Start up, tear down, and configure the local Kubernetes development environment for OpenShell. Uses k3d (Docker-backed k3s) + Skaffold + Helm.
Use when a product brief is finalized and ready to hand off to the engineering team, or when asked to send a brief to Apex, kick off engineering work, or start development on a…
Holistic evaluation framework for language models measuring accuracy, calibration, robustness, and fairness
Use when asked to build a product roadmap, prioritize a backlog, decide what to build next, or sequence a list of feature ideas.
Implement production deployment strategies including secrets management, blue-green deployments, canary releases, and upgrade procedures.
Product landscape reconnaissance — survey existing briefs, research, strategy, and team output before writing new briefs or dispatching specialists.
Generate production-ready Helm charts for Kubernetes applications. Use when users need to create new Helm charts, convert Kubernetes manifests to Helm templates, scaffold charts…
Use when working with Helm templates and template functions for generating Kubernetes manifests dynamically.
Use when managing Helm values files and configuration overrides for customizing Kubernetes deployments.
Manage Helm values across environments with override precedence, multi-environment configurations, and secret management.
Helm Values Manager - Auto-activating skill for DevOps Advanced. Triggers on: helm values manager, helm values manager Part of the DevOps Advanced skill category.
Dockerfile の作成・改善を支援する。「Dockerfile を作って」「Dockerfile 作成」「Dockerfile をレビュー」「Dockerfile 改善」「Dockerfile 最適化」「Dockerfile lint」「マルチステージビルド」「alpine 化」「イメージサイズ削減」「Dockerfile のベスト — from…
Always prefer Laravel's built-in helper classes over native PHP functions. Use `Arr::`, `Str::`, and Collection methods instead of native PHP equivalents.
Provides JavaScript/TypeScript helper functions and utilities for SonarJS rule implementation. Use when implementing rule fixes, searching for existing utilities, or needing to…
Use when the user types /prompts:hep-build, mentions @Hephaestus for build work, asks to create a single Agentlas agent, create a multi-agent team, or package an existing…
Set up an isolated git worktree for a Laravel project served by Laravel Herd (Pro-aware). Composes vd:worktree for the worktree/.env/port mechanics, then adds the Herd layer: link…
Use shell heredoc syntax as a workaround when write_file fails on complex TypeScript/JSX/code files with encoding or escaping issues
在桌面 / Web GUI 应用、业务系统或非 Python 语言宿主中「对接与集成」Hermes AI Agent Python 库的技能。 定位：**对接集成引擎**——复制 `examples/` 底座 → 快速把 `AIAgent` 接进你的应用 → 门禁收尾，而非从零开发 Agent 框架。 触发：给应用的 GUI 加一个内嵌 Hermes…
Fix Node.js version managers (fnm, nvm) broken by Hermes Agent installation. Hermes installs its own Node.js and may leak empty FNM_* env vars that break version managers.
Umbrella for Hermes model/provider and media-generation configuration: Claude subscription auth/claude-cli lanes, Codex/OpenAI image generation defaults, Cloudflare image MCP,…
Use when optimizing Hermes Tool Backpack, Skill Backpack, tool_backpack, skill_backpack, lazy tool surface, tool routing, search_files output, hm/hm-full production smoke…
Modify, debug, or extend the s6-overlay supervision tree inside the Hermes Agent Docker image — adding new services, debugging profile gateways, understanding the Architecture B…
Web UI 3-panel cho AI agent — sessions, chat, file browser. Python + vanilla JS, không framework. Reference architecture cho YAMTAM IO web mode.
Summarizes what the operator did during takeover (via git log), optionally queues instructions in NEXT-TASK.md, updates SHELL.md, and restarts the Docker container.
View or change hermit configuration for this project. Manages model, channels, budget prompts, morning brief, heartbeat, routines, idle behavior, compaction thresholds, Docker…
Stops the Docker container running the autonomous hermit, marks the session as operator takeover, loads full hermit context, and presents a summary.
Manage Heroku apps, dynos, and add-ons via CLI and API. Deploy and scale applications.
Operate Heroku Postgres with a safe inspection-first workflow. Use when the agent needs to provision, inspect, attach, promote, back up, restore, diagnose, or reason about…
Write Python code in the style of Raymond Hettinger, Python core developer. Emphasizes beautiful, idiomatic code using iterators, generators, and built-in tools elegantly.
