원클릭으로
diagnostics
Access LSP diagnostics and suggest project rollback. Use for debugging static errors and helping users revert changes.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Access LSP diagnostics and suggest project rollback. Use for debugging static errors and helping users revert changes.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | diagnostics |
| description | Access LSP diagnostics and suggest project rollback. Use for debugging static errors and helping users revert changes. |
Tools for debugging code issues and managing project state.
Use this skill when:
Retrieve LSP diagnostics - syntax errors, type errors, and code issues.
Parameters:
filePath (str, optional): File path to check. If omitted, checks all files with errors.Returns: Dict with diagnostics (file paths to error lists) and filePath (filter used)
Example:
// Check specific file after editing
const result = await getLatestLspDiagnostics({ filePath: "src/auth.ts" });
for (const [path, errors] of Object.entries(result.diagnostics)) {
for (const error of errors) {
console.log(`Line ${error.startLine}: ${error.message}`);
}
}
// Check all files for errors
const allErrors = await getLatestLspDiagnostics();
console.log(`Files with errors: ${Object.keys(allErrors.diagnostics)}`);
When to check LSP:
Skip LSP when:
Suggest rolling back to a previous checkpoint.
Parameters:
reason (str, required): Short, non-technical explanation for why rollback is suggestedReturns: Dict with success, message, and reason
Example:
await suggestRollback({ reason: "The changes caused unexpected errors across multiple files" });
Use when user expresses intent to:
Important:
// After making code changes
const errors = await getLatestLspDiagnostics({ filePath: "src/services/user.ts" });
if (Object.keys(errors.diagnostics).length > 0) {
// Fix each error
for (const [path, diags] of Object.entries(errors.diagnostics)) {
for (const diag of diags) {
console.log(`Fix: ${diag.rendered}`);
}
}
}
// User: "Everything broke, can you undo this?"
await suggestRollback({ reason: "Recent changes caused errors. Click View Checkpoints to restore a working version." });
A test skill for validating secondary skill deployment.
List and manage user feedback items from the agent inbox. Use when the user asks about feedback, bug reports, feature requests, or inbox items.
Spawn a code review (architect) subagent for deep analysis, planning, and debugging. The architect specializes in strategic guidance rather than implementation. Architect should be called after building major features. Relies on `delegation` skill.
Create and manage Replit's built-in PostgreSQL databases, check status, execute SQL queries with safety checks, and run read-only queries against the production database.
Delegate tasks to specialized subagents. Use subagent for synchronous task execution, startAsyncSubagent for background task execution, messageSubagent for async follow-ups, or messageSubagentAndGetResponse for sync follow-ups.
Configure and publish your project. Use to set deployment settings and suggest publishing when the app is ready.