analyze
무료Risk analysis and approach selection before planning. Use when requirements are ambiguous, approaches vary, or work touches hub/bridge nodes. Skip for typo fixes.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Serena code intelligence — LSP-powered symbol navigation, diagnostics, and targeted code surgery. Activate before complex refactors, cross-file analysis, or when graph tools need symbol-level depth.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
설치 방법 보기설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.
Activate Serena MCP for LSP-powered code intelligence: symbol navigation, type diagnostics, and safe code surgery.
CRITICAL: Call initial_instructions first when starting any Serena work — it loads the Serena Instructions Manual with project-specific context.
mcp__plugin_serena_serena__initial_instructions()
# or
mcp__serena__initial_instructions()
mcp__plugin_serena_serena__activate_project()
mcp__plugin_serena_serena__get_symbols_overview()
Returns top-level symbols, classes, functions — fast structural map of the codebase.
| Tool | Use case |
|---|---|
find_symbol | Locate a symbol by name across codebase |
find_declaration | Jump to where a symbol is declared |
find_implementations | Find all implementations of an interface / abstract class |
find_referencing_symbols | Find all callers and usages of a symbol |
| Tool | Use case |
|---|---|
activate_project | Register project with Serena — requires mcp__plugin_serena_serena__ namespace |
get_current_config | Read Serena's current project configuration |
open_dashboard | Open the Serena dashboard UI |
execute_shell_command | Run shell commands (use with caution — confirm before destructive ops) |
| Tool | Use case |
|---|---|
get_diagnostics_for_file | IDE-level type errors, lint warnings for a specific file |
get_symbols_overview | Project structure overview — top-level symbols map |
| Tool | Use case |
|---|---|
replace_symbol_body | Replace function/method body — exact, no regex risk |
insert_after_symbol | Insert code after a symbol definition |
insert_before_symbol | Insert code before a symbol definition |
rename_symbol | Safe rename across entire codebase |
safe_delete_symbol | Delete symbol, verify no remaining references |
| Tool | Use case |
|---|---|
find_file | Find files by name pattern |
list_dir | List directory contents |
read_file | Read file content |
search_for_pattern | Regex search across files |
replace_content | Replace text content in file |
create_text_file | Create a new text file |
| Tool | Use case |
|---|---|
write_memory | Save analysis findings for future sessions |
read_memory | Recall prior analysis |
list_memories | List all saved memories |
edit_memory | Update an existing memory |
rename_memory | Rename an existing memory entry |
delete_memory | Remove stale memory |
Use Serena memory to persist analysis state across sessions — avoids re-deriving complex blast radius mappings:
# Save findings after analysis:
mcp__serena__write_memory(title="auth-refactor-callers", content="find_referencing_symbols(login) = [A, B, C]")
# Recall in next session:
mcp__serena__read_memory(title="auth-refactor-callers")
Serena is invoked as optional hooks inside other supergraph skills:
| Skill | Hook | Tools used |
|---|---|---|
scan | Step 2b/3b | activate_project, get_symbols_overview |
plan | Step 3b | find_referencing_symbols, find_implementations, write_memory |
analyze | Step 2b | find_referencing_symbols, find_implementations |
tdd | After RED, after GREEN, refactor | get_diagnostics_for_file, replace_symbol_body, rename_symbol |
execute | Code surgery, post-execution | replace_symbol_body, rename_symbol, insert_after_symbol, find_referencing_symbols |
fix | Pre-loop + each iteration | get_diagnostics_for_file, replace_symbol_body, rename_symbol |
verify | Step 3b | get_diagnostics_for_file |
review | Step 3b | find_referencing_symbols, find_implementations, get_diagnostics_for_file, write_memory |
integration | Post-test | find_referencing_symbols, get_diagnostics_for_file |
architecture | Step 2 | get_symbols_overview |
database-migrations | Impact check | find_referencing_symbols |
browser-agent | Component impact | find_referencing_symbols |
flutter-dart-code-review | MCP-Integrated Review | get_diagnostics_for_file, find_referencing_symbols, find_implementations |
Two variants may be present depending on project setup:
# Plugin variant (full feature set — file ops + symbol nav):
mcp__plugin_serena_serena__<tool>
# Direct variant (symbol navigation focus):
mcp__serena__<tool>
Use whichever responds. If both are available: prefer mcp__plugin_serena_serena__ for file operations, mcp__serena__ for symbol navigation.
If Serena MCP is not available:
initial_instructions before any other Serena toolreplace_symbol_body and rename_symbol over raw text edits for code changessafe_delete_symbol instead of manual deletion — it verifies no remaining referencesexecute_shell_command for destructive operations without user confirmation아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.
로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.
아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.
Risk analysis and approach selection before planning. Use when requirements are ambiguous, approaches vary, or work touches hub/bridge nodes. Skip for typo fixes.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Proactive architecture review — explore codebase structure, generate a self-contained HTML report with Mermaid diagrams and candidate improvements, then grill the findings. Use when planning a large refactor, onboarding to an unfamiliar codebase, or before a major architectural change.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Autonomous human-like browser control and professional QA/QC testing. Powered by agent-browser (Rust native CDP, zero Playwright) with ISTQB test matrix generation, automated testcase execution, console/network error tracing, and defect reporting.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Persistent token-compression mode (~75% reduction) — now always-on by default. Strips filler while keeping code exact.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Database migration best practices for schema changes, data migrations, rollbacks, and zero-downtime deployments across PostgreSQL, MySQL, and common ORMs (Prisma, Drizzle, Kysely, Django, TypeORM, golang-migrate).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.