AG

Create, debug, and optimize VS Code agent customization files.

Install

mkdir -p .claude/skills/agent-customization-cgsog-jumpstarts && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/10689" && unzip -o skill.zip -d .claude/skills/agent-customization-cgsog-jumpstarts && rm skill.zip

Installs to .claude/skills/agent-customization-cgsog-jumpstarts

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Create, update, review, fix, or debug VS Code agent customization files (.instructions.md, .prompt.md, .agent.md, SKILL.md, copilot-instructions.md, AGENTS.md). Use for: saving coding preferences; troubleshooting why instructions/skills/agents are ignored or not invoked; configuring applyTo patterns; defining tool restrictions; creating custom agent modes or specialized workflows; packaging domain knowledge; fixing YAML frontmatter syntax.
443 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Intermediate

Key capabilities

  • Create customization files
  • Debug agent instructions
  • Configure applyTo patterns
  • Define tool restrictions
  • Validate YAML frontmatter

How it works

It provides a framework for creating and debugging agent-specific files like .instructions.md or .agent.md.

Inputs & outputs

You give it
Customization request
You get back
Agent configuration file

When to use agent-customization

  • Save coding preferences
  • Debug why instructions are ignored
  • Create custom agent modes

About this skill

Agent Customization

Decision Flow

PrimitiveWhen to Use
Workspace InstructionsAlways-on, applies everywhere in the project
File InstructionsExplicit via applyTo patterns, or on-demand via description
MCPIntegrates external systems, APIs, or data
HooksDeterministic shell commands at agent lifecycle points (block tools, auto-format, inject context)
Custom AgentsSubagents for context isolation, or multi-stage workflows with tool restrictions
PromptsSingle focused task with parameterized inputs
SkillsOn-demand workflow with bundled assets (scripts/templates)

Quick Reference

Consult the reference docs for templates, domain examples, advanced frontmatter options, asset organization, anti-patterns, and creation checklists. If the references are not enough, load the official documentation links for each primitive.

TypeFileLocationReference
Workspace Instructionscopilot-instructions.md, AGENTS.md.github/ or rootLink
File Instructions*.instructions.md.github/instructions/Link
Prompts*.prompt.md.github/prompts/Link
Hooks*.json.github/hooks/Link
Custom Agents*.agent.md.github/agents/Link
SkillsSKILL.md.github/skills/<name>/, .agents/skills/<name>/, .claude/skills/<name>/Link

User-level: {{USER_PROMPTS_FOLDER}}/ (*.prompt.md, *.instructions.md, *.agent.md; not skills) Customizations roam with user's settings sync

Creation Process

If you need to explore or validate patterns in the codebase, use a read-only subagent. If the ask-questions tool is available, use it to interview the user and clarify requirements.

If you are creating or updating an agent and discover the solution also needs a reusable skill, use this skill for the agent customization itself and reference the skill-creator skill for the skill-authoring portion of the work.

Follow these steps when creating any customization file.

1. Determine Scope

Ask the user where they want the customization:

  • Workspace: For project-specific, team-shared customizations → .github/ folder
  • User profile: For personal, cross-workspace customizations → {{USER_PROMPTS_FOLDER}}/

2. Choose the Right Primitive

Use the Decision Flow above to select the appropriate file type based on the user's need.

3. Create the File

Create the file directly at the appropriate path:

  • Use the location tables in each reference file
  • Include required frontmatter as needed
  • Add the body content following the templates

4. Validate

After creating:

  • Confirm the file is in the correct location
  • Verify frontmatter syntax (YAML between --- markers)
  • Check that description is present and meaningful

Edge Cases

Instructions vs Skill? Does this apply to most work, or specific tasks? Most → Instructions. Specific → Skill.

Skill vs Prompt? Both appear as slash commands in chat (type /). Multi-step workflow with bundled assets → Skill. Single focused task with inputs → Prompt.

Skill vs Custom Agent? Same capabilities for all steps → Skill. Need context isolation (subagent returns single output) or different tool restrictions per stage → Custom Agent.

Agent plus Skill? If a new agent needs a companion skill for a reusable domain workflow, create the .agent.md here and route the skill design and evaluation work through the skill-creator skill.

Hooks vs Instructions? Instructions guide agent behavior (non-deterministic). Hooks enforce behavior via shell commands at lifecycle events like PreToolUse or PostToolUse — they can block operations, require approval, or run formatters deterministically. See hooks reference.

When not to use it

  • General coding
  • Skill authoring (use skill-creator)

Limitations

  • Does not handle skill authoring directly
  • Requires manual validation

How it compares

It focuses specifically on the lifecycle of agent customization files rather than general agent development.

Compared to similar skills

agent-customization side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
agent-customization (this skill)03moNo flagsIntermediate
enhance-claude-memory115moReviewBeginner
windsurf-custom-prompts12moNo flagsBeginner
taskery05moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry