Agent skill · kochetkov-ma
semble-setup
Installs, audits, repairs, updates, enables, reindexes or removes the semble_code semantic code-search MCP for a project. Triggers: semble, semantic code search, semble status, настрой semble, статус semble, переиндексируй, удали semble.
What it needs
About 12k tokens when loaded.
What this skill does
Semble Lifecycle router for semblecode — a semantic repository-search MCP server (semble 0.5.5, pinned) registered at user scope with alwaysLoad: true, indexing the corpus named by SEMBLECONTENTARGS into one shared cache root. This skill decides the mode, prints the state before touching anything, and delegates every mutation to the scripts under scripts/. No mutation logic lives in this file. Two tools become available once it is wired: Tool Purpose ------ --------- mcpsemblecodesearch find code by intent / behavior / name mcpsemblecodefindrelated neighbors of a KNOWN location, after a useful seed Both take a required repo parameter — the absolute project root, or an explicit https:///http:// git URL. It is never inferred. Since 0.5.5 both also accept optional content=code docs config all; omitting it uses the server's registered code docs config corpus. Results carry filepath, startline, endline, score and optional result content — there is no result line field. MCP defaults are topk=5, maxsnippetlines=10. Honest limits — state these to the user, never oversell Fact Consequence ------ ------------- There is no watcher and no daemon. semble 0.5.5 has no background thread, no service, nothing to start or stop. Never report a daemon as running, starting or stopped. Staleness is re-checked inside each tool call, behind a 3x last-build-duration cooldown. The embedding model is pre-loaded when the MCP server starts, and tool calls block until it is ready The first query on a cold cache downloads the embedding model (hundreds of MB) and is slow — allow up to 600 s and say so before starting. Offline with a cold HuggingFace cache = every call errors. The corpus is whatever SEMBLECONTENTARGS says — read the constant, never retype it .json/.json5/.csv/.tsv/.psv are excluded from every content type — unreachable even with --content all — and .mdx/.txt are in no bucket at all. Use rg for those. Full table: references/language-coverage.md. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills kochetkov-ma/semble-setup