40 skills · sorted by relevance
OpenViking long-term memory plugin guide. Once installed, the plugin automatically remembers important facts from conversations and recalls relevant context before responding.
The English summary is being prepared. Showing the original description.
Activate when the user asks about any repository listed in the system prompt under 'OpenViking — Indexed Code Repositories', or when they ask about an external library, framework, or project that may have been indexed. Also activate when the user wants to add, remove, or manage repos. Always search the local codebase first before using this skill.
The English summary is being prepared. Showing the original description.
Operate and maintain OpenViking server - configure, install, start, stop, and cleanup the server. Use when need to setup or manage OpenViking service deployment.
The English summary is being prepared. Showing the original description.
Design knowledge systems that preserve document structure and connections across sources. Choose retrieval methods, organize conversation memory, and plan evidence-based updates, review workflows, and access controls for information that scattered text searches cannot adequately cover.
Summarize articles, YouTube videos, podcasts, and local files, or extract available text and transcripts. Choose the summary length to suit the task and use transcript extraction to inspect video content when available.
Turn documents, notes, research, or code into a knowledge graph that maps identifiable things and their relationships. Create or update entity files and typed connections, with source evidence attached for inspection and later visualization.
Get current weather and forecasts for a city or airport without an API key. Retrieve brief reports with temperature, humidity, and wind, save a forecast image, or use Open-Meteo for structured weather data.
Turn recurring procedures and specialized knowledge into reusable agent skills. It guides the design of SKILL.md, scripts, reference documents, and output assets, then validates the structure and packages the files for distribution.
Convert GitHub resource links into proxy URLs for cloning repositories and downloading files when access is slow. Covers release attachments, raw files, repository archives, and Gist files, with a Python helper for URL conversion.
Control interactive command-line tools through tmux by sending keystrokes, capturing terminal output, and waiting for prompts. Supports session management and running multiple coding agents in parallel, with helper scripts for finding sessions and detecting text.
Work with GitHub issues, pull requests, and automated checks through the gh command-line tool. Inspect failed workflow steps and their logs, retrieve selected fields, and query the GitHub API for data beyond standard commands.
Schedule reminders and recurring work with the cron tool. Send fixed messages, have an agent execute tasks and report results, or arrange a one-time action at a specified time. List and remove scheduled jobs as needed.
Inspect OpenCode sessions with helper scripts that list sessions and retrieve their latest messages. Use the last message’s sender as a rough guide to task status when checking activity across multiple OpenCode sessions.
从 0 到 1 搭建、配置、验收和维护真实数据驱动的销售智能工作台，覆盖需求澄清、Agent Plan 模型、专业数据集（DataPro）、豆包搜索（联网搜索）、AI Native 应用开发底座（Supabase）、Agent 记忆（OpenViking）、Codex CLI 调度飞书 CLI 导入资料，以及企业搜索、档案和资料问答闭环。用户要求搭建销售工作台、部署或继续开发该项目、导入销售资料、排查 Provider、迁移数据库、备份恢复或验收真实业务链路时使用。
The English summary is being prepared. Showing the original description.
ARK 套餐管理(Agent Plan / Coding Plan,个人版 + 企业版):查询持有 / 购买 / 续费 / 模型清单 / 轮换 APIKey,**以及企业版席位的全部管理操作**:列出席位(`plans team seat-list`)、给员工分配席位(`plans team seat-assign`)、查谁绑了哪个 seat、轮换席位 APIKey(`plans team rotate-apikey`)。也负责购买参数的逐步澄清，以及 `payment_failed` + Order ID 后回到已有订单补单/取消，禁止重新 buy。命中关键词:套餐 / 买 / 续费 / 列席位 / 看 seat 绑定 / 谁绑了哪个 seat / 给员工分席位 / 解绑 / 团队席位 admin 视图 / 轮换 APIKey。反触发：Token 额度包/资源包不是 Agent Plan/Coding Plan，应走 arkcli-profile 判断 platform 切面。**用量类问题(还剩多少额度 / 用了几成 / 每个 seat 用了多少)走 [arkcli-usage](../arkcli-usage/SKILL.md)。**动词路由:**列 / 绑 / 分 / 轮换 / 解绑** → 这里;**用 / 消耗 / 多少** → arkcli-usage。另含 harness-status:只读查看本机 AI Agent(claude-code/codex/opencode/openclaw/trae)上 Agent Plan 内置 MCP(豆包搜索/dataPro/OpenViking)装没装、key 就没就绪;命中:我的 MCP 装好了吗 / 查 MCP 安装状态 / 看 agent 上的 MCP / harness 状态。
The English summary is being prepared. Showing the original description.
arkcli helper：为 Claude Code / Codex / OpenCode / OpenClaw / Hermes / ZCode 配置火山方舟 Plan 或 Platform Endpoint 的 model/provider，或给支持的 Agent（含 MCP-only Trae）配置 Harness 工具。真人 TTY 运行 `arkcli helper` 可选择模型和 Harness 能力；`helper mcp` 默认保持整组 Agent Plan MCP 行为，传 `--capability datapro|web-search|agent-memory` 只配单项，传 `--capability cua` 只给目标 Agent 安装云电脑 Skill；连 model/provider 一起配置用 `helper configure`，查状态用 `helper list`，移除用 `helper reset`。Agent Plan / Team 还支持专业数据集、豆包搜索、Agent 记忆、AI Native 应用开发底座、Agent 进化与 routing.v1 强制检索路由；上下文出现 ARKCLI ROUTING ENFORCEMENT / routing.v1，或用户要求在豆包搜索、DataPro、OpenViking、Supabase 之间强制分流时也使用本 Skill：调用这四类受管 Provider 前先提交 Route Plan，再调用唯一授权 Provider；原生 WebSearch/WebFetch/WebExtract 位于路由管理范围之外。Platform 只允许本人创建、Running、已验证为文本输出的 Endpoint，不配置 MCP、Supabase 或强制路由。豆包搜索配置成功后默认关闭目标客户端原生 WebSearch；传 `--keep-native-websearch` 可保留，并可用 `helper reset` 完整恢复 ArkCLI 配置。
The English summary is being prepared. Showing the original description.