MCP App StoreMCP App Store
de ucai27
Conseils et modèles pour concevoir des tests, mettre en place des tests unitaires/intégration/E2E et améliorer la qualité et la couverture des tests pour divers langages et frameworks.
Fournit des modèles de conception de tests, des conseils de détection de stack et une checklist de revue pour aider les agents ou les ingénieurs à générer des tests unitaires, d'intégration et E2E robustes. Couvre les pyramides de tests, les stratégies de mocking, les tests asynchrones, la prévention des tests instables (flaky tests) et les conventions de nommage.
À invoquer lorsqu'il s'agit de générer des tests, de mettre en place des suites E2E, d'analyser ou d'améliorer la couverture de tests, de configurer des runners de tests (Jest, Vitest, Playwright) ou d'auditer la qualité des tests avant la fusion. Utile lors du développement de fonctionnalités, des efforts d'automatisation des tests et des améliorations de la CI.
Idéal pour les agents capables d'inspecter les fichiers du dépôt et d'exécuter ou de générer du code de test (Claude Code, Copilot/GitHub Code assistants, agents capables d'utiliser le CLI).
Pure instructional SKILL.md for QA/testing patterns across languages. No bundled scripts. Covers test pyramid, mocking strategy, anti-gaming verdicts, and review checklist. Well-structured but contains environment-specific paths (/home/joncik/apps/Pragma) and is mostly general best practices rather than actionable automation.
No security concerns — purely instructional text with no scripts, network calls, or credentials. The skill is well-written but overlaps heavily with general testing knowledge. The anti-gaming verdicts are the most unique/value-add part. Environment-specific paths should be generalized.
Development Worktree
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
Full Stack Builder
End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.
Claw Bench
Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.
SWE-AF — Autonomous Software Engineering Fleet
Orchestrates a coordinated multi-agent engineering workflow to plan, implement, test, and merge production-grade changes across single or multiple repositories.
Claude Code (Clawdbot)
Wrapper to run the local Claude Code CLI in headless or interactive (tmux) modes for code analysis, refactors, tests, and structured output.
BK-CI Design Patterns Guide
Practical guide to design patterns used in the BK-CI project (Kotlin/Spring). Covers factory, strategy, singleton, decorator, observer, template method, chain-o
Repository Module Architecture (BK-CI)
Guidance for integrating and managing code repositories in BK-CI: authentication, webhooks, SCM differences, PAC handling and repository-type concerns.
Infrastructure Drift Detector
Detect infrastructure drift between Terraform state and real cloud resources; report unmanaged/changed/missing resources for remediation.