Install any skill in seconds. Free to start, no credit card required.
Get Started Free →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.
.claude/skills/majiayu000-agent-customization/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 20% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 173% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 43% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -15% | 0% |
| Primitive | When to Use | |-----------|-------------| | Workspace Instructions | Always-on, applies everywhere in the project | | File Instructions | Explicit via applyTo patterns, or on-demand via description | | MCP | Integrates external systems, APIs, or data | | Custom Agents | Subagents for context isolation, or multi-stage workflows with tool restrictions | | Prompts | Single focused task with parameterized inputs | | Skills | On-demand workflow with bundled assets (scripts/templates) |
Consult the reference docs for templates, domain examples, advanced frontmatter options, asset organization, anti-patterns, and creation checklists.
| Type | File | Location | Key Field | Reference | |------|------|----------|-----------|---------| | Workspace Instructions | copilot-instructions.md, AGENTS.md | .github/ or root | N/A (always applies) | Link | | File Instructions | *.instructions.md | .github/instructions/ | applyTo (explicit), description (on-demand) | Link | | Prompts | *.prompt.md | .github/prompts/ | description (user-invoked) | Link | | Custom Agents | *.agent.md | .github/agents/ | description (on-demand), infer (subagent) | Link | | Skills | SKILL.md | .github/skills/<name>/ | description (on-demand) | Link |
User-level: {{USER_PROMPTS_FOLDER}}/ (.prompt.md, .instructions.md, .agent.md; not skills) Customizations roam with user's settings sync
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.
Follow these steps when creating any customization file.
Ask the user where they want the customization:
.github/ folder{{USER_PROMPTS_FOLDER}}/Use the Decision Flow above to select the appropriate file type based on the user's need.
Create the file directly at the appropriate path:
After creating:
--- markers)description is present and meaningfulInstructions vs Skill? Does this apply to most work, or specific tasks? Most → Instructions. Specific → Skill.
Skill vs Prompt? 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.
Other measured skills in the registry, with their headline benchmark lift.