CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

testing

Write, extend, and run Jest unit/integration tests for POSCursor (Expo RN + WatermelonDB LokiJS). Use when adding services/screens/hooks, fixing failing Jest tests, following TDD, or choosing mocks/createTestDatabase patterns. Do not use for Playwright E2E or the full release matrix — use systematic-test-matrix instead.

73

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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.

A highly actionable, well-structured project skill: executable patterns, exact commands, a safety guard, and a definition-of-done checklist with error-recovery guidance. Its weaknesses are mild — stale-prone dated metrics inline and a companion reference that is only signposted at the very end.

Suggestions

Move the dated baseline metrics ('As of 2026-09-11' suite/test counts, bucket file tallies) into references/patterns.md or a clearly labeled baseline section so staleness doesn't erode the main skill.

Surface references/patterns.md contextually (e.g., link it from the Patterns section) rather than only in the final 'Related docs' section, so deeper examples are discoverable at the point of need.

Add 'test coverage' and '.test.ts' style trigger phrasing guidance to help routing, since 'improve test coverage' requests currently only map to this skill via the body's backlog section.

DimensionReasoningScore

Conciseness

Dense, project-specific tables and snippets that assume Claude's competence (no explaining what Jest or TDD is), but dated baseline metrics ('As of 2026-09-11... ~193 suites... ~1554 tests') and approximate bucket file counts will go stale and are not placed in a deprecated/old-patterns section.

4 / 5

Actionability

Copy-paste-ready code for the main test patterns (createTestDatabase injection, jest.mock of the database module, RNTL navigation/auth mocks) plus exact executable commands like 'npx jest src/services/__tests__/CashService.test.ts --no-coverage' covering the common cases.

5 / 5

Workflow Clarity

The TDD workflow is clearly sequenced (RED → GREEN → REFACTOR) with a validation checklist in 'Definition of done' (targeted file passes, bucket/suite green, no production URL) and an explicit error-recovery loop for hung LokiJS workers (kill worker, re-run the file alone).

5 / 5

Progressive Disclosure

Well-sectioned body with a real one-level-deep reference ('Deeper inventory & examples: references/patterns.md', verified to exist) and cross-links to sibling skills; however the reference is only surfaced in a final 'Related docs' section rather than contextually, and inline inventory detail (bucket file counts, coverage backlog) could live in the companion file.

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.

A strong description: concrete third-person capabilities, an explicit 'Use when' trigger clause with multiple natural phrases, and clear disambiguation from the sibling systematic-test-matrix skill. The only gap is a few missing natural trigger variations such as 'test coverage' or '.test.ts'.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Write, extend, and run Jest unit/integration tests' plus 'choosing mocks/createTestDatabase patterns' — with named stack and third-person voice; comprehensive coverage of the skill's actions with no gaps.

5 / 5

Completeness

Explicitly answers both 'what' (write, extend, and run Jest unit/integration tests for POSCursor) and 'when' ('Use when adding services/screens/hooks, fixing failing Jest tests, following TDD, or choosing mocks/createTestDatabase patterns') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good natural keyword coverage ('Jest', 'unit/integration tests', 'failing Jest tests', 'TDD', 'mocks'), but misses common variations users would say such as 'test coverage', 'spec', or file extensions like '.test.ts'.

4 / 5

Distinctiveness Conflict Risk

Clear niche (Jest unit/integration testing for a specific app) reinforced by an explicit negative boundary — 'Do not use for Playwright E2E or the full release matrix — use systematic-test-matrix instead' — minimizing conflict with sibling skills.

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

zazakia/JetFarm

Path

.agents/skills/testing/SKILL.md

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.