Create, review, run, inspect, pause, resume, and cancel durable JavaScript workflows that coordinate multiple headless Codex agents. Use for dynamic fan-out and fan-in, per-item analysis, multi-stage agent pipelines, loops or branches driven by worker results, long background runs, and ports of Claude Code dynamic workflows. Do not use for a small linear task that one Codex turn can handle directly.

For CLI agents WITHOUT subagent support (e.g., Codex CLI). Search previous code agent sessions for specific work, decisions, or code patterns.

Extract full context of the last task from the most recent parent session shown in the session lineage. Strategically uses sub-agents to avoid bloating your own context.

Maintain StaticPHP v3 packages and artifacts. Use when adding, modifying, reviewing, or validating config under config/pkg or config/artifact; package classes under src/Package; extension/library/target/tool dependencies; PHP configure args; build hooks; package metadata; or related tests and docs.

Synchronize bilingual documentation when StaticPHP v3 user-facing or developer-facing documentation must change. Use when adding, modifying, deprecating, or removing documented features, CLI commands/options, environment variables, configuration formats, public APIs/extension points, workflows, installation requirements, migration guidance, or user-visible behavior. Do not use solely for internal implementation changes, package/library additions, or build bug fixes unless they change documented behavior or require updating existing docs.

Diagnose StaticPHP v3 failures. Use when investigating build, compile, linker, download, doctor, environment, CI, smoke-test, terminal output, spc.output.log, spc.shell.log, config.log, CMake logs, or user-provided error snippets from StaticPHP commands.

Run local ClawSweeper exact-item or committed-range reviews without GitHub mutation.

Use the Crabbox wrapper for validation across Linux, macOS, Windows, and WSL2, including delegated Blacksmith Testbox proof. Report the actual provider and id.

运行项目测试（涵盖 Python 后端、Vue 前端及多语言校验）

进行深入访谈以收集需求并编写详细的规格说明书 (spec)

规划、实现或重构角色扮演模式（默认上帝视角下的单角色接管）时使用。适用于一期文本决策、二期统一有限选择框架、三期依附 Conversation 动作的自由对话，以及对应的 runtime/API/frontend/test 收口。

Use when working on tools/img_gen avatar image generation, OpenAI-compatible image API config, human or yaoguai portrait prompts, qi-refining base generation, image-to-image realm edits, white-background postprocessing, manifests, or prompt rules that preserve pixel-art identity while changing cultivation realms.

国际化 (i18n) 开发指南。在添加新文本、创建物品/事件、修改翻译或管理 PO/MO 文件时使用。

通过真实游戏模拟验证角色死亡、墓碑 POI 创建、地图渲染和点击详情。用于需要测试寿元死亡或其他游戏内死亡流程、墓碑 POI，且不得直接调用 handle_death 的任务。

创建包含正确远程处理的 Pull Request

运行 Phase 2 工作流。执行脚本扫描缺失的多语言词条，并按注册表补全启用语言（如 en-US、zh-TW、vi-VN、ja-JP、fr-FR），最后修复相关测试。

规划或实现面向外部 agent / Claw 的稳定控制 API，优先做底层分层、query/command 收口、runtime 串行化与契约文档，而不是零散补接口

Guide for using ToolHive CLI (thv) to run and manage MCP servers and skills. Use when running, listing, stopping, building, or configuring MCP servers locally. Covers server lifecycle, registry browsing, secrets management, client registration, groups, container builds, exports, permissions, network isolation, authentication, and skill management (install, uninstall, list, info, build, push, validate). NOT for Kubernetes operator usage or ToolHive development/contributing.

Reviews vMCP code changes for known anti-patterns that make the codebase harder to understand or more brittle. Use when reviewing PRs, planning features, or refactoring vMCP code.

Creates ToolHive release PRs by analyzing commits since the last release, categorizing changes, recommending semantic version bump type (major/minor/patch), and triggering the release workflow. Use when cutting a release, preparing a new version, checking what changed since last release, or when the user mentions "release", "version bump", or "cut a release".