semble
Semantic code search using the Semble MCP server. Use when exploring an unfamiliar codebase, finding code by what it does rather than exact text, locating an implementation, understanding how a feature works, or discovering related code. Triggers on requests like "where is X handled", "find the code that does Y", "how does Z work", "search the codebase for", or any semantic/exploratory code question where grep's literal matching is a poor fit.
What this skill does
# Semble - Semantic Code Search Semble finds code by **meaning**, not literal text. Describe what code does (or name a symbol) and Semble returns the most relevant chunks ranked by semantic similarity. It builds and caches an index automatically on first use and refreshes it when files change. Prefer Semble over Grep/Glob/Read for any exploratory or semantic question. Reserve grep for exhaustive literal matches or confirming an exact string. ## When to Use - **Exploring an unfamiliar codebase**: "where is authentication handled?", "how does the caching layer work?" - **Finding an implementation by intent**: "find the code that retries failed requests" — even when you don't know the function name. - **Locating a symbol**: search by an identifier like `save_pretrained` and let Semble surface every relevant usage and definition. - **Discovering related code**: given a known file and line, find structurally/semantically similar code elsewhere. ## How to Use This plugin provides the Semble MCP server, which exposes two tools. ### `mcp__semble__search` Find relevant code with a natural-language or code query. - `query` (required) — natural language or code, e.g. `"authentication flow"`, `"save model to disk"`, or a symbol like `save_pretrained`. - `repo` (optional) — the project root to index. When working in a local project, pass the absolute project root. For remote code, pass an explicit `https://` git URL. **Never guess or infer URLs.** - `top_k` (optional, default 5) — number of results to return. The index is built on first use and cached for the session; it refreshes automatically when files change. ### `mcp__semble__find_related` Find code semantically similar to a specific location — use after `search` to explore connected implementations or callers. - `file_path` (required) — use the `file_path` from a prior `search` result. - `line` (required) — 1-indexed line number from that result. - `repo` (optional) — same as above. - `top_k` (optional, default 5). ## Recommended Workflow 1. Start with `mcp__semble__search`, passing the project root as `repo`; the index builds and caches automatically. 2. Inspect full files (with `Read`) only when a returned chunk lacks enough context. 3. Use `mcp__semble__find_related` on a promising result to explore connected implementations. 4. Fall back to grep only for exhaustive literal matching. ## Important Notes - The MCP server runs via `uvx --from "semble[mcp]" semble`, so [`uv`](https://docs.astral.sh/uv/) must be installed. No API key is required. - The first search in a session indexes the repo (downloads a small embedding model on first ever run); subsequent searches are fast and refresh automatically when files change. - Content scope (code vs. docs/config) is fixed at server launch. By default Semble indexes code; append `--content docs`, `--content config`, or `--content all` to the server args to widen it.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.