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).

70

Quality

85%

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

82%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.

A highly actionable, well-structured skill body with concrete templates and a real example. The main gaps are a missing build/run validation checkpoint and minor duplication between the steps and tips.

Suggestions

Add an explicit Step 5 validation checkpoint: build the test and run it to confirm it compiles and reproduces the original failure before considering it done, with a fix-and-retry loop if it does not.

De-duplicate the .csproj guidance: state the "register in Regression_ro_2.csproj unless env vars are needed" rule once (in Step 4) and have Tips reference it rather than restate it.

Consider moving the full Runtime_99391 worked example into a short reference snippet or trimming it to the minimal distinguishing lines, keeping the template as the primary inline example.

DimensionReasoningScore

Conciseness

The body is largely efficient with concrete code and brief conventions, but the .csproj guidance is restated between Step 4 and Tips, and the template plus the full Runtime_99391 example carry some redundancy, keeping it just below lean.

4 / 5

Actionability

Provides copy-paste-ready guidance: exact folder paths, file/class naming conventions, a full licensed C# template, a real Runtime_99391 example, and a complete .csproj with CLRTestEnvironmentVariable — covering the common cases fully.

5 / 5

Workflow Clarity

Steps 1–4 are clearly sequenced with an explicit upfront guard ("Do NOT create a test when..."), but there is no validation checkpoint confirming the test builds, runs, or actually reproduces the bug, leaving a minor validation gap.

4 / 5

Progressive Disclosure

Well-organized into numbered steps, conventions, examples, and tips in a single self-contained file with no bundle files present; structure is good but the full worked example is inlined rather than split, so it is not a pristine one-level-deep reference layout.

4 / 5

Total

17

/

20

Passed

Description

87%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.

A strong, well-scoped description that clearly states its purpose, gives concrete natural-language triggers, and draws sharp boundaries against adjacent skills. Minor room to expand keyword synonyms/extensions.

DimensionReasoningScore

Specificity

Lists several concrete actions — "Extract a standalone JIT regression test case", "save it under the JitBlue folder", "converting issue repro to xunit test" — but they are all facets of one task rather than a comprehensive set of distinct actions, so it stops short of 5.

4 / 5

Completeness

Explicitly answers both what (extract a JIT regression test from a GitHub issue and save under JitBlue) and when (concrete "USE FOR" triggers plus a "DO NOT USE FOR" boundary), matching the 5 anchor precisely.

5 / 5

Trigger Term Quality

Includes natural phrases users would say ("write a test for this JIT bug", "create a regression test for issue #NNNNN", "dotnet/runtime issues") but lacks file extensions and broader synonym coverage, falling just below the comprehensive 5 anchor.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (JIT regression tests for dotnet/runtime) with explicit "DO NOT USE FOR" boundaries distinguishing it from non-JIT tests, debugging, and benchmarks, giving minimal conflict risk.

5 / 5

Total

18

/

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
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.