আপনার এজেন্টের জন্য উপযুক্ত সক্ষমতা খুঁজে নিন।
Validates and coordinates batch study guide operations (both separate and merge modes). Ensures file availability, template compatibility, and source-only policy before launching agents. **CRITICAL AUTOMATION**: Prevents batch processing errors by validating all prerequisites.
Initialize projects with AI Dev Flow framework using domain-aware setup
交互式配置 GitHub Actions 通过 SSH 密钥连接 VPS 的向导。当用户需要设置 GitHub Actions 部署到 VPS、配置 CI/CD SSH 连接、生成部署 workflow 时使用此 skill。通过问答方式收集必要信息后生成完整配置。
Verify and enforce coding standards, AI guidelines, and workspace compliance across repositories. Use for standards propagation, compliance verification, and enforcing development best practices.
Run security scans locally (Semgrep, Trivy, Gitleaks) to detect vulnerabilities, secrets, and code issues before pushing. Use when the user wants to check for security issues, scan dependencies, or validate code security.
Provider-agnostic wait-for-change skill that uses the Dumbwaiter MCP server to wait on PR events (GitHub first) via wait.start/status/cancel/await, with progress notifications and durable state.
Automatically run the test suite when code changes are made to ensure all tests pass before proceeding. This skill runs pytest for backend projects and Playwright for frontend projects, and reports test results, coverage, and any failures.
Operational security guidance for deployment, monitoring, and maintenance. Use this skill when you need to understand which middlewares to apply, configure environment variables, monitor security post-deployment, or follow the pre-deployment checklist. Triggers include "security operations", "deployment security", "security monitoring", "environment variables", "when to use middleware", "pre-deployment", "security checklist", "production security".
Build mithril-core shared infrastructure. Use when implementing storage, compression, hashing, or common types for the Mithril ML toolkit.
GitHub Actions CI/CD pipelines with caching, matrix builds, and deployment strategies. Focuses on build speed, reliability, and security. Use when creating or optimizing CI/CD workflows, debugging pipeline failures, or implementing deployment automation.
Run multi-provider code reviews over git diffs/PR changes using headless AI CLIs (Claude Code `claude`, Google `gemini`, optionally GitHub `copilot`) and output structured findings + an optional synthesized report; use for security/bug/perf review of recent changes and for generating PR-ready review comments.
Develop custom Tekton Tasks and reusable pipeline components. Use when creating Tasks for Tekton Hub, building ClusterTasks, designing parameterized Task libraries, or packaging Tekton components for distribution.
Master Kubernetes Deployments, StatefulSets, DaemonSets, and workload orchestration. Learn deployment patterns and container orchestration strategies.
This skill should be used when the user is working in a jj-enabled repository (has .jj directory), asks to "commit changes", "push code", "check status", "create a PR", "view history", or performs any version control operation. Teaches Claude to prefer jj over git in jj repositories while maintaining git compatibility knowledge.
The agent implements Kubernetes container orchestration with deployments, services, Helm charts, and production patterns. Use when deploying containerized applications, configuring autoscaling, managing secrets, or setting up ingress routing.
Create Lunar collector plugins that gather SDLC metadata for guardrail enforcement. Use when building collectors (Bash scripts) that collect data from repositories, CI pipelines, or external APIs and write to the Component JSON. Covers hook types (code, cron, ci-after-command), the `lunar collect` command, plugin structure, containerization, and best practices.
Crea automáticamente changelogs orientados al usuario a partir de commits de git. Analiza el historial, categoriza los cambios y transforma commits técnicos en notas de release claras y amigables para el cliente.
