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.
80
71%
Does it follow best practices?
Impact
99%
7.61xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/copilot-sdk/skills/copilot-sdk/SKILL.mdQuality
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 strong skill description that clearly identifies its domain (GitHub Copilot SDK), lists specific concrete capabilities, and provides explicit trigger guidance with both a 'Use when' clause and a 'Triggers on' keyword list. It is well-differentiated from other skills and uses appropriate third-person voice throughout.
| 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' (explicit 'Use when...' clause with multiple trigger scenarios, plus an explicit 'Triggers on' list). | 3 / 3 |
Trigger Term Quality | Includes a rich set of natural trigger terms users would actually say: 'Copilot SDK', 'GitHub SDK', 'agentic app', 'embed Copilot', 'programmable agent', 'MCP server', 'custom agent'. These cover multiple natural variations of how users would phrase requests. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche around GitHub Copilot SDK specifically. The trigger terms like 'Copilot SDK', 'GitHub SDK', and 'embed Copilot' are very specific and unlikely to conflict with general coding or other AI-related skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with complete, executable code examples across four languages, but it is extremely verbose due to repeating nearly identical patterns for every language in every section. This creates a massive token footprint that could be reduced by 60-70% through progressive disclosure - showing one canonical language inline and linking to language-specific reference files. The lack of validation checkpoints in workflows and the monolithic structure significantly reduce its effectiveness as a skill file.
Suggestions
Show one canonical language (e.g., TypeScript) inline for each feature and move Python/Go/.NET variants to separate reference files (e.g., PYTHON_EXAMPLES.md, GO_EXAMPLES.md) linked from each section.
Remove the 'How Tools Work' section - Claude already understands tool calling patterns; the code examples are self-explanatory.
Add validation checkpoints after installation (e.g., 'Verify: run the Quick Start example and confirm output is 4') and after CLI authentication setup.
Move the configuration tables, event types reference, and common patterns into a separate REFERENCE.md file, keeping only the most essential information in the main skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose - repeats nearly identical code examples across 4 languages for every feature (Quick Start, Streaming, Custom Tools, MCP, Custom Agents, System Message, External CLI). This massively inflates token count. The 'How Tools Work' section explains concepts Claude already knows. Much of this could be condensed by showing one language with notes on cross-language differences. | 1 / 3 |
Actionability | Provides fully executable, copy-paste ready code examples across all four supported languages. Installation commands, run commands, and complete working examples are provided for each feature area. | 3 / 3 |
Workflow Clarity | Prerequisites and installation steps are clear, and the progression from Quick Start to advanced features is logical. However, there are no validation checkpoints (e.g., verifying installation succeeded, confirming CLI authentication works before proceeding), and the error handling section is isolated rather than integrated into workflows. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text (~600+ lines) with no references to separate files for detailed content. The 4-language code examples for each feature should be split into language-specific reference files, with the SKILL.md showing one canonical example and linking to others. Configuration tables, event types, and advanced patterns could all be separate documents. | 1 / 3 |
Total | 7 / 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 (915 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- github/awesome-copilot
- Commit
8395dce
- 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.