Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Roslyn Lsp

ASecurity

Use the Roslyn MCP for C# diagnostics, symbol navigation and semantic edits.

2 stars
0 votes
0 copies
0 views
Added 9/28/2026
ai-agentsc#

Works with

mcp

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

$npx -y skills add thomas-fazzari/roslyn-for-clankers --skill roslyn-lsp --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Roslyn Lsp?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Roslyn Lsp
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/thomas-fazzari-roslyn-lsp/badge)](https://www.skillsdirectory.com/skills/thomas-fazzari-roslyn-lsp)

More formats (shields.io, HTML) on the badges page.

Files
SKILL.md
---
name: roslyn-lsp
description: Use the Roslyn MCP for C# diagnostics, symbol navigation and semantic edits.
---

# Roslyn LSP

Use the `roslyn` server for C# diagnostics, navigation and semantic edits.
It reads saved files in the current workspace. Its tools take flat arguments:

- `diagnostics`: `{ "file": "src/Calculator.cs" }`. It reports errors and warnings unless `severity` is `information` or `hint`
- `navigate`: `action` (`definition`, `type_definition`, `implementation`, `references`, `callers`, `callees`, `supertypes`, `subtypes`, `hover`), and `symbol` or `file`, `line`, `character`
- `symbols`: `file`, or `query` for a workspace search
- `edit`: `action` (`rename`, `rename_file`, `code_actions`) with its inputs, `proposalId` and `apply`
- `lsp`: `action` (`status`, `capabilities`, `reload`, `request`), and `method` with `parameters` for raw requests

`diagnostics`, `navigate` and `symbols` are read-only.

## Scope and diagnostics

- Start with the files relevant to the task. To check that the MCP works, request diagnostics for one known C# file.
- Set `file` to a specific path or narrow glob. Omitting it, using `"*"` or `"**/*.cs"` selects all C# files. Use that scope only for a requested workspace audit. Split large audits by project or directory.
- `limit` caps returned items. It does not reduce the files analyzed or the analysis time.
- After a timeout, narrow the selection. If a single-file retry also times out, report the failure and stop retrying that request. Attribute the cause only when logs support it.
- Read the structured result and report the checked scope. Split truncated results into narrower requests. A failed, incomplete or truncated response cannot establish that the workspace is clean.

## Navigation

Use `navigate` with `definition`, `implementation` or `references` when symbol identity matters.
Prefer `symbol` over a position when you know the name, for example `"symbol": "Calculator.Add"`. It avoids reading the file first.
The name matches the end of the qualified name. Add a parameter list for an overload or a constructor.
On `ambiguous_symbol`, send back one of the returned `candidates` unchanged.
Pass `file`, `line` and `character`. Input positions start at 1 and count UTF-16 code units.
Navigation returns `items` grouped by `file`, with one-based `[line, character]` pairs in `positions`.
`total` counts occurrences before limiting. Check `truncated` before claiming completeness.
Use `callers`, `callees`, `supertypes` and `subtypes` for call and type relationships.
Related symbols return a `symbol` name that can be sent back unchanged, for example to follow callers of callers.
Set `context: true` to receive each result's source line instead of reading the file.
Diagnostics, symbols and related symbols also return one-based positions. Only raw `lsp` requests use zero-based LSP positions.
Use `lsp` with `capabilities` when an operation's support is uncertain.

## Edits

`edit` returns a preview and a `proposalId`. Apply the proposal with the same action, its `proposalId` and `apply: true`.
For code actions, send the listing's `proposalId` and zero-based `actionIndex` to resolve an edit preview, then apply its new `proposalId`.

Stay within the requested change. A preview-only request does not authorize applying it.
When implementation is requested, carry authorized edits through without adding a separate approval step.
After applying an edit, check diagnostics for the affected files. On `stale_edit`, request a fresh proposal against the current files.

Attribution

thomas-fazzarithomas-fazzari
View sourceMore from thomas-fazzari →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

695601 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →