Create reusable custom agent files tailored to specific roles and workflows.
The material indicates a prompt-only skill with no required secrets and no declared network endpoints, so overall risk is low. The main caution is that it references related external guidance/documents for behavior, but there is no evidence of code execution or sensitive local/remote data access.
The material explicitly states that no keys or environment variables are required, and it does not ask for tokens, account credentials, or other sensitive authentication data, so credential exposure appears minimal.
No remote endpoint is declared. The content only describes a prompt workflow for generating an `.agent.md` file, with no evidence of sending user data to external services.
The objective check marks it as prompt-only. The README mainly instructs how to summarize conversation context and draft an agent file, with no indication of spawning local processes, running scripts, or invoking system commands.
The material only mentions 'review the conversation history' and 'save it,' which reads like authoring guidance at the skill level. It does not declare direct access to arbitrary local files, system resources, or data beyond what is needed to generate an `.agent.md`.
A positive factor is that it is marked open-source and points to GitHub/microsoft/vscode, which supports auditability. However, the mapping between that repository and this specific skill, as well as license, maintenance status, and community adoption, is not clearly established in the provided material, so some supply-chain caution remains warranted.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "create-agent" skill from askskill: 1. Download https://raw.githubusercontent.com/microsoft/vscode/main/extensions/copilot/assets/prompts/skills/create-agent/SKILL.md 2. Save it as ~/.claude/skills/create-agent/SKILL.md 3. Reload skills and tell me it's ready
Create a .agent.md file for a frontend developer role. This agent should specialize in React, TypeScript, component refactoring, performance optimization, and code review, and include role definition, working principles, input/output format, common tasks, and constraints.
A .agent.md draft tailored for frontend development workflows.
Create a custom .agent.md agent configuration for a product manager focused on requirement analysis, PRD writing, competitor research, and release planning. Define the output structure, decision criteria, and communication style.
An agent specification file for product planning and requirement workflows.
Help me create a .agent.md file for a research assistant suited to literature review, research question breakdown, evidence synthesis, and report writing. Include citation rules, fact-checking requirements, and response boundaries.
A custom agent configuration for research and evidence-analysis tasks.
Related skill: agent-customization. Load and follow agents.md for template and principles.
Guide the user to create an .agent.md.
First, review the conversation history. If the user has been using the agent in a specialized way (e.g., restricting tools, following a specific persona, focusing on certain file types), generalize that into a custom agent. Extract:
If no clear specialization emerges from the conversation, clarify:
Remember to follow the agent-customization guidelines to create highly effective agents.
Validate Azure DevOps pipeline changes and troubleshoot builds and YAML faster.
Update the GitHub Copilot CLI or SDK to a newer version.
Upgrade Anthropic SDKs, migrate versions, and fix dependency or typing issues.
Generate or update chat customization files for AI coding agents.
Find and read Code OSS dev build logs for faster debugging.
Merge session branch changes back into the base branch cleanly.
Generate reusable AI agent skills and draft configs from website documentation.
Manage agent reputation, expertise claims, job bidding, and task delivery workflows.
Create, refine, validate, and restructure AgentSkills and SKILL.md files.
Collaborate with AI agents to solve complex tasks, search knowledge, and use tools.
Set up portable agents aligned with your codebase, workflows, and engineering standards.
Build multi-agent workflows to automate coding, analysis, and task orchestration.