testing-workflow

Generates test plans, writes unit/integration/E2E test files, identifies coverage gaps, flags common testing anti-patterns. Use when writing tests, creating test suites, planning test strategies, mocking dependencies, measuring code coverage, or test planning.

Quality

86%

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

80%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 an efficient, well-sectioned rulebook with concrete commands and thresholds, but it reads as a checklist of constraints rather than an operational workflow. Adding a short ordered sequence with a validation feedback loop (run coverage, add tests, re-run) would raise its weakest dimension.

Suggestions

Add a short ordered workflow (plan tests → write unit/integration → run npx vitest run --coverage → add tests if below minimums → re-run) so the sequencing dimension has an explicit pipeline instead of standalone rules.

Include an explicit feedback-loop checkpoint for the batch E2E runs, e.g. "If a suite fails or coverage is under 95%, fix and re-run before logging results", to satisfy the validation requirement for batch operations.

Add one copy-ready example of a unit test case and a log entry appended to .opencastle/logs/e2e-results.md to close the remaining actionability gap.

Dimension	Reasoning	Score
Conciseness	The body is lean and rule-driven — "Max 3 screenshots", "Reload between flows — clears state", "evaluate_script() over take_snapshot() — returns less data" — with zero explanation of concepts Claude already knows, matching the lean-and-efficient anchor.	5 / 5
Actionability	Concrete commands ("npx vitest run --coverage", "npx playwright test"), numeric coverage minimums (95%, all boundaries), and real paths (.opencastle/logs/e2e-results.md) make the guidance mostly executable, but there are no copy-ready test or log-entry examples and suite details are delegated to a project file, leaving minor gaps versus fully executable.	4 / 5
Workflow Clarity	The content presents rules and minimums rather than a sequenced workflow: there is no plan → write → run → verify sequence and no explicit feedback loop (e.g., "if coverage is below 95%, add tests and re-run"), and running full test suites is a batch operation whose missing validation cycle caps this at 3.	3 / 5
Progressive Disclosure	This is a simple skill under 50 lines with no bundle files, and the body is organized into clear, well-labeled sections (E2E Context Limits, Coverage Minimums, Anti-Patterns), so the simple-skill exception applies.	5 / 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 strong: it pairs a comprehensive, concrete list of capabilities with an explicit multi-trigger "Use when" clause, and all trigger terms are natural phrasings a user would say. The only weakness is modest synonym coverage in the trigger list.

Dimension	Reasoning	Score
Specificity	"Generates test plans, writes unit/integration/E2E test files, identifies coverage gaps, flags common testing anti-patterns" lists four distinct concrete actions with comprehensive coverage of the testing domain, matching the top anchor rather than the 'minor gaps' anchor at 4.	5 / 5
Completeness	It explicitly answers "what" with four concrete actions and "when" with an explicit "Use when..." clause listing multiple concrete triggers, matching the top anchor exactly.	5 / 5
Trigger Term Quality	"writing tests, creating test suites, planning test strategies, mocking dependencies, measuring code coverage, or test planning" gives good natural keyword coverage, but common variations like "TDD", "test coverage", or "writing unit tests" are missing, so it sits between the good and comprehensive anchors.	4 / 5
Distinctiveness Conflict Risk	All triggers are testing-specific and the domain niche (test generation, coverage, anti-patterns) is clearly distinct from adjacent skills such as code review or linting, giving minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: monkilabs/opencastle
Path: src/orchestrator/skills/testing-workflow/SKILL.md
Commit: c0f4566

Reviewed: 1 day 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.