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

Vscode Ready

ASecurity

Use only when the user asks to set up VS Code/Cursor launch, debug, run, or tasks configs (e.g. "make this project VSCode-ready"). Do not run on your own.

7 stars
0 votes
0 copies
0 views
Added 9/27/2026
ai-agentsrustgoshellnodedebugginggitdatabasedocumentation

Works with

cursorvscodecli

Security Analysis

A100/100

Scanned 9/27/2026

Install to Claude Code

$npx -y skills add kargnas/skills --skill vscode-ready --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Vscode Ready?

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

Security grade badge for Vscode Ready
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/kargnas-vscode-ready/badge)](https://www.skillsdirectory.com/skills/kargnas-vscode-ready)

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

Download with Pro
Files
SKILL.md
---
name: vscode-ready
description: Use only when the user asks to set up VS Code/Cursor launch, debug, run, or tasks configs (e.g. "make this project VSCode-ready"). Do not run on your own.
---

# Make this project VSCode-Ready

When starting, let the user know in one line that this skill is being used.

Act as a Principal Software Architect and Tooling Expert. Goal: create a seamless, "one-click" developer experience (DX) that leverages the full power of the IDE (VS Code, Cursor).

# Objective
Analyze the existing codebase and scaffold the infrastructure needed for a disciplined, high-automation environment. **MUST use available tools (agents, file readers, search)** to deeply understand the current stack before generating configurations.

# Execution Steps

## Step 0: Deep Codebase Analysis (CRITICAL)
**Before generating any files, scan the codebase thoroughly.**
- **Use Agents/Tools**: If `explore`, `grep`, or file-reading tools are available, use them to map the project structure.
- **Identify**:
  - The full Tech Stack (Languages, Frameworks, Database).
  - Existing build scripts (`package.json`, `Makefile`, `Cargo.toml`, etc.).
  - Entry points for debugging (where does `main` start?).
  - Current directory structure and module relationships.
  - Recent history of this repository using git (recent 20 commits).

## Step 1: The "Context" (`AGENTS.md` / `README.md`)
Create or update documentation to serve as the "manual" for both developers and AI.
- **Project Structure**: Based on the Step 0 scan, map out the file system.
- **Tech Stack**: Explicit versions and libraries found.
- **Dev Workflow**: How to build, run, and test based on existing scripts.

## Step 2: The "Controls" (VS Code Configuration)
Create a `.vscode` folder to standardize the workflow:
- **`launch.json`**: Create something the user can run as a daemon (for example `Run Dev Server`).
  - Create debug configurations for *every* part of the stack found in Step 0. Include a compound config to run everything at once.
  - The name MUST NOT have an emoji prefix. Exception: the 2 most important runs MAY use an emoji prefix.
  - Use separators to group the runs.
- **`tasks.json`**: Abstract complex CLI commands found in scripts into simple IDE tasks (e.g., `Install`, `Database Sync`).
  - Format: the name MUST have an emoji prefix. Append '...' when something must be chosen before running.
  - NO daemons allowed.
  - Don't make too-small tasks. Make tasks the user runs occasionally or initially. Maximum 5 tasks.
- **`settings.json`**: Enforce formatting (Prettier/Black/Rustfmt) and linting rules at the workspace level.
  - Add this recommended-plugin json (makes VS Code Tasks visible on the bottom status bar):
    ```json
    {
      "recommendations": [
        "actboy168.tasks"
      ]
    }
    ```

Don't confuse `launch` and `tasks` purposes. Ensure no duplicated features, be creative, and improve the user's AI-assisted development efficiency. Take care of feature order.

## Step 3: Ensure dependencies
- If dependencies are needed, add them to `package.json` / `Cargo.toml`, or add a script into `tasks.json` and tell the user to run it.

## Output Requirement
1. **Analysis Summary**: Briefly state what Step 0 found.
2. **Configuration Files**: Output the full content for `.vscode/launch.json`, `.vscode/tasks.json`, and `AGENTS.md`.
3. **Scripts**: Any shell/node scripts needed to glue the automation.

## Test
- Ensure everything works.

# Instruction
1. Start by scanning the current directory to understand the project state.
2. Remove unnecessary/outdated tasks and launches in `tasks.json` and `launch.json`.
3. Add fresh new tasks and launches following the steps.
4. Re-order and group the launches.
5. Re-order the tasks.
6. Commit the changes to the repository.

Attribution

kargnaskargnas
View sourceMore from kargnas →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

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

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

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', ...

694821 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 →