mirror of
https://github.com/github/awesome-copilot.git
synced 2026-03-13 04:35:12 +00:00
febaf64d94
* feat: add cli-mastery skill — interactive Copilot CLI training Adds cli-mastery, an interactive training system for the GitHub Copilot CLI. 8 modules covering slash commands, keyboard shortcuts, modes, agents, skills, MCP, configuration, and advanced techniques. Includes scenario challenges, a final exam, XP/leveling system, and SQL-based progress tracking. Source: https://github.com/DUBSOpenHub/copilot-cli-mastery (MIT) Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * fix: address review feedback on frontmatter and consistency - Switch description from folded block scalar (>) to single-quoted string per AGENTS.md documented format - Fix Module 7 heading: backtick-wrap @ separately from 'file mentions' to avoid implying '@ file mentions' is a literal command - Fix Final Exam Q6: change '@ + filename' to '@filename' with example to match the @src/auth.ts syntax taught in modules - Fix Final Exam Q7: add GEMINI.md to match Module 7 precedence list Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * fix: rename curriculum/ to references/ per agentskills.io spec Addresses review feedback from @aaronpowell on PR #915. The Agent Skills specification defines references/ as the standard directory for supplementary documentation that agents read on demand. - Renamed skills/cli-mastery/curriculum/ → references/ - Updated all path references in SKILL.md - Updated asset paths in docs/README.skills.md Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: DUBSOpenHub <DUBSOpenHub@users.noreply.github.com> Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
1.4 KiB
1.4 KiB
Module 4: Agent System
Built-in Agents
| Agent | Model | Best For | Key Trait |
|---|---|---|---|
explore |
Haiku | Fast codebase Q&A | Read-only, <300 words, safe to parallelize |
task |
Haiku | Running commands (tests, builds, lints) | Brief on success, verbose on failure |
general-purpose |
Sonnet | Complex multi-step tasks | Full toolset, separate context window |
code-review |
Sonnet | Analyzing code changes | Never modifies code, high signal-to-noise |
Custom Agents — define your own in Markdown
| Level | Location | Scope |
|---|---|---|
| Personal | ~/.copilot/agents/*.md |
All your projects |
| Project | .github/agents/*.md |
Everyone on this repo |
| Organization | .github-private/agents/ in org repo |
Entire org |
Agent file anatomy
---
name: my-agent
description: What this agent does
tools:
- bash
- edit
- view
---
# Agent Instructions
Your detailed behavior instructions here.
Agent orchestration patterns
- Fan-out exploration — Launch multiple
exploreagents in parallel to answer different questions simultaneously - Pipeline —
explore→ understand →general-purpose→ implement →code-review→ verify - Specialist handoff — Identify task →
/agentto pick specialist → review with/fleetor/tasks
Key insight: The AI automatically delegates to subagents when appropriate.