Name: code-testing-agent
Rating: 64.8 (1 reviews)
Author: dotnet

code-testing-agent

Generates comprehensive, workable unit tests for any programming language using a multi-agent pipeline. Use when asked to generate tests, write unit tests, improve test coverage, add test coverage, create test files, or test a codebase. Supports C#, TypeScript, JavaScript, Python, Go, Rust, Java, and more. Orchestrates research, planning, and implementation phases to produce tests that compile, pass, and follow project conventions.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/code-testing-agent/SKILL.md

Quality

Content

63%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 body is well-structured and concise with a clear multi-agent pipeline and validation feedback loops, but its actionability and progressive disclosure are undermined by references to bundle files (unit-test-generation.prompt.md, extensions/dotnet.md) that are not present in the skill bundle.

Suggestions

Add the missing unit-test-generation.prompt.md bundle file (or remove the reference) so the core guidance it promises is actually reachable.

Provide the referenced extensions/ folder (e.g., extensions/dotnet.md) or drop the Troubleshooting pointer to it, since dangling references break navigation.

Expand the thin two-step Step-by-Step section with the explicit Builder→Tester→Fixer validation checkpoints so the workflow is fully sequenced in SKILL.md itself.

Dimension	Reasoning	Score
Conciseness	Sections are lean with no basic-concept padding (e.g., no explanation of what unit tests are), but the large ASCII pipeline diagram is somewhat decorative and could be trimmed; not a 5 because of that minor excess.	4 / 5
Actionability	It gives a concrete agent-invocation template ("Generate unit tests for [path…], following the unit-test-generation.prompt.md guidelines") and reference tables, but the primary detailed-guidance file it points to (unit-test-generation.prompt.md) does not exist, leaving the guidance incomplete.	3 / 5
Workflow Clarity	The Research→Plan→Implement pipeline with Builder/Tester/Fixer sub-agents and the Troubleshooting feedback loops provide a clear sequence with validation; not a 5 because the main Step-by-Step section is only two steps and defers all detail to the generator agent.	4 / 5
Progressive Disclosure	References are well-signaled and one level deep ([unit-test-generation.prompt.md], extensions/dotnet.md), but those bundle files do not exist, so the navigation the structure promises is broken; this drops it below 4.	3 / 5
	Total	14 / 20 Passed

Description

91%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 strong: it explicitly covers what the skill does and when to use it with natural, comprehensive trigger terms and a distinct generation niche. The only weakness is that part of the capability framing describes internal pipeline mechanics rather than user-facing actions.

Dimension	Reasoning	Score
Specificity	"Generates comprehensive, workable unit tests" and "Orchestrates research, planning, and implementation phases to produce tests that compile, pass, and follow project conventions" list several concrete actions with broad language coverage; stops short of 5 because the phase orchestration is internal mechanism rather than a distinct user-facing capability.	4 / 5
Completeness	It explicitly states what ("Generates comprehensive, workable unit tests…") and when ("Use when asked to generate tests, write unit tests, improve test coverage…") with concrete trigger phrases.	5 / 5
Trigger Term Quality	"generate tests, write unit tests, improve test coverage, add test coverage, create test files, or test a codebase" provides comprehensive natural phrasing including synonyms a user would actually say.	5 / 5
Distinctiveness Conflict Risk	The generation focus (vs. the separate run-tests skill) gives a clear niche, but "test a codebase" and "improve test coverage" carry minor overlap risk with related testing/maintenance skills.	4 / 5
	Total	18 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: dotnet/machinelearning
Path: .github/skills/code-testing-agent/SKILL.md
Commit: cd2fbd6

Reviewed: 10 days ago

Table of Contents

Discovery Implementation Validation

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.