This skill provides guidance for creating agents and applications with the GitHub Copilot SDK. It should be used when the user wants to create, modify, or work on software that uses the GitHub Copilot SDK in TypeScript, Python, Go, or .NET. The skill covers SDK usage patterns, CLI configuration, custom tools, MCP servers, and custom agents.
Install with Tessl CLI
npx tessl i github:intellectronica/agent-skills --skill copilot-sdk96
Does it follow best practices?
Agent success when using this skill
Validation for skill structure
TypeScript SDK event handling
Correct npm package
100%
100%
Handler before send
100%
100%
Correct content access
0%
100%
Correct delta access
100%
100%
Streaming enabled
100%
100%
Session idle handling
100%
100%
assistant.message used
0%
100%
Session cleanup
100%
100%
Client cleanup
100%
100%
Valid model ID
100%
100%
Without context: $0.3307 · 1m 29s · 16 turns · 480 in / 2,939 out tokens
With context: $0.4348 · 59s · 19 turns · 20 in / 3,374 out tokens
Python SDK with custom tools
Correct pip package
100%
100%
Pydantic tool params
100%
100%
define_tool decorator
100%
100%
Handler before send
100%
100%
Python enum .value access
0%
100%
Python delta_content naming
70%
50%
Correct content access
100%
100%
Session/client cleanup
100%
100%
Valid model ID
100%
100%
Wait for completion
100%
100%
Without context: $0.8441 · 3m 35s · 30 turns · 578 in / 5,746 out tokens
With context: $0.3616 · 52s · 18 turns · 51 in / 2,604 out tokens
Custom agent and MCP config
Agent in .github/agents/
0%
0%
YAML frontmatter present
0%
100%
description field present
70%
100%
Correct target value
0%
100%
Tools restriction correct
40%
100%
infer field set
0%
100%
MCP config key
100%
100%
MCP server name
100%
100%
MCP secret reference
100%
100%
MCP config location noted
0%
100%
local type field
0%
100%
Without context: $0.2445 · 1m 7s · 12 turns · 60 in / 3,903 out tokens
With context: $0.3349 · 1m 6s · 16 turns · 65 in / 3,169 out tokens
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.