serena-code-workflowlisted

# Serena Code Workflow ## Purpose Use Serena MCP as the primary semantic layer for code work. The goal is low semantic entropy: understand structure before reading bodies, edit symbols instead of brittle line ranges, keep project knowledge synchronized, and prefer scalable patterns over quick text surgery. User-facing conversation stays in Russian unless the user asks otherwise. Repository documentation, code comments, commit messages, memory files, plan files, and research archive files are written in English. ## When To Use Use this skill without waiting for explicit invocation when the task asks to: - Inspect, index, explore, understand, map, review, edit, refactor, or trace repository code. - Analyze projects, directories, files, symbols, classes, functions, references, call sites, dependencies, or implementation scope. - Find where a feature is implemented, how code is connected, what can be deleted, or what will be affected by a change. - Make non-trivial code changes where semantic structure matters more than raw text matching. - Use or prefer Serena MCP, LSP-aware tools, symbol navigation, or project memories. If Serena is unavailable or the file type is not supported, state the fallback and continue with Claude Code-native tools (Read, Grep, Glob, Edit). Do not block progress just because a preferred MCP tool is missing. ## Serena Tool Order (read) For reading code, follow this order unless the task is trivial or the current session lacks a listed tool: 1.