菜单
Diagnose and align Kode LSP behavior with the reference CLI (plugin-based .lsp.json, stdio-only, no install menus). Use when LSP results are missing, LSP is disabled, or you need to configure plugin LSP servers without telling the user to run menu-style install commands.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Kode capability-management playbook: treat features (LSP, statusline, output styles, plugins, notifications) as configurable capabilities and drive changes through the agent CLI (SlashCommand/Task) instead of pushing users into menu-like flows. Use when the user asks to enable/disable/configure a capability, diagnose why it’s off, or wants the agent to self-manage Kode’s own features (meta capability management).
A structured workflow for co-authoring high-signal docs (PRD, RFC, design docs, proposals, decision records). Use when the user needs to turn messy context into a readable artifact with clear goals, tradeoffs, and next steps. Emphasizes context capture, outline-first drafting, and context-free reader testing to catch blind spots.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
A set of resources to help write internal communications in common company formats. Use when asked to write internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Guide for building high-quality MCP (Model Context Protocol) servers and tools: what MCP is, how to design tools/resources/prompts for agent usability, and how to implement servers in TypeScript or Python. Use when you need MCP best practices, server architecture patterns, or a step-by-step build workflow (with language preference).
Troubleshoot Kode permission prompts/denials (tool allowlists, commandAllowedTools, dontAsk fail-closed, subagent inheritance). Use when tools are unexpectedly blocked, permission prompts repeat, or behavior differs between main agent and subagents.
| name | lsp-maintain |
| description | Diagnose and align Kode LSP behavior with the reference CLI (plugin-based .lsp.json, stdio-only, no install menus). Use when LSP results are missing, LSP is disabled, or you need to configure plugin LSP servers without telling the user to run menu-style install commands. |
| allowed-tools | Read Edit SlashCommand |
/lsp-maintain install” or “run /lsp-maintain doctor”.SlashCommand (e.g. /plugin ..., /lsp) or Edit to configuration files.Kode’s LSP tool is enabled only when there is at least one resolved LSP server and at least one is not in error.
/lsp via SlashCommand and read the “Configured servers” list.Kode resolves LSP servers from enabled plugins:
.lsp.json (JSON, top-level record)lspServers (inline record or relative file path within plugin root)If the user needs a new server, the correct path is: enable a plugin that provides it, or add/update a plugin’s .lsp.json.
Prefer:
SlashCommand to manage plugins (/plugin ...) and re-check with /lsp.Edit to update the plugin’s .lsp.json or manifest lspServers record/file./lsp and confirm servers are resolved.LSP tool call (e.g. goToDefinition) on a file extension that is mapped in extensionToLanguage.command must be an executable (avoid embedding arguments; use args).restartOnCrash, startupTimeout, or shutdownTimeout in the config (Kode treats them as unsupported).