test-review
Analyze test coverage requirements and assess whether code meets testing standards. Use when reviewing test plans, evaluating test coverage, or assessing testing quality.
Découvrez les skills Entreprise, comparez leurs dépôts et consultez leurs instructions.
Analyze test coverage requirements and assess whether code meets testing standards. Use when reviewing test plans, evaluating test coverage, or assessing testing quality.
Review production code for bugs, security vulnerabilities, performance issues, and maintainability. Use when reviewing pull requests, code changes, or assessing code quality.
Review production system designs for architecture, scaling, security, and operational concerns. Use when reviewing system architecture, technical designs, or complex technical approaches.
Protocol untuk meningkatkan kecerdasan, presisi, dan keamanan dalam coding dan debugging.
Panduan dan referensi skema untuk membangun AI Agent yang stateful dan cerdas, berdasarkan best practice LangGraph.
Edit GitHub PR title/body (and optionally comments) reliably on Windows. Use when asked to update PR metadata or when GitHub API returns 404 due to missing auth (private repos often return 404 when unauthentica...
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoid...
Standardized commit + push + PR workflow. Use when the user asks to commit/push/open PR to ensure checks run, messages are consistent, and pushes/force-pushes are handled safely.
Build or extend an extensible UI self-check framework for Web UIs (React/Vite or plain HTML) using Playwright. Use when asked to add/upgrade ui-check or ui-watch flows, enforce data-qa/data-testid discovery, ad...
Use when writing, reviewing, or refactoring React/Next.js components, pages, or data fetching where performance, bundle size, or render efficiency is a concern.
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement...
Use when reviewing UI, accessibility, or UX in web interfaces and you need to audit components against web design best practices.
Coordinate multi-commit epic work using git worktrees, feature branches, PRs, and CI. Use when working on epics or large features that span multiple tasks.
Complete individual tasks with test-first development, quality gates, and proper commits. Use when working on bugs, features, or tasks that result in a single commit.
Debugs failing tests, flaky tests, and Node processes that won't exit after tests complete. Use when backend/shared/frontend tests fail or hang.
Keeps GitHub milestone descriptions in sync with milestone issue CRUD by reanalyzing delivery slices, inserting gaps, and applying a deterministic ordered plan (with auth + heredoc guardrails). This should be u...
Runs and interprets exit graph consistency scans (dangling exits, orphan locations, missing reciprocal exits). Use when exits/navigation look wrong or when changing location graph data.
Enforces the two-stage shared→backend workflow (publish shared first, then consume from registry). Use when changing both shared/ and backend/ or when shared package versioning/publishing is involved.
Generate or refine world lore, locations, NPCs, factions, and prompt templates for The Shifting Atlas while respecting established docs, D&D constraints, and traversal invariants.
Runs and troubleshoots the Azure Functions backend locally (build/watch/func host start, local.settings modes). Use when developing or debugging backend HTTP/queue functions.
Validates and bundles prompt templates (schema validation, secret token scan, canonical hashes, bundle artifact). Use when editing shared/src/prompts/templates or when prompt validation/bundling fails.
This is a new rule
Complete Godot Engine knowledge base combining official documentation and source code analysis
Comprehensive assistance with godot_docs
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.