pangcheng1849
15 verified skills
ip-diagnosis
在 macOS + Chrome 上排查公网 IPv4/IPv6 出口、国家/地区、ASN/组织、DNS、默认路由、utun 状态，以及浏览器侧 Server Response 与 WebRTC 暴露情况。适用于用户要求检查 IP、地区一致性、VPN/代理接管情况、IPv6 问题或浏览器网络暴露，并输出详细运维报告与复查链接。
development
parallel-implementation
Plan how to slice a non-trivial coding task across parallel subagents. Returns a dispatch plan (file assignments, dependencies, output-format contracts) — the main Agent then executes it with the Agent tool + `isolation: "worktree"`. Invoke only when work justifies multi-agent overhead: (a) greenfield 0→1 across multiple independent modules, (b) change touches ≥3 modules, or (c) ≥5 files each with >50 lines of diff. Small changes write inline.
tools
feishu-channel-doctor
诊断飞书频道健康状态 — 排查多进程冲突、WebSocket 连接问题、日志分析。当用户报告"没有回复""消息丢失""连接异常"或想查看飞书频道运行状态时使用。
development
feishu-channel-configure
设置飞书频道 — 保存应用凭证、查看访问策略和频道状态。当用户提供飞书应用凭证、要求配置飞书、问"怎么设置"或"谁能联系我"、或想查看频道状态时使用。
tools
claude-remote
Manage **remote-control** Claude Code sessions (i.e. `claude --remote-control`, NOT regular local sessions) running in Terminal.app — start, stop, list, or resume them for mobile / remote desktop access. Triggers on "start/open/launch a remote claude", "stop/kill remote session", "list remote sessions", "continue last remote conversation in <dir>".
development
feishu-channel-access
管理飞书频道访问控制 — 批准配对、编辑白名单、设置私聊/群组策略。当用户需要配对、批准某人、查看谁有权限、或更改飞书频道策略时使用。
tools
code-review
Review code for bugs, security issues, and performance
development
hello
Greet the user with a friendly message
tools
claude-code-agent
通过 Claude Code CLI 的 `claude -p` Agent SDK 入口，将编码、审查、诊断、规划和结构化输出任务委派给独立 Claude Code 会话。使用场景包括 `--resume` / `--continue` 续接多轮会话、`--output-format json` 单结果输出、`stream-json` 事件流，以及需要 `--worktree`、工具白名单、`--bare` 或结构化 JSON 输出的 scripted / CI 调用。
tools
deep-review
Run a formal, multi-dimensional code review of a pull request. Dispatches parallel reviewers (spec-conformance, correctness, test-quality, docs-sync, robustness, security, ux, performance, structure, code-quality, skill-plugin-quality) and synthesizes findings into a punch list. Use when the user asks to review a PR, run /deep-review, mark a PR as ready for review, or requests a formal/thorough code review.
tools
codex-agent
通过 Codex CLI 将编码、审查、诊断、规划、结构化输出和本机浏览器调研任务委派给独立的 Codex 会话。使用场景包括 `codex exec` 新建任务、`codex exec resume` 续接多轮会话、`codex exec review` 做只读审查，以及需要 `--json` 事件流、`-o` 最终消息落盘、图片输入或 Computer Use 浏览器操作时。
tools
feishu-channel-config
修改飞书频道体验配置 — 确认表情、引用回复、分块方式等。当飞书消息中用户请求更改频道显示/回复行为时使用。仅限体验配置，安全配置（策略、白名单、群组）必须拒绝。
tools
gemini-agent
通过 Gemini CLI 将编码、审查、诊断、规划和结构化输出任务委派给独立的 Gemini 会话。使用场景包括 `gemini -p` 非交互执行、`gemini -r latest` 续接最近会话、`gemini -r "<session-id>"` 指定会话恢复，以及需要 `--output-format json` / `stream-json`、`--approval-mode plan` 只读审查、`--sandbox` 隔离执行，或 `--worktree` 在独立 git worktree 中跑任务的 scripted / CI 调用。
tools
reviewer-creator
Scaffold a new project-level custom reviewer for the deep-review skill. Creates a properly-structured reviewer file at `docs/rules/review/<name>.md` that the deep-review orchestrator will discover and dispatch automatically. Use when the user asks to "create a custom reviewer", "add a project-specific reviewer", "扩展 deep-review", or invokes `/reviewer-creator`.
testing
test-designer
Design failing tests for complex features using Independent Evaluation — dispatches a context-free agent that sees only the requirement spec and code paths (not the implementation approach), then returns executable failing tests. Use when starting TDD for a non-trivial feature, when the requirement is ambiguous enough that biased tests are a risk, or when the user asks for independent test design.
development