's eyes before publishing.
- The text quotes program output that has to match a real run.
- Slides with D2 diagrams must be built from one Markdown file.
Not a fit when
- The text is for a broad audience with no specific reader.
- Node-based checks are unavailable and the numbers do not matter.
- Documents are in Japanese and `yomiyasu` is not an option.
Example request
Explain TLA+ to a backend colleague with verified examples and a diagram. Then run the draft through first-reader.Limitations
Verification scripts run on Node 24 or newer and need `@mizchi/vlmkit`, `marked`, `playwright` and `mermaid`; D2 diagrams add the `d2` CLI. Install `explainer`, `explainer-book` and `first-reader` together because the book skill calls a sibling script. README figures are in Japanese, and the animation package was removed in 0.5. Japanese text checks need a separate `yomiyasu`. For Japanese documents the check relies on a separate linter, and the README lists no dedicated check for Russian.
How to disable. Run `/plugin uninstall explainer@explainer` and optionally drop the marketplace with `/plugin marketplace remove explainer`. Dependencies added with `npm i -D` are removed separately in the documents repository.
FAQ
How does `explainer` differ from `explainer-book`?
`explainer` writes one short course, `explainer-book` builds a chaptered one. The book skill checks learning objectives, concept order, reading time and exercises.
Does `first-reader` edit the text?
No. It only reports where a simulated reader loses the thread and what sticks the next day. The author makes the fixes.
How do I update an installed plugin?
Run `claude plugin marketplace update explainer`, then `claude plugin update explainer@explainer`. Changes are listed in `CHANGELOG.md`.
Can it be installed without Claude Code plugins?
Yes. `npx skills add mizchi/explainer --skill '*' -a claude-code` or `apm install mizchi/explainer --target claude` put the same skills into `.claude/skills/`.
Which diagrams does verification support?
Mermaid and D2, plus SVG and HTML. `figure-check.mjs` compares a diagram with a fact sheet and looks for overlap, clipping and unreadable arrows.
Discussion
No questions or reviews yet.
Related
PluginsMicrosoft's utility and MCP server that turn PDF, Word, Excel, PowerPoint, HTML and other files into Markdown for models
Anthropic skills
Skills
Anthropic's official skill examples: docx, pdf, pptx and xlsx documents, design, MCP builder and the Agent Skills spec
A skill that draws validated architecture, workflow, sequence and data-flow diagrams as one interactive HTML file
PaddleOCR agent skills
PaddleOCR Agent Skills
Two official PaddleOCR skills: text recognition from images and PDFs, and parsing complex documents into Markdown
MinerU is a CLI with a document library: search and revisit an already parsed report using its local cache.
Tesseract OCR is a CLI for multilingual scans: select language datasets and compare recognition on a sample page.
README in short
The repository is its own marketplace with one plugin holding five skills. The principle: write for one reader only what they do not know, and check claims and figures with tools.