LSP Simulate

Trust Score 88/100

Simulate code edits in-memory using an LSP-backed session to verify diagnostics and prevent breaking changes before writing to disk.

triggers:simulate editpreview_editcreate_simulation_sessionevaluate_sessioncommit_session

GitHub SKILL.md

What it does

LSP Simulate lets an agent apply code edits to an in-memory overlay (a simulation session) backed by a language-server-like MCP server, run diagnostics, and report whether edits introduce errors. Use it to preview single edits or multi-edit sessions, evaluate risk with net_delta/confidence metrics, and safely commit only verified patches. Sessions are ephemeral and should be destroyed after use.

When to use it

Planning a risky refactor across multiple files
Verifying a proposed edit will not introduce type or lint errors
Running a quick preview-edit for a small change before committing to disk
Chaining edits and finding how far through the chain is safe to apply

What's included

Scripts: references folder with patterns and evaluation guidance (has_references=true)
Instructions: Quick start for preview_edit, full session workflow (create, simulate_edit, evaluate_session, commit/discard, destroy_session), chained mutation pattern and cleanup rules
Compatibility: Requires the agent-lsp MCP server and its RPC tools (preview_edit, create_simulation_session, simulate_edit, evaluate_session, commit_session, discard_session, destroy_session)

Compatible agents

Best used by agents that can call MCP server tools (agents with MCP/toolcall capability). Works well with Claude Code, Copilot-style agents, or any agent runtime that can call the listed mcp__lsp__* tools.

Audit Summary

LSP Simulate enables in-memory code edit simulation via an MCP server, letting agents verify edits are safe before writing to disk. No scripts were present to execute. The SKILL.md is well-structured with clear workflows, decision guides, and session state documentation. Clean security profile with no executable code — purely instructs MCP tool calls.

Watch Out

Requires the agent-lsp MCP server to be running
No version pinning for the MCP server dependency

Notes

Pure instruction skill with no bundled scripts. Documentation quality is above average. The external MCP server dependency is the main practical barrier to adoption.

Information

Repository: agent-lsp
Stars: 49

Trust Score

Overall88

Security95

Code Quality82

Architecture78

Usefulness72

More from agent-lsp

LSP Extract Function

Extract a selected block of code into a named function using LSP code actions when available, with a manual fallback that analyzes captured variables, return va

Related Skills

Reverse Engineer

Provides step-by-step guidance and best practices for binary reverse engineering: static analysis, dynamic tracing, disassembly, and documentation workflows for

FastAPI Project Templates

Creates production-ready FastAPI project scaffolds with async patterns, DI, middleware, and testing best practices for high-performance APIs.

GraphQL Inspector — Validate

Validate GraphQL operations against a schema with configurable depth, complexity, alias and directive limits to catch errors before runtime.

Ip2Location IO Automation (Composio)

Automate Ip2location IO tasks via Composio's Rube MCP toolkit — discover tools, verify connections, and execute schema-compliant workflows safely.

JJ Hunk

Programmatic hunk selection for Jujutsu (jj): list, split, commit, or squash specific hunks to enable partial commits and fine-grained history editing without a

Codex Collab

Bridge Claude and Codex to run tasks, perform code reviews, and run background jobs for research or implementation workflows.

Cursor Hello World Tutorial

A concise 10-minute hands-on tutorial demonstrating Cursor's Tab completion, Chat, Inline Edit, and Composer features for getting started quickly.

BK-CI Design Patterns Guide

Practical guide to design patterns used in the BK-CI project (Kotlin/Spring). Covers factory, strategy, singleton, decorator, observer, template method, chain-o

Back to Skills