基于 opencli 命令的智能搜索路由器。当用户想要使用 OpenCLI、CLI 或 API 搜索、查询、查找或研究信息时,尤其是涉及指定网站、社交媒体、技术资料、新闻、购物、旅游、求职、金融或中文内容时,务必使用此 skill
npx skills add https://github.com/mxyhi/ok-skills --skill smart-search
根据话题和场景,将查询路由到最佳的 opencli 搜索源。此 skill 的核心目标不是记忆命令,而是先定位数据源,再让 Agent 通过 opencli 自己读取实时帮助,避免文档漂移。
每次使用前,必须先做下面两步:
opencli list -f yamlstrategy、browser、domain选定站点后,必须再做下面两步:
opencli <site> -h 查看该站点有哪些子命令opencli <site> <command> -h 查看参数、输出列、策略不要在 skill 文档里硬编码参数或假设命令签名;以 opencli ... -h 的实时输出为准。
只使用这一条规则,不再维护多套优先级:
grok、doubao、gemini 三选一。把“单个用户问题”理解为同一意图链路下的一次问题求解;同一轮追问、澄清、补充条件,若核心问题未变,仍算同一题。
先建立一份站点调用台账。每次真正执行搜索命令后,立刻更新:
sitequerycountstatus计数规则:
opencli list -f yaml、opencli <site> -h、opencli <site> <command> -h 属于预检与帮助,不计入搜索次数opencli <site> ... 搜索/查询执行,计为该站点 1 次调用频率上限:
触发限频后的处理:
每次查询结束后,回答末尾必须追加一段简短的“搜索摘要”,至少包含下面三项:
如果有被限频跳过的站点,也要明确写出。
建议使用下面的固定格式:
搜索摘要
- 网站:<site1> | 查询词:<term1> | 次数:<n>
- 网站:<site2> | 查询词:<term2>;<term3> | 次数:<n>
- 已跳过:<site3>,原因:达到频率上限
grok适合实时讨论、英文互联网舆论、Twitter/X 语境、热点追踪。
doubao适合中文语境、字节抖音生态、生活方式内容、中文热点与泛中文问答。
gemini适合全球网页、英文资料、通用信息检索、背景综述。
如果用户没有指定网站,默认先判断语言和语境,再从这三个里只选一个。
一旦某个 AI 站点已经执行过一次真实查询,就不要在同一题里改写关键词后再次调用该 AI 站点。若答案不足,优先补专用源,不要反复追打同一个 AI 站点。
当使用 AI 源时,不要只丢一个过短关键词。优先构造成“主题 + 目标 + 限定条件”的查询。
用户真正要查的对象、事件、产品、人物、公司、技术名词。
想要什么结果,例如总结、对比、原因、趋势、推荐、原始线索。
语言、地区、时间范围、平台范围、受众、价格带、岗位地点、是否要引用原始来源。
优先使用下面这种表达方式:
<主题> + <你要回答的问题><主题> + <时间范围/地区/语言><主题> + <平台或来源范围><主题> + <输出要求>避免只输入:
当出现以下任一情况时,再补充专用源:
单次查询通常控制在 1 个 AI 源 + 1 到 2 个专用源,避免结果过载。
当站点不可用时:
opencli list -f yaml 与 opencli <site> -h 的实际结果为准不要假设任何站点“绝对可用”。即使是公开站点,也以当前环境中的 live help 和执行结果为准。
根据需要读取对应文件:
references/sources-ai.md — AI 默认源references/sources-tech.md — 技术 / 学术references/sources-social.md — 社交媒体references/sources-media.md — 媒体 / 娱乐references/sources-info.md — 资讯 / 知识references/sources-shopping.md — 购物references/sources-travel.md — 旅游references/sources-other.md — 其他垂直源只读与当前查询相关的文件,无需全部加载。
Generate clinical trial protocols for medical devices or drugs. This skill should be used when users say "Create a clinical trial protocol", "Generate protocol for [device/drug]", "Help me design a clinical study", "Research similar trials for [intervention]", or when developing FDA submission documentation for investigational products.
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.
Multi-agent research skill for parallel research execution (10 agents, battle-tested with real case studies).
Generate and prioritize US equity long-side edge research tickets from EOD observations, then export pipeline-ready candidate specs for trade-strategy-pipeline Phase I. Use when users ask to turn hypotheses/anomalies into reproducible research tickets, convert validated ideas into `strategy.yaml` + `metadata.json`, or preflight-check interface compatibility (`edge-finder-candidate/v1`) before running pipeline backtests.
Use this skill when building or modifying Minecraft server plugins for Paper, Spigot, or Bukkit, including plugin.yml setup, commands, listeners, schedulers, player state, team or arena systems, persistent progression, economy or profile data, configuration files, Adventure text, and version-safe API usage. Trigger for requests like "build a Minecraft plugin", "add a Paper command", "fix a Bukkit listener", "create plugin.yml", "implement a minigame mechanic", "add a perk or quest system", or "debug server plugin behavior".
Internal guidance for composing Codex and GPT-5.4 prompts for coding, review, diagnosis, and research tasks inside the Codex Claude Code plugin
Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade and prompt-upgrade guidance; use OpenAI docs MCP tools for non-Codex docs questions, use the Codex manual helper first for broad Codex self-knowledge, and restrict fallback browsing to official OpenAI domains.
This skill should be used when designing autonomous agent harnesses: research loops, evaluation scaffolds, locked and editable surfaces, durable logs, novelty gates, pruning, rollback, PR preparation, and human approval boundaries.
Take mxyhi/smart-search from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.