agent-customization

Create a .instructions.md file in .github/instructions/ with YAML frontmatter containing a description and optional applyTo glob pattern. Use a keyword-rich description starting with "Use when..." so the agent can discover it on demand.

Both appear as slash commands in chat. A prompt file handles a single focused task with parameterized inputs, while a skill provides a multi-step workflow bundled with scripts, references, and assets in its own folder.

Silent failures usually come from YAML frontmatter errors like unescaped colons, tabs instead of spaces, or a name that does not match the folder. Quote descriptions containing colons and verify the file is in the correct location.

Use hooks when behavior must be enforced deterministically, such as blocking dangerous commands or auto-formatting after edits. Instructions only guide agent behavior non-deterministically, while hooks run shell commands at lifecycle events like PreToolUse.

Yes, applyTo "**" loads the instruction into the context window on every interaction regardless of relevance. Use specific globs like **/*.py or src/api/** unless the instruction truly applies to all files.