jetbrains-skill
JetBrains Skill
Quick start
Goal: use JetBrains IDE features (index, inspections, refactoring, run configurations, integrated terminal) as tools for an external client, while keeping changes auditable and safe.
notes + tool list (condensed): skills/jetbrains-skill/references/jetbrains-skill.md.
Connection & modes
Client setup (done in the IDE)
- Settings → Tools → MCP Server
- Enable MCP Server
- Use “Auto-configure” for supported clients (updates their JSON config), or copy SSE / Stdio config for manual setup
- Restart the external client to apply changes
Brave Mode (no confirmations)
The IDE can allow running shell commands / run configurations without per-action confirmation (“Brave mode”). This increases automation power but also increases risk. Require explicit user confirmation before enabling/disabling it.
Workflow decision tree
- Do I need IDE-grade analysis/refactoring?
- File diagnostics:
get_file_problems - Symbol semantics / docs:
get_symbol_info - Safe rename across project:
rename_refactoring(prefer over plain text replace) - Indexed search:
search_in_files_by_text/search_in_files_by_regex - Find files:
find_files_by_name_keyword(fast, name-only) orfind_files_by_glob(path glob)
- Do I just need file operations in the project?
- Read file text:
get_file_text_by_path - Create file:
create_new_file - Targeted replace:
replace_text_in_file(auto-saves) - Open in editor:
open_file_in_editor - Reformat:
reformat_file
- Do I need to run something?
- List run configs:
get_run_configurations - Run a config (wait for completion):
execute_run_configuration - Run a terminal command in IDE:
execute_terminal_command(may require confirmation; output is capped)
Constraints (avoid common mistakes)
- Always pass
projectPathwhen known to avoid ambiguity. - Many tools require paths relative to the project root and only operate on project files.
- Line/column positions are 1-based for location-based tools.
- Prefer controlling output with
maxLinesCount+truncateMode; do not rely on defaults for large outputs. - Terminal commands and running configurations are high-risk; require explicit confirmation for any potentially destructive command. Brave Mode removes guardrails.
Recommended high-value patterns
Debug via inspections first
get_file_problemsto find errors/warnings → 2)get_symbol_infoto understand the code → 3)rename_refactoringfor renames → 4)replace_text_in_fileonly for truly textual changes.
Use indexed search for scale
Prefer search_in_files_by_text / search_in_files_by_regex since it uses IDE search/indexing and highlights matches with ||.
Running and output control
Use execute_run_configuration with a sane timeout (ms). For terminal commands use execute_terminal_command, but remember output caps; for huge output, redirect to a file and read it via file tools.
References
- notes + tool list (condensed):
skills/jetbrains-skill/references/jetbrains-skill.md
More from ry-run/run-skills
desktop-commander
Use Desktop Commander MCP (typically tools like `mcp__desktop-commander__*`) for local files, precise edits, search, and long-running processes on the machine. Use it when the task requires direct local execution, rather than IDE-only actions or remote platform operations.
61desktop-commander-mcp
使用 Desktop Commander MCP(常见为 `mcp__desktop-commander__*` 工具)进行本地文件/目录读写与搜索、精确文本替换、Excel/PDF 处理、启动与交互长生命周期进程(Python/Node/SSH/DB)、查看与终止进程/会话、读取工具调用历史与用量统计、管理服务器配置。适用于:需要“在机器上执行操作”的任务(读写代码/配置、批量改文件、搜索代码、分析 CSV/Excel、生成/修改 PDF、跑命令并持续读取输出、交互式 REPL 调试/数据分析)时。
2deepwiki
Use DeepWiki MCP for repository-focused documentation from deepwiki.com. Use it when you need a fast overview of an external repository, architecture, or repo-specific concepts, rather than live library docs or broad web research.
1ace-tool
Use Ace Tool MCP (`mcp__ace_tool__search_context`) for semantic repository discovery. Use it when the exact file, symbol, or implementation path is unknown, rather than starting with exact IDE search or direct file edits.
1context7
Use Context7 MCP for up-to-date library and framework documentation tied to an exact library ID. Use it for versioned API usage, setup, migrations, and code examples, rather than generic documentation-site search.
1vercel-skill
Use Vercel MCP for project discovery, deployments, build and runtime logs, toolbar threads, protected preview access, and Vercel documentation. Use it when the task centers on Vercel-hosted application state, rather than local-only execution.
1