From rldyour-lsps
Проверка LSP и Serena prerequisites для Python/Rust/Dart/Flutter/TS/JS/Go/C++/Qt/YAML/Docker/HTML/CSS/Shell. Используй для: проверь LSP, проверь язык-серверы, диагностики LSP, доступны ли LSP в проекте. EN triggers: check LSP, language server health, LSP diagnostics, verify LSP setup, are LSP installed, LSP project prerequisites, LSP doctor.
How this skill is triggered — by the user, by Claude, or both
Slash command
/rldyour-lsps:lsp-health-checkThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Verify that language servers and project prerequisites are available before relying on diagnostics, semantic navigation, or Serena symbol tools.
Verify that language servers and project prerequisites are available before relying on diagnostics, semantic navigation, or Serena symbol tools.
Run from a repository root:
bash ${CLAUDE_PLUGIN_ROOT}/scripts/check_lsps.sh
For another project:
bash ${CLAUDE_PLUGIN_ROOT}/scripts/check_lsps.sh /path/to/project
${CLAUDE_PLUGIN_ROOT}/references/lsp-server-matrix.md.stdio LSP sessions as a test - they hang waiting for a real LSP client.compile_commands.json as a serious warning because diagnostics may be wrong.tsconfig.json or jsconfig.json.pyproject.toml, pyrightconfig.json, or virtual environment expectations.pubspec.yaml, analysis_options.yaml, and dependency resolution.In Russian, summarize:
pyright-langserver --stdio без LSP-клиента (зависает).compile_commands.json для C/C++ критично).command -v.npx claudepluginhub nddev-it-com/rldyour-claudecode --plugin rldyour-lspsGuides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Synthesizes the current conversation into a structured spec (PRD) and publishes it to the project issue tracker with a ready-for-agent label, without interviewing the user.