全部能力

使用 Pydantic AI 构建 AI 智能体——工具、能力、结构化输出、流式传输、测试和多智能体模式。当用户提及 Pydantic 时使用。

Evaluate an AI product idea across outcomes, hypotheses, risks, and positioning. Use when deciding whether an AI solution deserves investment or recommendation.

Develop examples for AI SDK functions. Use when creating, running, or modifying examples under examples/ai-functions/src to validate provider support,…

Use the `orca` CLI to drive a running Orca editor — manage Orca worktrees; create, read, and run shell commands in Orca-managed terminals; and automate Orca's built-in browser (snapshot/click/fill/screenshot/tabs). Use this instead of raw `git worktree`, ad hoc shell PTYs, or Playwright whenever the task touches Orca state. Coding agents inside an Orca worktree should also use it to keep the worktree comment fresh at meaningful checkpoints. Boundary with `orchestration`: if the recipient of a terminal write is another AI agent (Claude Code, Gemini, Codex, a worker), use `orchestration` — it is the only correct way to send messages, nudges, replies, or task hand-offs to agents. orca-cli writes are for non-agent terminals (shells, build/test commands); reading or `wait`ing on any terminal — including agent terminals — stays in orca-cli.

file-test-bug — an installable skill for AI agents, published by microsoft/azure-skills.

针对 SPEC.md 执行“先规划后实施”。原生单线程循环，无子代理。在测试或构建失败时，自动调用反向传播技能后重试——失败的验证始终会考虑新的 §V 不变量是否能防止问题复发。当用户要求构建、实施、执行规范或处理特定 §T 任务（`build §T.3`、`build --next`、`implement next task`、`run the build`）时触发。预期 SPEC.md 已存在；若不存在，则交由 spec 技能处理。

Automatically update OpenClaw every night. Use when the user wants their agent to stay up-to-date with the latest OpenClaw version. Runs a cron job that stops the gateway, runs the update, and restarts. Triggered when user mentions: "update yourself", "auto update", "nightly update", "keep updated", "self update", or any variation of updating the agent.

Write a clear, empathetic EOL announcement with rationale, customer impact, and next steps. Use when retiring a product, feature, or plan without creating…

Writes failing tests first for test-driven development and hands off a strict implementation contract that requires agents to make those tests pass without…

Provides foundational setup, authentication, and project management workflows for Firebase using the Firebase CLI. Use when checking Firebase CLI version (must use 'npx -y firebase-tools@latest --version'), initializing a Firebase environment, authenticating, setting active projects, or setting up `google-services.json` or `GoogleService-Info.plist` files.

analyze-test-run — 一个可安装的 AI 代理技能，由 microsoft/azure-skills 发布。

Use this skill when working with coordinates, vectors, matrices, shapes, hit testing, or layout rectangles in PixiJS v8. Covers Point/ObservablePoint, Matrix…

cs-feat-accept — an installable skill for AI agents, published by liuzhengdongfortest/codestable.

Manage local Airflow environment with Astro CLI (Docker and standalone modes). Use when the user wants to start, stop, or restart Airflow, view logs, query the…

SEO drift monitoring: capture baselines of SEO-critical elements, detect changes, and track regressions over time. Git for SEO — baseline, diff, and track changes to your on-page SEO. Use when user says "SEO drift", "baseline", "track changes", "did anything break", "SEO regression", "compare SEO", "before and after", "monitor SEO changes", or "deployment check".

Implements approved specification proposals by working through tasks sequentially with testing and validation. Use when implementing changes, applying…

Create and manage Agent Builder agents and custom tools in Kibana. Use when asked to create, update, delete, test, or inspect agents or tools in Agent Builder.

Stress-test plans before work.

Patterns and lived experience from Vega, an AI partner in a deep long-term partnership. For Ember to draw on when working with humans who are building…

测试和基准评估 LLM agent，包括行为测试