backend-tests

Use when writing unit tests under test/unit-tests/backend/*.test.ts that run in Node with Mocha+Chai and no VS Code API. For pure logic: parsers, helpers, env merging. Triggers: "backend test", "unit test", "mocha test without vscode".

Quality

85%

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

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.

The body is highly actionable with copy-paste skeletons, exact commands, and a decision-tree workflow backed by an explicit fallback loop and a pitfalls table. It is efficient and well-structured, with only minor over-explanation and validation steps that are present but not formalized as numbered checkpoints.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's intelligence (no explanations of Mocha/Chai/TDD), but a few asides like 'They are the fastest feedback loop — no Extension Host, no display server, just Node + Mocha' and the mirror-pattern rationale could be trimmed.	4 / 5
Actionability	Fully executable: copy-paste skeleton code for both the direct-import and mirror patterns, an exact run command (yarn backendTests) plus the full command, a path-alias table, an import decision tree with code, and a pitfalls table with concrete fixes.	5 / 5
Workflow Clarity	Presents the work as an unambiguous decision tree with an explicit feedback loop ('Test it — if it fails, fall back to the mirror pattern') and an error-recovery pitfalls table, but validation is scattered rather than structured as explicit numbered checkpoints in the workflow.	4 / 5
Progressive Disclosure	No bundle files exist; the body is a single self-contained file well-organized into clear sections with one clearly-signaled, one-level-deep 'See also' reference. Good structure, though the bulk (mock surface area, full run command, pitfalls) stays inline rather than being split out.	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.

The description is specific, third-person, and explicitly pairs a concrete 'what' with an explicit 'Use when'/'Triggers' clause, giving it strong completeness and distinctiveness. Trigger-term coverage is good but not exhaustive of synonyms and file extensions, capping it just below the top anchor on that dimension.

Dimension	Reasoning	Score
Specificity	Names the concrete domain (unit tests under test/unit-tests/backend/*.test.ts in Node with Mocha+Chai, no VS Code API) and enumerates specific candidate types ('parsers, helpers, env merging') — several concrete actions with minor coverage gaps, fitting just above the midpoint.	4 / 5
Completeness	Clearly answers both 'what' (writing unit tests under a specific path, Node/Mocha+Chai, no VS Code API, for pure logic) and 'when' (explicit 'Use when...' plus a 'Triggers:' list with concrete trigger phrases).	5 / 5
Trigger Term Quality	An explicit 'Triggers:' clause supplies three natural phrases ('backend test', 'unit test', 'mocha test without vscode') a user would actually say, but it stops short of comprehensive synonym/extension coverage (no '.test.ts' or 'Chai test').	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche (backend-only unit tests, no VS Code API, specific path/runner) with distinct triggers, making false-fires against other test-writing skills unlikely.	5 / 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 suspicious	Warning

	Total	15 / 16 Passed

Repository: microsoft/vscode-cmake-tools
Path: .github/skills/backend-tests/SKILL.md
Commit: 916baba

Reviewed: 4 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.