CtrlK
BlogDocsLog inGet started
Tessl Logo

running-integration-tests

This skill enables Claude to run and manage integration test suites. It automates environment setup, database seeding, service orchestration, and cleanup. Use this skill when the user asks to "run integration tests", "execute integration tests", or any command that implies running integration tests for a project, including specifying particular test suites or options like code coverage. It is triggered by phrases such as "/run-integration", "/rit", or requests mentioning "integration tests". The plugin handles database creation, migrations, seeding, and dependent service management.

Install with Tessl CLI

npx tessl i github:jeremylongshore/claude-code-plugins-plus-skills --skill running-integration-tests
What are skills?

69

1.07x

Does it follow best practices?

Evaluation73%

1.07x

Agent success when using this skill

Validation for skill structure

SKILL.md
Review
Evals

Evaluation results

70%

18%

Integration Test Infrastructure for PayTrack API

Test environment scripts and config

Criteria
Without context
With context

setup script name

0%

0%

run script name

0%

0%

cleanup script name

0%

0%

config file location

0%

100%

DB creation in setup

100%

100%

Migrations in setup

100%

100%

Seeding in setup

100%

100%

DB drop in cleanup

100%

100%

Service stop in cleanup

100%

100%

Temp file removal

0%

100%

Services in config

100%

100%

Without context: $0.4538 · 1m 52s · 15 turns · 15 in / 8,462 out tokens

With context: $0.4467 · 1m 40s · 18 turns · 66 in / 6,526 out tokens

78%

-10%

Automated Test Reporting for ShipFast Logistics Platform

Test report generation with coverage

Criteria
Without context
With context

report generator name

0%

0%

pass/fail counts

100%

100%

execution times

100%

100%

coverage metrics

100%

100%

coverage as option

100%

100%

run_tests.sh exists

100%

0%

report generator called

100%

100%

detailed log capture

100%

100%

report output file

100%

100%

suite totals in report

100%

100%

Without context: $0.7478 · 2m 35s · 25 turns · 26 in / 10,514 out tokens

With context: $0.6828 · 2m 36s · 23 turns · 278 in / 10,840 out tokens

80%

Targeted Integration Test Runner for MediTrack EHR System

Selective suite execution and full lifecycle

Criteria
Without context
With context

run_tests.sh accepts suite arg

100%

100%

suite filtering applied

100%

100%

all-suites default

100%

100%

setup before tests

100%

100%

cleanup after tests

100%

100%

DB drop in cleanup

100%

100%

Services stopped in cleanup

100%

100%

Progress logging

100%

100%

Setup script name

0%

0%

Cleanup script name

0%

0%

Without context: $0.4985 · 1m 59s · 18 turns · 18 in / 8,157 out tokens

With context: $0.7593 · 2m 48s · 30 turns · 30 in / 10,491 out tokens

43%

23%

Integration Test Infrastructure Bootstrap

Configuration and seed asset files

Criteria
Without context
With context

YAML config filename

0%

0%

Services in YAML config

100%

100%

SQL seed filename

0%

0%

SQL seed content

100%

100%

Setup script name

0%

0%

Seed invoked in setup

0%

50%

Migrations in setup

0%

100%

Run script name

0%

0%

Cleanup script name

0%

0%

Config file placement

0%

50%

DB reset in setup

25%

100%

Without context: $0.4258 · 1m 41s · 16 turns · 58 in / 7,322 out tokens

With context: $0.6302 · 2m 49s · 21 turns · 145 in / 11,612 out tokens

100%

Integration Test Reporting Pipeline

HTML report template generation

Criteria
Without context
With context

Report generator filename

100%

100%

HTML template filename

100%

100%

Template used by generator

100%

100%

Pass/fail counts in report

100%

100%

Execution time in report

100%

100%

Coverage metrics in report

100%

100%

Run script name

100%

100%

Generator invoked from runner

100%

100%

Report saved to file

100%

100%

HTML structure valid

100%

100%

Without context: $0.5882 · 2m 28s · 19 turns · 19 in / 10,899 out tokens

With context: $0.6689 · 2m 45s · 22 turns · 53 in / 12,052 out tokens

68%

12%

Adding Integration Tests to an Existing Project

Isolated environment and focused test design

Criteria
Without context
With context

Focused tests: DB interaction

100%

100%

Focused tests: cache interaction

100%

100%

Separate DB for integration

100%

100%

No port 5000 conflict

100%

100%

Setup script name

0%

0%

Run script name

0%

0%

Cleanup script name

0%

0%

DB drop in cleanup

100%

100%

Config file location

0%

0%

Test design documented

100%

100%

Temp files removed in cleanup

0%

100%

Without context: $0.6747 · 2m 52s · 23 turns · 24 in / 10,511 out tokens

With context: $0.6602 · 2m 51s · 21 turns · 22 in / 10,912 out tokens

Evaluated
Agent
Claude Code
Model
Unknown

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.