Review Hetzner Cloud infrastructure posture including Firewall inbound and outbound rules and server attachment, Load Balancer health check configuration and target pool design,…
Provisions infrastructure on Hetzner Cloud with Terraform/Pulumi. Generates IaC code for CX11/CX21/CX31 instances, managed Postgres, SSL configuration, Docker deployment.
Configure Hex CI/CD integration with GitHub Actions and testing. Use when setting up automated testing, configuring CI pipelines, or integrating Hex tests into your build process.
Diagnose and fix Hex common errors and exceptions. Use when encountering Hex errors, debugging failed requests, or troubleshooting integration issues.
Collect Hex debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support tickets, or collecting diagnostic information for…
Deploy Hex integrations to Vercel, Fly.io, and Cloud Run platforms. Use when deploying Hex-powered applications to production, configuring platform-specific secrets, or setting up…
Create a minimal working Hex example. Use when starting a new Hex integration, testing your setup, or learning basic Hex API patterns.
Configure Hex local development with hot reload and testing. Use when setting up a development environment, configuring test workflows, or establishing a fast iteration cycle with…
Optimize Hex API performance with caching, batching, and connection pooling. Use when experiencing slow API responses, implementing caching strategies, or optimizing request…
Execute Hex production deployment checklist and rollback procedures. Use when deploying Hex integrations to production, preparing for launch, or implementing go-live procedures.
Implement Hex rate limiting, backoff, and idempotency patterns. Use when handling rate limit errors, implementing retry logic, or optimizing API request throughput for Hex.
Implement Hex reference architecture with best-practice project layout. Use when designing new Hex integrations, reviewing project structure, or establishing architecture…
Reviews code architecture for hexagonal patterns, checks dependency directions, and suggests improvements for ports and adapters separation.
Hexagonal architecture (ports & adapters) — dependencies point inward; domain declares ports, adapters implement them; domain never imports framework/DB/HTTP.
Design, implement, and maintain applications using hexagonal architecture (ports and adapters). Use when (1) designing new systems requiring clear separation between domain logic…
Hexagonal architecture (ports & adapters) for Java Spring Boot. Package structure, port definitions, use case implementation, adapter patterns, and testing strategy.
Hexagonal architecture (ports & adapters) for TypeScript Node.js backends. Package structure, port definitions, use case implementation, adapter patterns, DI wiring, and testing…
Advanced Hexagonal Architecture anti-patterns for TypeScript — domain importing framework dependencies, use cases depending on concrete adapters, HTTP handlers bypassing use…
Debug Hey API generation, OpenAPI drift, stale clients, wrong types, auth, and CI.
Review OpenAPI and Hey API clients for contract, auth, validation, and CI safety.
面向团队与企业用户的 HeyGen 文字转语音工具(专业版)。核心能力: - 涵盖免费版全部能力(Starfish TTS、多语言、语速控制、停顿) - SSML 高级标记(完整语音合成标记语言) - 批量生成:队列与并发处理 - 词级时间戳(word timestamps) - 多语言混合语音 - 本地化语音(locale)选择 - A — from…
Discover the effective local AWS profile, region, account, and caller identity before any AWS task without exposing credentials.
Create an isolated Python environment with a compatible Python version and boto3 for SageMaker or AWS automation.
Plan and coordinate a model deployment to Amazon SageMaker, including serving stack and real-time versus async inference.
Implement a production SageMaker endpoint with autoscaling, CloudWatch alarms, and tags. Use after the serving image and IAM role are known; use the deployment planner first when…
Select and verify the current region-specific serving container URI for a SageMaker model deployment.
Operate and integrate cooperative lifecycle control for detached Hugging Face Jobs with the hf-job-control Python package and CLI, including durable chunked outputs, audits, and…
Maps hh.ru automation in this repo: Playwright scripts, vacancies queue, dashboard, cover letter fill vs chat apply, selector files.
Use when building a sample-level hierarchical clustering dendrogram from a bulk expression matrix and sample annotation table, especially for QC, batch inspection, or sample…
Expertise in architecting, implementing, reviewing, and debugging hierarchical matching systems. Use when working with: (1) Two-sided matching (Gale-Shapley, hospital-resident,…
Use when the user mentions Higgsfield Canvas, a node-based or node graph workspace, an infinite board/canvas, chaining generations into a pipeline, or wants to wire prompts →…