testing

Governs how to examine, write, fix, and run tests in the rc-unified-crm-extension monorepo. Use when writing new tests, debugging failing tests, examining test coverage, adding tests for new features or connectors, or asking about test conventions, test structure, mocking strategies, or running tests.

Quality

90%

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

88%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 tight, highly actionable testing guide with executable templates, clear decision workflows, and feedback loops for debugging. It could trim a few asides and would benefit from offloading some template bulk into reference files now that the skill exceeds overview length.

Suggestions

Remove parenthetical asides like 'the jest config also sets clearMocks: true, but be explicit' and 'both work — stay consistent per file' to tighten conciseness toward anchor 5.

Consider moving the large unit/integration code templates and the connector coverage checklist into reference files under references/ (e.g. references/templates.md) so the SKILL.md body reads as an overview with one-level-deep pointers, raising progressive_disclosure.

Add a brief explicit verification checkpoint note in the 'Fixing Tests' section (e.g. re-run the isolated file and confirm green before moving on) to formalize the feedback loop already present in the debugging workflow.

Dimension	Reasoning	Score
Conciseness	Efficient and assumes Claude's competence with no concept tutorials, but a few asides ('both work — stay consistent per file', 'the jest config also sets clearMocks: true, but be explicit') are minor over-explanation that could be trimmed, fitting anchor 4 over 5.	4 / 5
Actionability	Provides copy-paste-ready unit/integration/MCP templates, exact commands, named helpers (createMockUser, resetConnectorRegistry), the SQLite pattern, and error-return shape conventions — fully executable and covering the common cases per anchor 5.	5 / 5
Workflow Clarity	Debugging and decision workflows are numbered and sequenced with explicit validation feedback loops (revert-and-rerun, nock.recorder); these are diagnostic rather than destructive/batch operations so the destructive-cap does not apply, matching anchor 5.	5 / 5
Progressive Disclosure	Well-organized into headers, tables, and code with no nested references, but at ~230 lines the bulk is inline templates and conventions rather than an overview pointing to one-level-deep files; good structure with minor organization gaps fits anchor 4.	4 / 5
	Total	18 / 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 specific, complete, and well-scoped, clearly answering both what the skill does and when to use it with concrete trigger phrases tied to a named monorepo. Its only weakness is slight synonym breadth in the trigger terms.

Dimension	Reasoning	Score
Specificity	Quotes concrete actions 'examine, write, fix, and run tests' tied to a named domain, enumerating multiple specific actions with comprehensive coverage — a clear anchor-5 match rather than 4 since no real coverage gaps exist.	5 / 5
Completeness	Explicitly answers both 'what' ('Governs how to examine, write, fix, and run tests...') and 'when' ('Use when writing new tests, debugging failing tests...') with concrete trigger phrases, matching anchor 5.	5 / 5
Trigger Term Quality	Strong natural scenarios a user would say ('debugging failing tests', 'running tests', 'test coverage', 'mocking strategies'), but missing some pure synonyms and file-pattern triggers that the anchor-5 example carries, so it sits at 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	Scoped to 'the rc-unified-crm-extension monorepo' with distinct test-specific triggers, giving a clear niche with minimal conflict risk — an anchor-5 fit.	5 / 5
	Total	19 / 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: 5 suspicious	Warning

	Total	15 / 16 Passed

Repository: ringcentral/rc-unified-crm-extension
Path: .cursor/skills/testing/SKILL.md
Commit: ca1742e

Reviewed: 2 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.