Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From split
Use split MCP tools instead of Read/Grep when exploring source. Read-only fn-level index, multi-language via WASM. Watcher rebuilds the index when source changes. Edit happens on the source file via normal tools.
npx claudepluginhub yesitsfebreeze/split --plugin splitHow this skill is triggered — by the user, by Claude, or both
Slash command
/split:splitThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
`split` MCP server indexes source files into per-function `.fs` body files under `.split/`.
Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Analyzes provided content for SEO quality, E-E-A-T signals, readability, keywords, and structure. Scores and recommends improvements based on best practices.
Share bugs, ideas, or general feedback.
split MCP server indexes source files into per-function .fs body files under .split/.
Source is the truth. .split/ is a derived cache. Watcher: source → .fs (one-way).
Edit source files with normal tools (Edit/Write). The index catches up.
Multi-language via WASM. Builtins: rs, py. Add more by dropping .wasm into .split/languages/ (project) or ~/.config/split/languages/ (user). Extensions without a language module still work — whole file stored as one body.
| Instead of | Use |
|---|---|
Read file.<ext> | open_source(source_path) → fn list, then read_body(path) |
Grep pattern src/ | search_bodies(query) |
| Edit one fn | read_body for context → Edit on source path |
| Find bloated functions | find_large() |
| Discover supported languages | list_languages() |
list_languages() — installed extensions + source (builtin/user/project) + comment markeropen_source("src/path/to/file.<ext>") — fn list sorted by size, ⚠ flags fns over SPLIT_MAX_LOCread_body(".split/src/path/to/file/fn_name.fs") — load one fnsearch_bodies("symbol_name") — grep across all indexed fnsread_body — first line shows §head <src>:<start>-<end> <name> with exact source line rangeEdit (or Write) on the original source file using that rangeIf .split/ is empty:
index_dir(src_dir="src")| Variable | Default | Purpose |
|---|---|---|
SPLIT_MAX_LOC | 256 | Line threshold for ⚠ warnings and find_large |
SPLIT_SRC_DIR | src | Source directory for watcher |
SPLIT_DEBOUNCE_MS | 500 | Watcher debounce (ms) |
SPLIT_EXT | rs | File extension to index |
| Operation | Read | split |
|---|---|---|
| Explore large file | ~2700 tokens | ~140 tokens |
| Cross-codebase search | ~5000 tokens | ~50 tokens |