lsp-guided-coding
by Roy Yuen
Supercharge your agent with semantic code intelligence for safer refactors, precise navigation, and zero-error edits.
- Perform type-safe symbol renames across entire multi-file repositories.
- Identify and fix hidden type errors using real-time LSP diagnostics.
- Map unknown codebases by tracing definitions and semantic references.
$5
One-time purchase
Included in download
- Perform type-safe symbol renames across entire multi-file repositories.
- Identify and fix hidden type errors using real-time LSP diagnostics.
- Includes example output and usage patterns
See it in action
LSP Analysis: Found 3 references for `processUserData` in `api/handler.ts`. Refactor: Updated signature to include `RequestID`. Verification: LSP diagnostics passed for `services/auth.ts` and `api/handler.ts`. Status: No type errors introduced in the dependency graph.
Supercharge your agent with semantic code intelligence for safer refactors, precise navigation, and zero-error edits.
$5
One-time purchase
⚡ Also available via Agensi MCP — your AI agent can load this skill on demand via MCP. Learn more →
Included in download
- Perform type-safe symbol renames across entire multi-file repositories.
- Identify and fix hidden type errors using real-time LSP diagnostics.
- Includes example output and usage patterns
- Instant install
- One-time purchase
See it in action
LSP Analysis: Found 3 references for `processUserData` in `api/handler.ts`. Refactor: Updated signature to include `RequestID`. Verification: LSP diagnostics passed for `services/auth.ts` and `api/handler.ts`. Status: No type errors introduced in the dependency graph.
Screenshots
About This Skill
Safer Semantic Coding
LSP-Guided Coding bridges the gap between simple text-based AI editing and professional-grade development by integrating Language Server Protocol (LSP) intelligence directly into your agent's workflow. Instead of guessing symbol relationships via string matching, this skill enables your agent to act with semantic certainty.
What it does
The skill empowers your agent to utilize "intelligence-first" coding practices. It builds project context using actual definitions, references, and hover types rather than just file contents. It proactively checks diagnostics to catch syntax and type errors before you even run a build.
- Precise Refactoring: Uses LSP references to ensure every call site is updated during API changes.
- Diagnostic-Driven Debugging: Identifies type mismatches and unreachable code utilizing real-time compiler feedback.
- Intelligent Navigation: Jumps to definitions across complex directory structures to understand dependencies.
- Validation: Runs post-edit diagnostic passes to verify that changes didn't break the type graph.
Why use this skill
Manual prompting often leads to hallucinated imports or missed references in large repositories. By providing a structured workflow for LSP interaction, this skill ensures your AI agent works like a senior engineer who verifies their assumptions using the IDE's internal logic, resulting in significantly fewer "broken build" cycles.
📖 Learn more: Best Code Review Skills for Claude Code →
Use Cases
- Perform type-safe symbol renames across entire multi-file repositories.
- Identify and fix hidden type errors using real-time LSP diagnostics.
- Map unknown codebases by tracing definitions and semantic references.
- Verify code changes immediately with compiler-level feedback loops.
How to Install
unzip lsp-guided-coding.zip -d ~/.claude/skills/Reviews
No reviews yet - be the first to share your experience.
Only users who have downloaded or purchased this skill can leave a review.
Early access skill
Be the first to review this skill.
Only users who have downloaded or purchased this skill can leave a review.
Security Scanned
Passed automated security review
Permissions
No special permissions declared or detected
Frequently Asked Questions
Learn More About AI Agent Skills
Similar Skills
codex-grade-coding
Turn your AI agent into a senior engineer with strict task classification and verification-driven coding protocols.
env-doctor
Diagnoses why your project will not start. Checks runtime versions, dependencies, environment variables, databases, ports, and build artifacts systematically.
code-reviewer
Reviews your code for bugs, security vulnerabilities, logic errors, performance issues, and style violations. Organizes findings by severity and suggests fixes with code examples.
git-commit-writer
Writes conventional commit messages by analyzing your staged git changes. Detects commit type, scope, and breaking changes automatically.