CtrlK
BlogDocsLog inGet started
Tessl Logo

jit-regression-test

Extract a standalone JIT regression test case from a given GitHub issue and save it under the JitBlue folder. USE FOR: creating JIT regression tests, extracting repro code from dotnet/runtime issues, "write a test for this JIT bug", "create a regression test for issue #NNNNN", converting issue repro to xunit test. DO NOT USE FOR: non-JIT tests (use standard test patterns), debugging JIT issues without a known repro, performance benchmarks (use performance-benchmark skill).

76

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

87%Weight 40%Scale 1-3

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

The body is actionable and well-structured with concrete, executable examples and clear sequencing, but it lacks an explicit verification step confirming the generated test actually reproduces the issue or builds successfully. Adding a build/run validation checkpoint would round out the workflow.

Suggestions

Add a final verification step (e.g., 'Build and run the test to confirm it reproduces the reported bug before the fix and passes after') to close the workflow_clarity validation gap.

De-duplicate the license header by showing it once and referencing it in the second example, slightly improving conciseness.

Note how to register the test in Regression_ro_2.csproj with a concrete one-line example so users don't have to infer the registration format.

DimensionReasoningScore

Conciseness

Lean and task-focused; it assumes Claude's competence without explaining JIT, xunit, or NoInlining, and every section drives toward action. The only mild redundancy is the license header appearing in both C# examples, which is not enough to drop it below the top anchor.

3 / 3

Actionability

Provides fully executable, copy-paste-ready code: a complete C# test file (Runtime_99391) with NoInlining usage, a full .csproj example, exact target paths, and concrete naming conventions — matching the top anchor.

3 / 3

Workflow Clarity

Steps 1–4 are clearly sequenced and there is a useful pre-flight 'Do NOT create a test when…' decision gate, but there is no post-creation validation checkpoint (e.g., build the test, run it to confirm it reproduces the bug) — a verification gap that caps this dimension at 2.

2 / 3

Progressive Disclosure

A single self-contained file with well-organized Step and Tips sections and no nested or missing references; for a skill of this size with no need for external reference files, the clean section structure earns the top anchor.

3 / 3

Total

11

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 specific, trigger-rich, and clearly scoped with both affirmative and negative guidance, making it highly distinguishable and unlikely to fire for the wrong skill. It cleanly satisfies every dimension at the top anchor.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Extract a standalone JIT regression test case from a given GitHub issue and save it under the JitBlue folder', 'extracting repro code from dotnet/runtime issues', 'converting issue repro to xunit test' — matching the top anchor's 'multiple specific concrete actions'.

3 / 3

Completeness

Explicitly answers both 'what' (extract and save a JIT regression test under JitBlue) and 'when' via a clearly labeled 'USE FOR:' trigger clause, satisfying the top anchor.

3 / 3

Trigger Term Quality

Includes natural phrases users would actually say — 'write a test for this JIT bug', 'create a regression test for issue #NNNNN', 'creating JIT regression tests' — giving good coverage of common variations, not just jargon.

3 / 3

Distinctiveness Conflict Risk

Clear JIT-test niche with distinct triggers plus an explicit 'DO NOT USE FOR' clause disambiguating non-JIT tests and performance benchmarks, making misfires unlikely.

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
dotnet/runtime
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.