pantheon-ai/github-copilot-models
Query and display available GitHub Copilot AI models with their capabilities, context limits, and features. Use when: "what models are available", "show copilot models", "list github models", "check model capabilities", "switch models". Examples: - user: "What models can I use with GitHub Copilot?" → fetch and display available models - user: "Show me models with vision support" → filter models by capability - user: "Which model has the largest context window?" → compare model specifications - user: "List all GPT-5 models" → filter by model family
Overall
score
89%
Does it follow best practices?
Validation 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 an excellent skill description that hits all the marks. It provides specific capabilities, includes a comprehensive 'Use when' clause with natural trigger terms, and is clearly distinguishable from other skills through its GitHub Copilot focus. The examples section adds valuable context for edge cases like filtering and comparing models.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Query and display available GitHub Copilot AI models with their capabilities, context limits, and features.' The examples further demonstrate specific actions like filtering by capability, comparing specifications, and filtering by model family. | 3 / 3 |
Completeness | Clearly answers both what (query and display GitHub Copilot AI models with capabilities, context limits, features) AND when (explicit 'Use when:' clause with multiple trigger phrases). The examples section further reinforces when to use the skill. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'what models are available', 'show copilot models', 'list github models', 'check model capabilities', 'switch models'. The examples add more natural phrases like 'What models can I use' and 'Which model has the largest context window'. | 3 / 3 |
Distinctiveness Conflict Risk | Very clear niche focused specifically on GitHub Copilot AI models. The triggers are distinct ('copilot models', 'github models') and unlikely to conflict with general coding skills or other model-related skills due to the specific GitHub Copilot context. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill with excellent executable examples and clear workflows. The main weakness is length - the anti-patterns and decision framework sections, while valuable, make the skill verbose for what is essentially a model-querying task. The content would benefit from splitting detailed guidance into separate reference files.
Suggestions
Move the 'Anti-Patterns' section to a separate ANTI-PATTERNS.md file and link to it, keeping only a brief warning in the main skill
Consider moving 'Decision Framework' to a separate file or condensing it to 3-4 bullet points in the main skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Content is mostly efficient but includes some redundancy - the 'Decision Framework' and 'Anti-Patterns' sections, while useful, add significant length. The troubleshooting and model selection criteria sections could be tightened. | 2 / 3 |
Actionability | Excellent executable examples throughout - bash commands are copy-paste ready, jq queries are complete and specific, and the script options table provides clear usage patterns. Every section includes concrete, runnable commands. | 3 / 3 |
Workflow Clarity | Clear sequences with validation steps - the 'Switching Models' section includes explicit validation ('Test the model is active'), authentication failure recovery is documented, and the decision framework provides clear criteria for when to use each approach. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but everything is inline in one file. The 'Example Workflows' and 'Anti-Patterns' sections could be split into separate reference files, and the script options table could link to a more detailed reference. | 2 / 3 |
Total | 10 / 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.
Install with Tessl CLI
npx tessl i pantheon-ai/github-copilot-modelsReviewed
Table of Contents