Using skills

Skills turn recurring tasks into reusable workflows that ChatGPT can follow consistently, reducing the need to re-explain steps and requirements while ensuring high-quality results.
Using skills
Create reusable workflows that guide ChatGPT through recurring tasks.
Skills turn the way you already work into reusable workflows that ChatGPT can follow consistently—so you spend less time re-explaining steps, formats, and requirements, and more time getting to a solid result.
If you’ve ever found yourself reusing the same prompt or pasting the same template again and again, skills are designed to fix that.
A skill is a reusable, shareable workflow that tells ChatGPT how to do a specific task. Rather than starting from scratch each time, you define the process once so it can be applied reliably whenever the task comes up.
A skill typically includes:
- Name and description: Help ChatGPT recognize when the skill is relevant.
- Workflow instructions: Step-by-step guidance for the workflow—usually written in a file called SKILL.md.
- Resources: Supporting materials the workflow depends on, like templates, examples, brand guidelines, schemas, or tool access.
Skills are most useful when getting a good output from ChatGPT depends on following a repeatable approach—especially when tasks involve multiple steps, structured formats, or specific requirements.
Skills help with:
- Consistency: Fewer missed sections, less drift in tone or format, and closer adherence to preferred format.
- Built-in best practices: Lightweight enough for everyday users, but grounded in SME-approved workflows.
- Sharing the playbook: Teams can use the same standard process directly in ChatGPT instead of relying on informal or undocumented knowledge.
- Reuse across surfaces: Build once and apply broadly across different chats and use cases.
A SKILL.md file is the skill’s playbook: a plain-text set of instructions that tells ChatGPT how to run a workflow consistently. It’s written in Markdown, a lightweight formatting style that uses simple symbols—like "#" for headings and "-" for lists—so the file is easy to read and edit in most tools.
Because it’s plain text and Markdown-based, SKILL.md is portable. It can be shared, versioned, and reused across tools. It’s also designed as an open standard, so similar patterns may appear in other AI apps and platforms.
A typical SKILL.md file defines:
- What the skill does
- Required inputs
- Step-by-step instructions
- Required output format
- Final checks before completion
Types of Skills
- Reusable processes (multi-step workflows): Tasks where sequence matters and the goal is to follow a defined playbook.
- Tool-based workflows (consistent use of systems): Work that depends on reliably pulling or combining information from specific tools.
- Conventions and standards (voice, structure, quality bar): Workflows that enforce consistent tone or format.
Design tip: Skills often work best as small building blocks you can mix and match, rather than one massive end-to-end skill.
How to Build and Install
- Draft the skill: Ask ChatGPT to "Build me a skill..." and provide the job-to-be-done, inputs, process, and output format.
- Install: Review the generated draft and select Install to add it to your workspace.
- Use: Once enabled, ChatGPT can use it automatically or via @-mention.
Skills vs. GPTs vs. Projects
- Skills: Reusable workflows for specific tasks.
- GPTs: Custom versions of ChatGPT for team expertise or specific projects.
- Projects: Shared context and files for teams working towards an end goal.
Source: OpenAI News









