Recommended Free Tools
GitHub Copilot instructions provide persistent guidance within a defined scope; prompt files are reusable templates you invoke for a particular task; and agent skills package instructions with resources such as scripts for Copilot to load when relevant. Choose based on whether you want guidance applied automatically, a prompt you run deliberately, or a repeatable workflow package—and check that your Copilot environment supports the feature.
How prompts, skills, and instructions differ
| Type | What it provides | How it is activated | Best fit | Documented project location |
|---|---|---|---|---|
| Custom instructions | Persistent context and guidance within a defined scope | Automatically, when the request or files fall within that scope | Project conventions, standards, and guidance that should inform relevant work | .github/copilot-instructions.md; .github/instructions/*.instructions.md; agent instruction files such as AGENTS.md |
| Prompt files | Reusable, standalone prompt templates that may accept input variables | Manually, by referencing or selecting the prompt file | Focused tasks you want to repeat with different inputs, such as generating tests or applying a review checklist | .github/prompts/*.prompt.md |
| Agent skills | A folder containing instructions and potentially scripts and other resources | Copilot can load the skill when it is relevant to the prompt | Repeatable workflows that benefit from instructions plus supporting files | .github/skills/<skill-name>/SKILL.md is one documented project path; other supported paths exist |
These definitions, examples, and paths are from GitHub’s Copilot customization cheat sheet. Treat the locations as documented examples, not universal requirements: available paths and support depend on the Copilot product surface.
![The Microsoft Copilot Bible for Beginners & Busy Professionals: [5 in 1] How to Boost Productivity, Save Hours Every Week, and Automate Your Work with AI](https://m.media-amazon.com/images/I/41tTEg9fueL._SL160_.jpg)
As an Amazon Associate I earn from qualifying purchases.
When to use custom instructions
Use custom instructions for guidance that should accompany many relevant Copilot interactions rather than a single manually launched task. For example, repository conventions can apply broadly, while instructions tied to certain files can be limited to matching paths.
Quick wins for a faster PC:
Repair Windows errors before they cause bigger problemsFix Now →Scan for outdated or missing drivers - takes under a minuteDriver Scan →Repository-wide guidance
GitHub documents repository-wide instructions in .github/copilot-instructions.md. They apply to requests made in repository context.
#1 Best Overall
Guidance for matching files
Path-specific instructions use NAME.instructions.md files in or below .github/instructions, with applyTo glob patterns defining the paths they match. When a matching file is in scope and repository-wide instructions also exist, GitHub says both are used. This is not a general rule that one instruction type overrides the other.
On GitHub.com, path-specific instructions are currently supported for Copilot cloud agent and code review; that support statement should not be assumed to apply to every IDE or Copilot feature. See GitHub’s repository custom-instructions guide for setup and scope details.
When to use a prompt file
Choose a prompt file when you want a reusable template for a discrete task and want to decide when to run it. You can provide different inputs each time—for example, use the same test-generation prompt for different functions or use a review checklist on selected changes.
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
Unlike persistent custom instructions, a prompt file is manually invoked: the user references or selects it. GitHub documents .github/prompts/*.prompt.md as a project location. See the customization cheat sheet and response customization overview for details and environment-specific considerations.
When to use an agent skill
Use an agent skill when a task is better treated as a repeatable workflow than as a one-off prompt. A skill can combine directions with supporting files, making it a fit for specialized work that needs more than a standalone template.
GitHub Docs describes agent skills as “folders of instructions, scripts, and resources that Copilot can load when relevant to improve its performance in specialized tasks.” Skills are relevance-loaded rather than deliberately selected like prompt files. One documented project path is .github/skills/<skill-name>/SKILL.md, but other supported paths exist. Consult the cheat sheet for the target environment’s supported locations.
A practical way to choose
- Ask how the guidance should start. If it should accompany relevant work automatically, use custom instructions. If you want to launch a template yourself, use a prompt file. If Copilot should load a packaged workflow when relevant, use a skill.
- Define the scope. Use repository-wide instructions for broad project context and path-specific instructions for guidance tied to matching files. Keep a prompt focused on the task you invoke; use a skill when the workflow benefits from bundled resources.
- Check the target surface. Confirm that the IDE, GitHub.com feature, or agent you use supports the chosen customization and its location. GitHub documents differences across environments in its customization cheat sheet and response customization overview.
What these customizations do not guarantee
Instructions are guidance, not a hard enforcement mechanism. GitHub cautions that Copilot may not follow instructions identically every time because its behavior is non-deterministic. The documentation describes different mechanisms and use cases; it does not establish that one type always produces better results than another.
Quick Recap
Best Value
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
