MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
A skill your agent uses when working with the ranuts utility library — DOM/BOM/string/object/number/color/time helpers and reactivity from ranuts/utils (e.g.
$ npx skills add chaxus/ran --skill ranuts -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install chaxus/ran ranuts --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/chaxus/ran.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/ranuts/skills/ranuts .claude/skills/ranuts && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "ranuts" agent skill from https://github.com/chaxus/ran/tree/main/plugins/ranuts/skills/ranuts into .claude/skills/ranuts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ranuts", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/chaxus/ran/tree/main/plugins/ranuts/skills/ranutsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add chaxus/ran --skill ranuts -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install chaxus/ran ranuts --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/chaxus/ran.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/ranuts/skills/ranuts .agents/skills/ranuts && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ranuts" agent skill from https://github.com/chaxus/ran/tree/main/plugins/ranuts/skills/ranuts into .agents/skills/ranuts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ranuts", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add chaxus/ran --skill ranuts -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install chaxus/ran ranuts --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/chaxus/ran.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/ranuts/skills/ranuts .cursor/skills/ranuts && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ranuts" agent skill from https://github.com/chaxus/ran/tree/main/plugins/ranuts/skills/ranuts into .cursor/skills/ranuts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ranuts", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/chaxus/ran.git --path plugins/ranuts/skills/ranuts--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add chaxus/ran --skill ranuts -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install chaxus/ran ranuts --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/chaxus/ran.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/ranuts/skills/ranuts .gemini/skills/ranuts && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "ranuts" agent skill from https://github.com/chaxus/ran/tree/main/plugins/ranuts/skills/ranuts into .gemini/skills/ranuts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ranuts", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install chaxus/ran ranutsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add chaxus/ran --skill ranuts -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/chaxus/ran.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/ranuts/skills/ranuts .github/skills/ranuts && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "ranuts" agent skill from https://github.com/chaxus/ran/tree/main/plugins/ranuts/skills/ranuts into .github/skills/ranuts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ranuts", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add chaxus/ran --skill ranuts -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install chaxus/ran ranuts --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/chaxus/ran.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/ranuts/skills/ranuts .opencode/skills/ranuts && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ranuts" agent skill from https://github.com/chaxus/ran/tree/main/plugins/ranuts/skills/ranuts into .opencode/skills/ranuts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ranuts", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
ranutsA skill your agent uses when working with the ranuts utility library — DOM/BOM/string/object/number/color/time helpers and reactivity from ranuts/utils (e.g.
Ranuts is an agent skill from chaxus/ran. Use when working with the ranuts utility library — DOM/BOM/string/object/number/color/time helpers and reactivity from ranuts/utils (e.g. createSignal, throttle/debounce, cloneDeep, escapeHtml, getMime, MessageCodec, localStorage helpers), the node-only server toolkit ranuts/node, the 2D rendering engine ranuts/visual, or the ranuts/vnode virtual DOM. Covers the import map, inventory, conventions, and where the full function reference lives.
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It works with TypeScript. The repository describes itself as: ranui — a Web Components UI library — plus ranuts utilities. Hand-built frontend infrastructure. The licence is MIT.
Read from SKILL.md and the folder at commit a73eadb. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are typescript).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Ranuts loads about 1.5k tokens when it runs. Until then it costs about 115 tokens; SKILL.md has 522 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from chaxus/ran at commit a73eadb, republished under its MIT licence (© chaxus). 522 words, ~1,544 tokens.
.claude/skills/ranuts/SKILL.md (or your agent's skills folder).A broad, tree-shakeable utility toolkit. Four independent entry points; import from the
subpath, never from ranuts/dist/... or the internal @/... alias.
When ranuts is installed, its docs ship inside the package:
node_modules/ranuts/docs/API.md — the full generated function reference for
ranuts/utils (signatures + one-line descriptions). This is the source of truth.node_modules/ranuts/CLAUDE.md — usage guide: entry-point map, project layout,
the visual/ engine, conventions, and gotchas.| Import from | What | Runtime |
|---|---|---|
ranuts | Root barrel — re-exports utils + visual surface | browser + node |
ranuts/utils | DOM/BOM, string, object, number, color, time, reactivity | browser + node* |
ranuts/node | HTTP server, router, ws, fs, streams, middleware | node only |
ranuts/visual | 2D rendering engine (Canvas / WebGL / WebGPU) | browser only |
ranuts/vnode | Snabbdom-style virtual DOM (h, init, modules) | browser |
ranuts/stream | SSE parsing + provider-neutral streamed-response fold | browser + node |
ranuts/conversation | Event log → renderable conversation nodes | browser + node |
* Most ranuts/utils functions are browser-oriented (touch window/document) but
guard with typeof window/document !== 'undefined'; pure helpers run anywhere. Never
import ranuts/node in browser code — it pulls in fs/http/child_process.
ranuts/utils — frequently usedReactivity: createSignal(value, opts?) → [getter, setter] (signal primitive).
Timing: throttle, debounce, generateThrottle, durationHandler, getFrame.
String/HTML: escapeHtml, clearStr, clearBr, changeHumpToLowerCase,
getMatchingSentences, checkEncoding.
Object/data: cloneDeep, filterObj, compose (async→sync middleware), createData.
Files/MIME: getMime(ext), getExtensions(mimeType), createObjectURL(blob|buffer),
convertImageToBase64(file).
URL/cookie/query: appendUrl, encodeUrl, getAllQueryString, getQuery, getCookie,
getCookieByName, getHost.
Env/device: currentDevice, Platform, connection, getPerformance, getPixelRatio,
canvasVendor/audioVendor (fingerprints).
