论文安装
- 作者仓库星标 1
- 作者更新于 实时读取
- 作者仓库 researchbuddy
- 领域
- 工程开发
- 兼容 Agent
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- 信任分
- 88 / 100 · 社区维护
- 作者 / 版本 / 许可
- @willemave · 未声明 license
- Token 消耗评级
- 低消耗
- 接入复杂程度
- 需简单配置
- 是否需要外部 API Key
- 需要 · Firecrawl
- 兼容的系统
- 未声明(默认跨平台)
- 底层运行要求
- 无特殊要求
- 文件与系统权限
-
- 只读
- 允许写入 / 修改
- 读取环境变量
- 网络行为
- 允许外网请求
- 安装命令数
- 26 条
档案由构建时根据 SKILL.md 与安装命令自动衍生,可能与作者实际意图存在差异。
需要注意: 未限定 allowed-tools,默认拥有全部工具权限。
---
name: research
description: Use when a user asks to research something with ResearchBuddy, run web research or deep research…
category: 工程开发
runtime: 无特殊运行时
---
# research 输出预览
## PART A: 任务判断
- 适用问题:代码实现、重构、调试或代码审查。
- 输入要求:目标材料、限制条件、期望输出和验收方式。
- 证据边界:围绕“Quick Start / Read These References As Needed / Operating Rules”读取原文规则,不把推断写成作者承诺。
## PART B: 执行结果
- **01** 任务判断:确认你的需求是否属于代码实现、重构、调试或代码审查,并标出输入、限制和预期结果。
- **02** 执行计划:优先按“Quick Start / Read These References As Needed / Operating Rules”拆成步骤,说明每一步会读取什么、修改什么、产出什么。
- **03** 交付结果:给出可复制的命令、文件改动、检查清单或内容草稿,并说明如何继续迭代。
- **04** 风险边界:结合 读取文件、写入/修改文件、读取环境变量、会按任务需要访问外部网络、需要准备 Firecrawl API Key 给出执行前确认项。
## Running Rules
- 读取文件、写入/修改文件、读取环境变量;会按任务需要访问外部网络;需要准备 Firecrawl API Key。
- 先小样例验证,再放大到真实任务。
- 交付时同时给结果、检查口径和下一步迭代建议。 原文出现了 `/path` 这类斜杠命令;如果你的 Agent 支持命令触发,优先用命令开场,再补充目标和边界。
告诉 Agent 目标文件或材料、期望结果、不可改范围、是否允许联网或执行命令。本 Skill 的权限画像是:读取文件、写入/修改文件、读取环境变量。
先用一个小任务确认它会围绕“Quick Start / Read These References As Needed / Operating Rules”工作;涉及文件或命令时,先看 diff、日志、预览或测试结果。
检查最终产物是否包含明确结果、必要证据和下一步动作;如果输出泛泛而谈,就补充输入、边界和验收标准后重跑。
---
name: research
description: Use when a user asks to research something with ResearchBuddy, run web research or deep research…
category: 工程开发
source: willemave/researchbuddy
---
# research
## 什么时候使用
- 把工程方向的常用动作沉淀成 Agent 可调用的技能 适合处理工程开发场景下的代码实现、调试、重构、测试或代码审查,核心价值是把输入、判断、执行、验证和交付边界固定下来,避免 Agent 泛泛回答。 把任务拆成可执行、可检查、可继续迭代…
- 面向代码实现、重构、调试或代码审查,优先处理能明确输入、步骤和验收标准的工作。
## 需要提供什么
- 目标材料、目录范围、期望结果和不可改动内容。
- 是否允许联网、执行命令、读写文件或调用外部服务。
## 执行规则
- 围绕「Quick Start / Read These References As Needed / Operating Rules」组织步骤,不把推断写成作者事实。
- 读取文件、写入/修改文件、读取环境变量;会按任务需要访问外部网络;需要准备 Firecrawl API Key。
- 先跑小样例,确认结果可检查后再扩大任务范围。
## 输出要求
- 给出最终产物、关键证据、验证方式和下一步动作。
- 信息不足时标记 unknown,不编造命令、平台或依赖。 作者原文负责流程事实;仓库文件负责来源和命令;流狐只补充适用场景、限制和质量判断。
skill "research" {
输入层 -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
上下文层 -> Quick Start / Read These References As Needed / Operating Rules
规则层 -> SKILL.md 触发条件 / 执行顺序 / 输出格式
运行层 -> 无特殊运行时 | 读取文件、写入/修改文件、读取环境变量 | 会按任务需要访问外部网络
安全层 -> 需要准备 Firecrawl API Key + 小任务验证 + diff / 日志复核
输出层 -> 可复制结果 + 检查清单 + 下一步迭代
} Research
Use this skill when the task is about using ResearchBuddy for research, installing it with Homebrew, asking questions against saved sessions, or fixing a machine that fails runtime checks.
