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

Avoid Common Vscode Mistakes

BSecurity

Avoid common VSCode mistakes — settings conflicts, debugger setup, and extension clashes.

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentstypescriptrustgoshellbashnodedockerdebugginggit

Works with

vscodeterminal

Security Analysis

B75/100
criticalAccesses sensitive system or user directories

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill avoid-common-vscode-mistakes --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Avoid Common Vscode Mistakes?

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

Security grade badge for Avoid Common Vscode Mistakes
[![Security: B — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-avoid-common-vscode-mistakes/badge)](https://www.skillsdirectory.com/skills/rondoflow-avoid-common-vscode-mistakes)

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

Download with Pro
Files
SKILL.md
---
name: avoid-common-vscode-mistakes
description: "Avoid common VSCode mistakes — settings conflicts, debugger setup, and extension clashes."
category: "Community"
author: community
version: "1.0.0"
icon: puzzle
---

## Settings Precedence
- User → Workspace → Folder — later overrides earlier
- `.vscode/settings.json` per project — overrides user settings
- `"editor.formatOnSave"` in workspace overrides user — can be confusing
- Multi-root workspaces need per-folder settings — or root `.code-workspace` file
- Some settings only work in user — `"terminal.integrated.shell"` is user-only

## Formatter Conflicts
- Multiple formatters for same language — set `"[language]": {"editor.defaultFormatter": "id"}`
- Prettier vs ESLint both formatting — disable one: `"prettier.enable": false` in ESLint projects
- Format on save runs wrong formatter — explicit `defaultFormatter` required
- `.editorconfig` overrides some settings — can conflict with extension settings

## Debugger Setup
- `launch.json` needed for most debugging — can't just press F5
- `"cwd"` relative to workspace root — not launch.json location
- `"program"` path wrong — use `${workspaceFolder}/path/to/file`
- Node.js: `"skipFiles"` to avoid stepping into node_modules
- Compound configurations for multi-process — `"compounds"` array in launch.json

## Extensions
- Extension host crash — disable recently installed, enable one by one
- "Cannot find module" after install — restart VS Code completely
- Extension settings not applying — check if workspace setting overrides
- Conflicting extensions — keybinding conflicts, duplicate features

## Terminal
- Wrong shell on new terminal — set `"terminal.integrated.defaultProfile.*"`
- Environment variables missing — terminal inherits from launch method, not .bashrc
- Path not updated after install — restart VS Code, not just terminal
- Shell integration issues — `"terminal.integrated.shellIntegration.enabled": false` to disable

## Remote Development
- SSH: `~/.ssh/config` Host must match — `"remote.SSH.configFile"` to use different config
- Containers: `.devcontainer/devcontainer.json` required — won't auto-detect Dockerfile
- WSL: extensions install separately — WSL extensions stay in WSL
- Port forwarding: auto but not always — check Ports panel

## Workspace Trust
- Restricted mode disables some features — debugging, tasks, some extensions
- Trust prompt on first open — "Trust Folder" to enable everything
- Per-folder trust in multi-root — can trust some folders, not others

## Common Fixes
- IntelliSense not working — check language server status in Output panel
- "Cannot find module" in TypeScript — restart TS server: Cmd+Shift+P → "TypeScript: Restart TS Server"
- Git not detecting changes — check if inside subfolder, `.git` must be at root or configured
- Settings not saving — check write permissions on settings.json

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
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', ...

693621 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 →