file-test-bug
File a GitHub issue for local integration test failures. TRIGGERS: file test bug, report test failure, create bug for test, integration test failed, test failure issue, junit failure
93
95%
Does it follow best practices?
Impact
81%
2.02xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Quality
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-crafted, focused skill description that clearly identifies its purpose and provides strong trigger terms. Its main weakness is that it describes only a single action rather than elaborating on the specific steps or capabilities involved (e.g., parsing test output, extracting stack traces, formatting the issue). The explicit TRIGGERS list is a strong approach for disambiguation.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names a specific action ('File a GitHub issue') and a specific domain ('local integration test failures'), but it only describes one concrete action rather than listing multiple specific capabilities. | 2 / 3 |
Completeness | The description clearly answers 'what' (file a GitHub issue for local integration test failures) and 'when' (explicit TRIGGERS list with multiple trigger phrases). The trigger terms serve as an explicit 'Use when...' equivalent. | 3 / 3 |
Trigger Term Quality | The TRIGGERS section includes a good variety of natural phrases users would say: 'file test bug', 'report test failure', 'create bug for test', 'integration test failed', 'test failure issue', 'junit failure'. These cover multiple natural variations including tool-specific terms like 'junit'. | 3 / 3 |
Distinctiveness Conflict Risk | This skill has a very clear niche: filing GitHub issues specifically for integration test failures. The combination of 'GitHub issue' + 'test failures' + specific trigger terms like 'junit failure' makes it highly distinct and unlikely to conflict with general issue-filing or general testing 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 a well-crafted skill that efficiently communicates a specific workflow for filing GitHub issues from test failures. It provides concrete file paths, tool names, and a complete issue template while maintaining a clear step sequence with an explicit validation checkpoint (diagnosis before issue creation). The constraint about preserving full agent-metadata.md contents is clearly called out.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient. It doesn't explain what GitHub issues are, what JUnit is, or how MCP servers work. Every section serves a purpose—input requirements, step sequence, issue template, and a critical constraint about not truncating logs. | 3 / 3 |
Actionability | Provides a concrete issue template with exact field values (owner, repo, labels), specific file paths to read (tests/reports/junit.xml, agent-metadata.md), and a precise MCP tool name (github-mcp-server-create_issue). The template is copy-paste ready with clear placeholders. | 3 / 3 |
Workflow Clarity | The 7-step workflow is clearly sequenced with an explicit validation checkpoint at step 6 ('REQUIRED - Write diagnosis BEFORE creating issue'). This ensures analysis happens before the destructive action of creating an issue, and the diagnosis step includes a structured feedback loop (analyze → compare → identify root cause → suggest fix). | 3 / 3 |
Progressive Disclosure | For a single-purpose skill under 80 lines with no need for external references, the content is well-organized into clear sections (Input, Steps, Important). The inline issue template is appropriately placed since it's the core deliverable of the skill. | 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.
- Repository
- microsoft/github-copilot-for-azure
- Commit
915f809
- 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.