copilot-sdk
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
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-structured skill description that clearly identifies its niche (GitHub Copilot SDK) and provides explicit trigger conditions. The description uses proper third-person voice and includes relevant technical keywords. The main weakness is that the capabilities listed are more topic areas than concrete actions, making it slightly less specific about what operations it enables.
Suggestions
Replace topic areas with concrete actions, e.g., 'Implements custom tools, configures CLI settings, integrates MCP servers, and builds custom agents' instead of 'covers SDK usage patterns, CLI configuration...'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (GitHub Copilot SDK) and mentions some actions like 'create, modify, or work on software' and covers 'SDK usage patterns, CLI configuration, custom tools, MCP servers, and custom agents', but these are more topic areas than concrete actions like 'extract', 'fill', 'merge'. | 2 / 3 |
Completeness | Clearly answers both what ('provides guidance for creating agents and applications with the GitHub Copilot SDK', covers 'SDK usage patterns, CLI configuration, custom tools, MCP servers, and custom agents') and when ('when the user wants to create, modify, or work on software that uses the GitHub Copilot SDK'). | 3 / 3 |
Trigger Term Quality | Includes good natural keywords users would say: 'GitHub Copilot SDK', 'TypeScript', 'Python', 'Go', '.NET', 'agents', 'MCP servers', 'custom tools'. These are terms developers would naturally use when seeking help with this SDK. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting GitHub Copilot SDK specifically, with distinct language identifiers (TypeScript, Python, Go, .NET) and specific concepts (MCP servers, custom agents). Unlikely to conflict with general coding skills or other SDK skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an exemplary skill file that efficiently covers a complex multi-language SDK. It provides actionable code examples, clear architecture overview, and well-organized progressive disclosure to detailed references. The troubleshooting table and critical notes about common pitfalls add significant practical value.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, using tables and code snippets without explaining concepts Claude already knows. No unnecessary padding about what SDKs are or how JSON-RPC works. | 3 / 3 |
Actionability | Provides executable TypeScript code, concrete installation commands for all languages, and specific model IDs. The quick start example is copy-paste ready with critical notes about handler registration timing. | 3 / 3 |
Workflow Clarity | The quick start demonstrates clear sequencing (start → createSession → register handler → send → destroy → stop) with an explicit critical note about handler registration order. The architecture diagram clarifies the flow. | 3 / 3 |
Progressive Disclosure | Excellent structure with a concise overview pointing to well-organized reference files (working-examples.md, event-system.md, troubleshooting.md, cli-agents-mcp.md). External documentation links are clearly categorized and one level deep. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Reviewed
Table of Contents
Is this your skill?
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.