CtrlK
BlogDocsLog inGet started
Tessl Logo

grade-tests

Grades a specified set of test methods individually and produces a concise table mapping each test (fully-qualified name) to a letter grade (A–F), a score band, and a one-line note — designed to be posted as a PR comment. Use when the caller wants per-test feedback on a curated list of methods (for example, the new or modified tests in a pull request), not a suite-wide audit. Polyglot: .NET, Python, TS/JS, Java, Go, Ruby, Rust, Swift, Kotlin, PowerShell, C++. Input is a list of test methods (or method bodies / file+line spans); output is a compact markdown table plus a short summary. DO NOT USE FOR: full suite audits (use test-quality-auditor agent or test-anti-patterns), writing new tests (use code-testing-generator agent or writing-mstest-tests), fixing failures, or measuring code coverage.

71

Quality

86%

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

81%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 a thorough, highly actionable grading rubric with a well-sequenced workflow and validation checkpoints, and it sensibly offloads language specifics to an extension skill. Its main weakness is redundancy: the Common Pitfalls and Validation sections restate rules already present in the Step 3 tables.

Suggestions

Collapse the Common Pitfalls table into the existing Step 3 rules or move it to a reference file — most rows duplicate the Critical/High/Medium/Low catalog and the Validation checklist.

Extract the inlined anti-pattern catalog (Critical/High/Medium/Low) into a references/ file and link to it from Step 3 to shorten SKILL.md and improve progressive disclosure.

Trim the Validation checklist to only the items not already enforced by the sub-grade tables to reduce repetition.

DimensionReasoningScore

Conciseness

The rubric tables and scoring formulas are dense and mostly earned, but the Common Pitfalls table (13 rows) and the Validation checklist restate rules already embedded in the Step 3 sub-grade tables, adding noticeable redundancy that could be tightened.

3 / 5

Actionability

As an instruction-only skill it provides fully actionable guidance: explicit deduction formulas, A–F sub-grade tables with concrete pattern matches, example note strings, and a copy-ready markdown output table with sample rows.

5 / 5

Workflow Clarity

A clear Step 0–Step 5 sequence with explicit validation (reject ambiguous input up-front, mark missing methods N/A, mark production-dependent findings Unverified) and an end-of-workflow checklist; the operation is read-only so the destructive-cap does not apply.

5 / 5

Progressive Disclosure

Well-organized into clear sections and smartly delegates language-specific guidance to the test-analysis-extensions skill, but the ~80-line inlined anti-pattern catalog and the largely redundant Common Pitfalls section are content that could be split into a reference file.

4 / 5

Total

17

/

20

Passed

Description

92%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 third-person, concrete, and tightly scoped, answering both what and when while explicitly distinguishing the skill from neighboring suite-audit and test-authoring tools. Trigger-term coverage is strong though not exhaustive of every synonym a user might utter.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — grades test methods individually, maps each to a letter grade/score band/one-line note, and emits a compact PR-comment table — with comprehensive coverage of inputs, output shape, and polyglot language support.

5 / 5

Completeness

Explicitly answers both what ('Grades a specified set of test methods... produces a concise table') and when ('Use when the caller wants per-test feedback on a curated list of methods'), plus a DO NOT USE FOR block that sharpens the trigger.

5 / 5

Trigger Term Quality

Good natural trigger coverage ('per-test feedback', 'curated list of methods', 'new or modified tests in a pull request', 'PR comment'), but a few common phrasings users might say (e.g. 'review these tests', 'are my tests good') are not surfaced as synonyms.

4 / 5

Distinctiveness Conflict Risk

Clear niche (per-test grading for PR comments) with explicit routing away from test-anti-patterns, test-quality-auditor, code-testing-generator, writing-mstest-tests, coverage-analysis, and crap-score, minimizing conflict risk.

5 / 5

Total

19

/

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/skills
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.