Storage: localStorageGetItem, localStorageSetItem (SSR-safe wrappers).
DOM: addClassToElement, removeClassToElement, create(tag),
createDocumentFragment, scriptOnLoad.
Messaging: MessageCodec (structured message encode/decode, used for cross-context /
desktop integration).
This is a shortlist. See
node_modules/ranuts/docs/API.mdfor the complete, exact list.
ranuts/stream + ranuts/conversation — streaming conversationsThree layers in stream, and the vendor-specific one is not shipped: you write the
mapping from your provider's SSE event onto StreamChunk.
parseEventStream(source) — bytes → ServerSentEvent. Handles chunk boundaries anywhere
(including mid multi-byte character and mid CRLF), repeated data:, : keep-alives, BOM,
and an unterminated trailing block.mapEventStream(source, map) — your mapping, returning [] to drop [DONE]/keep-alives.createStreamAccumulator() — folds chunks into blocks: snapshot(), text(),
reasoning(), toolCalls().Rules that bite: group by index, never arrival order; never parse tool arguments
mid-stream (argumentsDelta is text — parse after finish); block-end wins over deltas;
block-start is optional.
conversation projects the resulting events into nodes. Each kind of content is an
independently registered state machine — match / start / update — so adding a kind is
adding a definition, not editing a renderer. publication is the streaming throttle:
animation-frame for per-token deltas, immediate for discrete facts, none to record
without waking the view. Order is fixed at start, so a streaming message keeps its place.
createBottomFollower (from ranuts/utils) keeps such a view pinned to its floor without
fighting the reader: call follow() on every content change, pass observe: [column] for
growth that appends no node, and anchor with captureAnchor/restoreAnchor around a prepend.
diffLines(oldText, newText, { context }) (from ranuts/utils) returns unified-style
hunks with both gutters, degrading to a wholesale replacement past a table cap rather
than allocating unbounded memory.
<r-conversation> and <r-tool-card> in ranui compose all of this.
import { createSignal, throttle, escapeHtml, getMime, cloneDeep } from 'ranuts/utils';
// Reactive signal
const [count, setCount] = createSignal(0);
setCount(1);
count(); // 1
// Throttle a scroll handler
const onScroll = throttle(() => console.log('scrolled'), 200);
window.addEventListener('scroll', onScroll);
escapeHtml('<b>hi</b>'); // "<b>hi</b>"
getMime('png'); // "image/png"
cloneDeep({ a: { b: 1 } }); // deep copy, handles cyclesranuts/utils), not ranuts/dist/... or @/....typeof window !== 'undefined') in any code that might run
under SSR/node.ranuts/node is node-only and marked external in builds — keep it out of browser
bundles.ranuts/visual is browser-only (needs Canvas/WebGL/WebGPU).© chaxus, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in plugins/ranuts/skills/ranuts of chaxus/ran.
Open the folder on GitHubat commit a73eadb
Ranuts next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Ranuts this skillchaxus/ran | 271 | — | ~1.5k | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 64 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| Web Artifacts Builderanthropics/skills | 180k | 41 repos | ~769 | Automated safety check: Pass | Apache-2.0 | |
| Typescript Advanced Typesrolling-scopes/rsschool-app | 10k | 25 repos | ~4.2k | Automated safety check: Pass | MPL-2.0 | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 5 repos | ~1.1k | Automated safety check: Pass | MIT | |
| MCP Server BuildershareAI-lab/learn-claude-code | 78k | 5 repos | ~1.2k | Automated safety check: Pass | MIT |
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
anthropics/skills
Builds multi-component claude.ai HTML artifacts as a small React, TypeScript and Tailwind project, then bundles it into one shareable HTML file.
rolling-scopes/rsschool-app
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.
shareAI-lab/learn-claude-code
Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.
shareAI-lab/learn-claude-code
Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.
nrwl/nx
Import, merge, or combine repositories into an Nx workspace using nx import.
chaxus/ran
A skill your agent uses when building UI with the ranui web-component library (elements like <r-button, <r-modal, <r-select, <r-input, <r-message) or its fluent DOM builder (ranui/builder —…
chaxus/ran
A skill your agent uses when designing, reviewing, or improving web UI visual quality, especially when a developer-built interface feels cluttered, flat, generic, poorly spaced, weakly hierarchical…
Works with
A skill your agent uses when working with the ranuts utility library — DOM/BOM/string/object/number/color/time helpers and reactivity from ranuts/utils (e.g. Ranuts is an agent skill from chaxus/ran.g.
Ranuts fits situations like: working with the ranuts utility library — DOM/BOM/string/object/number/color/time helpers and reactivity from ranuts/utils (e.g.
Run `npx skills add chaxus/ran --skill ranuts -a claude-code`. Or copy the skill folder (plugins/ranuts/skills/ranuts in chaxus/ran) into .claude/skills/ranuts in your project. Claude Code loads it when a task matches its description.
Run `npx skills add chaxus/ran --skill ranuts -a codex`. Or copy the skill folder (plugins/ranuts/skills/ranuts in chaxus/ran) into .agents/skills/ranuts in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add chaxus/ran --skill ranuts -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ranuts, .gemini/skills/ranuts, .github/skills/ranuts and .opencode/skills/ranuts in your project.
SKILL.md names no scripts, command-line tools or credentials: Ranuts is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Ranuts is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.5k tokens (SKILL.md is roughly 6.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Ranuts: MCP Server Builder (anthropics/skills, 180k stars), Web Artifacts Builder (anthropics/skills, 180k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
chaxus (a GitHub user) maintains it in chaxus/ran, which has 271 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 7, 2026.
Source: chaxus/ran on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.