CtrlK
BlogDocsLog inGet started
Tessl Logo

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

64

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/file-test-bug/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is well-structured, actionable, and sequenced with a required pre-issue diagnosis checkpoint. It could improve by adding error-recovery guidance for edge cases and trimming the minor redundancy around agent-metadata.md inclusion.

Suggestions

Add a brief feedback loop for edge cases, e.g., what to do when junit.xml has no matching failures or when agent-metadata.md is missing for a test run.

Remove the redundancy between step 6, the template's <details> block, and the "Important" section regarding including agent-metadata.md verbatim — state the requirement once and reference it.

Provide a concrete example invocation of github-mcp-server-create_issue with the owner/repo/title/labels/body fields filled for one sample failure to make the action fully copy-paste ready.

DimensionReasoningScore

Conciseness

The body is lean with numbered steps and a concrete template, but has minor redundancy where the "Important" note and step 6 restate including agent-metadata.md verbatim, which is already shown in the template.

4 / 5

Actionability

Concrete file paths, a named MCP tool (github-mcp-server-create_issue), and a full issue-body template give mostly executable guidance, with minor gaps from placeholders and the absence of a complete MCP invocation example.

4 / 5

Workflow Clarity

Steps 1-7 are clearly sequenced with an explicit diagnose-before-create checkpoint, but the workflow lacks error-recovery feedback loops for cases like no failures found or missing metadata.

4 / 5

Progressive Disclosure

The skill is a single self-contained file with clear sections (Input, Steps, Important) and no nested references, but at ~55 lines with a sizable inlined template it slightly exceeds the simple-skill exception threshold, leaving a minor organization gap.

4 / 5

Total

16

/

20

Passed

Description

78%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise, third-person, and clearly answers both what the skill does and when to use it via explicit trigger phrases. It is strong on completeness and trigger coverage, slightly less comprehensive on enumerated capabilities.

DimensionReasoningScore

Specificity

"File a GitHub issue for local integration test failures" names the domain plus one concrete action (filing an issue), matching the anchor for 1-2 concrete actions without being comprehensive.

3 / 5

Completeness

It states a clear "what" (file a GitHub issue for integration test failures) and an explicit "when" via concrete TRIGGERS phrases, satisfying the anchor for clearly answering both with concrete trigger guidance.

5 / 5

Trigger Term Quality

The TRIGGERS list provides six natural phrases with synonyms ("file test bug", "create bug for test", "report test failure") plus the technical "junit failure", giving good coverage though a few natural variations and extensions are missing.

4 / 5

Distinctiveness Conflict Risk

The test-failure-to-issue niche with specific triggers is mostly distinct, with only minor overlap risk against a generic GitHub-issue-filing skill.

4 / 5

Total

16

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
microsoft/github-copilot-for-azure
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.