Tessl • The management layer for AI agent skills

SkillPublic

write-unit-tests

Write focused Vitest unit tests. Use when adding or improving unit tests for business logic, data access, common services, or other server modules.

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

100%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 well-structured, concise, and highly actionable skill body that assumes Claude's competence, gives executable commands, and includes an explicit test-green feedback loop. Progressive disclosure is handled cleanly via one-level-deep ADR references.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: it avoids explaining what unit tests or Vitest are and every section (When to use, Workflow, Run, Guardrails, Output) earns its place, matching the 'lean and efficient; every token earns its place' anchor.	5 / 5
Actionability	It provides copy-paste-ready, executable commands ('./scripts/cli scaffold up-test', 'pnpm test:server -- path/to/file.test.ts') and concrete fixture/test-kit guidance ('@crowd/test-kit', 'withQx'), covering the common cases fully.	5 / 5
Workflow Clarity	The numbered Workflow has an explicit feedback loop in step 5 ('Run the affected tests and fix failures until green') plus a testability-seam checkpoint in step 6, matching the 'clear sequence with explicit validation steps; feedback loops for error recovery' anchor.	5 / 5
Progressive Disclosure	The SKILL.md is a concise overview with clearly signaled, one-level-deep references (ADR-0007, ADR-0008) and well-organized sections; with no bundle files present, the body is appropriately self-contained and easy to navigate.	5 / 5
	Total	20 / 20 Passed

Description

67%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 concise, third-person description that covers both what the skill does and when to use it with concrete trigger context. It is well-scoped and distinct, with the main gap being slightly limited specificity of distinct actions.

Suggestions

List 1-2 more concrete actions (e.g., 'compose fixtures', 'add focused scenarios') to raise specificity beyond a single 'Write' verb.

Broaden trigger terms with common synonyms (e.g., 'specs', '.test.ts', 'test coverage') to improve natural-keyword coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Vitest unit tests') and one concrete action ('Write focused ... unit tests') plus a list of module types, but does not enumerate multiple distinct concrete actions, matching the 'domain and 1-2 concrete actions' anchor rather than the several-actions anchor above.	3 / 5
Completeness	It explicitly answers 'what' ('Write focused Vitest unit tests') and 'when' ('Use when adding or improving unit tests for ...'), but the 'when' trigger phrasing could be more specific/varied, fitting the 'both what and when, when could be more explicit' anchor rather than the fully concrete-trigger anchor.	4 / 5
Trigger Term Quality	It includes natural terms users would say ('unit tests', 'Vitest', 'business logic', 'data access', 'server modules') with good coverage, but lacks common synonyms or file-extension variants, sitting just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	Scoping to 'Vitest unit tests' for 'server modules' carves a clear niche distinct from API/E2E or worker-package tests, with only minor overlap risk against other test-writing skills.	4 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
relative_links	Relative link issues: 2 suspicious	Warning

	Total	14 / 16 Passed

Repository: linuxfoundation/crowd.dev
Path: .claude/skills/write-unit-tests/SKILL.md
Revision: f27ddfb

Reviewed: 2 months ago

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.

write-unit-tests

Table of Contents

Is this your skill?