copilot-sdk
Build agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming responses, managing sessions, connecting to MCP servers, or creating custom agents. Triggers on Copilot SDK, GitHub SDK, agentic app, embed Copilot, programmable agent, MCP server, custom agent.
82
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
100%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-crafted skill description that excels across all dimensions. It provides specific capabilities, comprehensive trigger terms that developers would naturally use, explicit 'Use when' guidance, and a distinctive focus on GitHub Copilot SDK that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'embedding AI agents in apps', 'creating custom tools', 'implementing streaming responses', 'managing sessions', 'connecting to MCP servers', 'creating custom agents'. | 3 / 3 |
Completeness | Clearly answers both what ('Build agentic applications with GitHub Copilot SDK') and when ('Use when embedding AI agents...') with explicit trigger terms listed separately. The 'Triggers on' clause provides additional explicit guidance. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'Copilot SDK', 'GitHub SDK', 'agentic app', 'embed Copilot', 'programmable agent', 'MCP server', 'custom agent'. These are terms developers would naturally use when seeking this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific focus on GitHub Copilot SDK and agentic applications. The combination of 'Copilot SDK', 'GitHub SDK', and 'MCP server' creates a clear niche unlikely to conflict with general coding or other AI SDK skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides excellent actionable, executable code examples across four languages with comprehensive API coverage. However, it suffers from being overly long and monolithic - the same patterns repeated for each language create significant redundancy. The lack of progressive disclosure (no external file references) and missing validation checkpoints in workflows reduce its effectiveness as a quick reference.
Suggestions
Split language-specific examples into separate files (e.g., TYPESCRIPT.md, PYTHON.md, GO.md, DOTNET.md) and keep only one primary language in the main skill with links to others
Move reference tables (Event Types, Client Configuration, Session Configuration) to a separate REFERENCE.md file
Add validation steps after installation (e.g., 'Verify installation: run this test script and expect this output')
Remove explanatory text that Claude already knows (e.g., 'When you define a tool, you tell Copilot...') and let the code examples speak for themselves
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some unnecessary explanations (e.g., 'When you define a tool, you tell Copilot: 1. What the tool does...') and repeats similar code patterns across all four languages for every feature, which inflates token count significantly. | 2 / 3 |
Actionability | Excellent executable code examples across all four languages (TypeScript, Python, Go, .NET). Every feature includes copy-paste ready code with proper imports, and the examples are complete and runnable. | 3 / 3 |
Workflow Clarity | Prerequisites and installation steps are clear, but the skill lacks explicit validation checkpoints. For example, there's no guidance on verifying the SDK installation worked, no troubleshooting for common setup issues, and error handling is shown but not integrated into workflows. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text at ~600+ lines with no references to external files. Content like the full API reference tables, all four language examples for every feature, and the complete interactive CLI assistant code should be split into separate reference files. | 1 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (864 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- 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.