ing

Manage project dependencies across languages including npm install, package versioning, dependency conflicts, security scanning, and lock files. Use when dealing with dependencies, version pinning, semantic versioning, or resolving conflicts.

Use when working with the OpenAI API (Responses API) or OpenAI platform features (tools, streaming, Realtime API, auth, models, rate limits, MCP) and you need…

Orchestrate agile development workflows for Gitea repositories using the tea CLI. Use when working with Gitea-hosted repos and asking to 'run the workflow',…

Configures health check endpoints for Kubernetes readiness/liveness/startup probes. Use when deploying to Kubernetes.

Generates GitHub Actions CI workflow configuration. Use when adding continuous integration to a project.

Creates implementation, refactoring, and test tasks from templates. Use when an approved task plan needs tasks created via the configured tracker provider and…

Executes implementation tasks through Todo, In Progress, To Review. Use when task needs coding with KISS/YAGNI. Not for test tasks.

When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when…

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6×…

Executive leadership guidance for strategic decision-making, organizational development, and stakeholder management. Use when planning strategy, preparing…

用于 production-validator 的 Agent 技能 - 使用 $agent-production-validator 调用

Agentica server + Claude proxy 设置 - 架构、启动顺序、调试

Datadog CLI for searching logs, querying metrics, tracing requests, and managing dashboards. Use this when debugging production issues or working with Datadog…

Set up or repair codecontext adoption in a project. Use this whenever the user wants to add @context annotations to a repo, install the codecontext toolchain, update AGENTS.md guidance, improve agent workflows around decision capture, or audit whether an existing codecontext setup is coherent. Prefer this skill over vague "document the tool" work: it is specifically for making a repo actually usable with codecontext.

用于 hierarchical-coordinator 的 Agent 技能 - 使用 $agent-hierarchical-coordinator 调用

代理技能，用于代理 - 使用 $agent-agent 调用

Build reliable, fast, and maintainable end-to-end test suites that provide confidence to ship code quickly and catch regressions before users do.

用于 sona-learning-optimizer 的 Agent 技能 - 使用 $agent-sona-learning-optimizer 调用

用于构建交易系统、回测策略、实现执行算法或分析市场微观结构 - 涵盖策略开发、…

用于沙箱的 Agent 技能 - 通过 $agent-sandbox 调用