স্কিল খুঁজুন
আপনার এজেন্টের জন্য উপযুক্ত সক্ষমতা খুঁজে নিন।
viya-dev-environment
Manage viya-app local development environment - set service versions from PRs, restart containers
moon-knowledge
Provides comprehensive knowledge about moonrepo/moon for monorepo management and task running. Use when user asks about moon configuration, workspace setup, task definitions, CI/CD integration, proto toolchain, caching, optimization, or migration from other tools. Triggers on "moon", "moonrepo", "monorepo with moon", ".moon/", "moon.yml", "workspace.yml", "proto toolchain", "moon task", "moon ci".
dependabot-solver
Fetches Dependabot security alerts from a repository and returns structured data about packages with vulnerabilities, their severity, and minimum versions needed to resolve them. Use with an LLM to intelligently resolve dependency updates with proper version management.
test-ci-locally
Test CI/CD scripts and workflows locally before pushing. Use when modifying GitHub Actions, CI configuration, or before pushing changes that might fail CI.
pre-commit-validator
Validates code quality before commits in the MigraineTracker React Native project. Use this skill when preparing to commit code, before pushing changes, or when the user asks to run pre-commit checks. Ensures TypeScript type safety, test coverage (80%+), passing tests, and proper branch strategy compliance.
docker-rocker
Production-grade Docker containerization for FastAPI, Pytest, SQLModel, and Pydantic projects. This skill should be used when users ask to dockerize FastAPI applications, create multi-stage Docker builds, optimize Docker images for Python APIs, set up CI/CD Docker pipelines, or deploy containerized Python web APIs with maximum performance and minimal image size.
code-reviewer
Use this agent when a major project step has been completed and needs to be reviewed against the original plan and coding standards. Examples: <example>Context: The user is creating a code-review agent that should be called after a logical chunk of code is written. user: "I've finished implementing the user authentication system as outlined in step 3 of our plan" assistant: "Great work! Now let me use the code-reviewer agent to review the implementation against our plan and coding standards" <commentary>Since a major project step has been completed, use the code-reviewer agent to validate the work against the plan and identify any issues.</commentary></example> <example>Context: User has completed a significant feature implementation. user: "The API endpoints for the task management system are now complete - that covers step 2 from our architecture document" assistant: "Excellent! Let me have the code-reviewer agent examine this implementation to ensure it aligns with our plan and follows best practices" <com
kubernetes
Comprehensive Kubernetes cluster management skill. Use this skill when working with Kubernetes resources, kubectl operations, Helm charts, container orchestration, debugging pods, managing deployments, or any Kubernetes-related infrastructure tasks.
test-traditional-build
Run a traditional AIB build test and report results. Builds a disk image using automotive-image-builder manifest and downloads the artifact.
local-development-standard
Standardized local development environment setup ensuring consistency across team members and reducing "works on my machine" issues.
supply-chain-security
A capability-oriented reasoning framework for identifying and describing security-relevant capability expansions in software supply-chain version transitions. Provides capability vocabulary, counterfactual reasoning scaffolds, and contextual analysis tools. Use when analyzing code version transitions to understand what new affordances emerge, not to classify code as malicious/benign. Atomic unit of analysis is the version transition (diff), not standalone code.
lxc-service-deployment
Standardized deployment procedure for services in LXC containers on the Proxmox HA cluster. Use when deploying a new service, creating LXC containers, configuring DHCP reservations (Kea), DNS rewrites (AdGuard), reverse proxy routes (Traefik), or integrating with monitoring (Uptime Kuma) and dashboard (Homepage). Triggers on phrases like "deploy a new service", "create container for", "set up DHCP", "add Traefik route", "configure DNS rewrite", or any homelab infrastructure deployment.
helm-chart-generator
Generate production-ready Helm charts for Kubernetes apps. Use when: (1) Deploying applications to Kubernetes, (2) Containerizing apps for Minikube/K8s, (3) Creating reusable deployment packages, (4) Needing parameterized K8s manifests, (5) Scaffolding new chart structures. Includes security contexts, resource limits, RBAC, NetworkPolicies, and multi-environment support (dev/prod). Provides templates for frontend, backend, and MCP server components.
generate-tests
Generate comprehensive, maintainable test suites through code analysis. Use when the user asks to write tests, create unit tests, add test cases, test a function, or improve test coverage.
commit-conventions
Standardized commit message formats and conventions for clear, searchable, and automated-friendly version control history.
openspec-constitution-guard
This skill composes project AGENTS.md constitution files into openspec commands (apply, archive, proposal) to enforce quality validation gates before handoff. Use this skill when initializing openspec for the first time in a project or when AGENTS.md files are updated. The skill ensures openspec artifacts are validated against project-specific quality criteria from constitutions.
cross-repo-coordination
Coordinate changes across project-beta repositories when updating runner configurations. Ensures workflow labels match runner scale set names. Use when changing runnerScaleSetName or deploying new runner pools.
run-ios-test
Run iOS unit tests for the AIQ project. Supports running all tests, a specific test file, or a specific test method. Use this skill whenever you need to verify iOS code changes or run the test suite.
deploy-railway
Deploy do CarInsight para Railway com verificações prévias