Quick Start
- Install with
brew tap willemave/researchbuddyandbrew install researchbuddyunless the user explicitly wants a source checkout. - Run
researchbuddy --helpto confirm the installed command surface. - For OpenClaw, install this skill with
researchbuddy skills install openclaw --scope shared, or use--scope workspace --workspace /path/to/workspacefor one workspace only. - In OpenClaw environments, inspect
~/.openclaw/openclaw.jsonbefore asking for search-provider credentials. If it already hasplugins.entries.<provider>.config.webSearch.apiKey, legacytools.web.search.<provider>.apiKey, ortools.web.search.apiKeyforexa,tavily, orfirecrawl, ask once whether ResearchBuddy should reuse it. - If the user approves reuse, do not ask them to paste a duplicate API key. Run
researchbuddy doctor --fix; ResearchBuddy auto-loads OpenClaw config and does not copy provider credentials into local.env. - If OpenClaw has no usable provider config, or the user declines reuse, ask for one provider key and set it through the runtime environment or local
.env, then rerunresearchbuddy doctor --fix. - Start long research jobs with
researchbuddy start "<prompt>" --json; the command returns immediately with the run ID, PID, status command, watch command, and log path. - Use
researchbuddy status,researchbuddy watch, andresearchbuddy followup "<question>"against the current run by default.
Read These References As Needed
- For every public command and option, read
references/commands.md. - For dependency failures and recovery steps, read
references/troubleshooting.md.
Operating Rules
- Prefer the Homebrew-installed
researchbuddycommand. Usescripts/researchbuddyonly inside a source checkout. - During first-time OpenClaw installs, prefer reusing the provider configured in
~/.openclaw/openclaw.jsonover asking the user for a freshEXA_API_KEY,TAVILY_API_KEY, orFIRECRAWL_API_KEY. - Do not copy OpenClaw secrets into skill files, chat logs, docs, command output, or ResearchBuddy
.env. Let ResearchBuddy load them directly from OpenClaw or Hermes. - Before debugging a broken runtime, run
researchbuddy doctor. - For long research work, use
researchbuddy start "<prompt>" --json; do not manually background a worker process. - Use
researchbuddy status --jsonwhen another agent or script needs machine-readable progress. - Use
researchbuddy watch --timeout 900when you need to stream the active worker log until completion. - ResearchBuddy currently ships cleanly as a packaged CLI, not a hosted web service.
- The runtime depends on the external
codexCLI. Ifdoctorfails oncodex, do not treat the environment as production-ready. - If
doctorfails onffmpeg, follow the OS-specific install steps inreferences/troubleshooting.md, verify withffmpeg -version, then rerunresearchbuddy doctor.
Public Commands
researchbuddy startresearchbuddy followupresearchbuddy statusresearchbuddy watchresearchbuddy doctorresearchbuddy skills install openclawresearchbuddy list
Read references/commands.md before using less-common options such as --prompt-file, --result-file, --output-dir, model overrides, --skip-playwright, or JSON output.
Config Model
- ResearchBuddy is env-driven. It reads process environment variables,
~/.hermes/.env,~/.openclaw/.env,~/.openclaw/openclaw.json, and local.env. - Shared agent configs are canonical for search-provider credentials; local
.envis only for manual fallback config. researchbuddy doctor --fixvalidates detected search-provider config, prepares storage/database, installs Playwright browsers, and repairs stale runs. It does not copy provider credentials into.env.- Homebrew installs should not edit files under the Homebrew prefix or uv cache for config.
Outputs
- Run artifacts are written under
~/.researchbuddy/storage/<run_id>/by default. - Key files are
synthesis.md,worker.log,run.log, and thehtml//markdown/crawl artifacts.
先判断是否适合
作者设计意图
作者的方法与取舍
边界和复核