菜单
Continuous IDE monitoring using bridge tools. Checks diagnostics, test results, or terminal output. Designed for use with /loop for recurring checks.
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
Find all @deprecated APIs in the workspace, count their callers, and extract migration guidance. Produces a prioritized report sorted by call count so you know which deprecations to tackle first.
Find unused exports, dead functions, and unreachable code across the workspace using LSP analysis. Cross-verifies detectUnusedCode with findReferences to eliminate false positives. Use to clean up technical debt or before a major refactor.
Diagnose and fix TypeScript/language type errors using LSP diagnostics, hover, and code actions. For each type error, fetches the expected vs actual types, surfaces quickfix suggestions, and optionally applies them. Use when getDiagnostics shows type errors you want to resolve quickly.
Test coverage heatmap from lcov or JSON coverage data. Finds coverage reports, parses line coverage per file, and renders a color-coded file-tree heatmap as HTML. Opens in the system browser.
Full debug workflow using IDE bridge tools. Runs tests to find failures, sets conditional breakpoints, evaluates expressions in the debugger, identifies root causes, applies fixes, and verifies. Use when debugging test failures or runtime issues.
Dependency graph for a file or symbol. Calls getCallHierarchy and findReferences, builds a directed graph, and renders an interactive HTML force-directed graph. Opens in the system browser.
| name | ide-monitor |
| description | Continuous IDE monitoring using bridge tools. Checks diagnostics, test results, or terminal output. Designed for use with /loop for recurring checks. |
| disable-model-invocation | true |
| effort | low |
| argument-hint | diagnostics | tests [filter] | terminal <name> |
getToolCapabilities MCP tool is available to you.
Not available (no MCP tool by that name): stop and tell the user:
"This skill requires the Claude IDE Bridge. It uses getDiagnostics and runTests which have no CLI equivalent.
To use this skill:
npm run start-all (in claude-ide-bridge/)claude --ide session (not remote-control)"Available: call it. If extensionConnected is false: show the same message. If true: proceed.
Monitor your IDE workspace continuously. Use with /loop for recurring checks.
/loop 5m /claude-ide-bridge:ide-monitor diagnostics
/loop 10m /claude-ide-bridge:ide-monitor tests
/loop 2m /claude-ide-bridge:ide-monitor terminal dev-server
Or run once:
/claude-ide-bridge:ide-monitor diagnostics
Parse $ARGUMENTS to determine the monitoring mode:
diagnostics (default if no argument)getDiagnostics to get all current errors and warningstests [filter]runTests with the optional filter from the argument/claude-ide-bridge:ide-debug to investigateterminal <name>getTerminalOutput with the terminal name from the argumentlistTerminals)Keep output concise for recurring checks: