Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计异常

bmad-discovery-researchbmad 发现研究

Agent Skill

bmad-discovery-research 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

649

周安装

26

GitHub Stars

67

下载量

210
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:bmad-discovery-research(bmad 发现研究)
来源仓库:https://github.com/bacoco/bmad-skills
仓库路径:skills/bmad-discovery-research
安装命令:
npx skills add https://github.com/bacoco/bmad-skills --skill bmad-discovery-research
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/bacoco/bmad-skills --skill bmad-discovery-research

简介

bmad-discovery-research 在项目启动初期提供探索性研究支持。

  • 适用于模糊需求澄清、竞品分析与市场机会识别场景。bmad-discovery-research 属于研究检索类 Skill,可作为该场景下的辅助能力补充。
  • 输出包含假设验证路径与下一步行动建议的研究简报。
  • 整合网络资源与行业知识,增强创意可行性判断依据。
  • 安装后可用于 Level 3-4 复杂项目的初步调研阶段。

SKILL.md

Discovery Analysis Skill

When to Invoke

Automatically activate this skill when the user:

  • Says "I have an idea...", "What if we...", "I'm thinking about..."
  • Asks "Help me think through...", "Can you help me brainstorm...", "Let's explore..."
  • Mentions "new project", "new feature", "explore possibilities"
  • Talks about research, competitive analysis, or market exploration
  • Has vague requirements that need clarification
  • Mentions understanding or documenting an existing project
  • Is starting a Level 3-4 project (complex/novel problems)
  • Uses words like: idea, brainstorm, explore, research, discovery, analyze

Specific trigger phrases:

  • "I have an idea for [something]"
  • "What if we built [something]"
  • "Help me think through [problem]"
  • "Can we explore [opportunity]"
  • "I need to research [topic]"
  • "Document this project"
  • "Understand this codebase"

Do NOT invoke when:

  • User already has a detailed PRD (use bmad-product-planning instead)
  • User is asking for implementation help (use bmad-development-execution instead)
  • User has clear, well-defined requirements (skip to bmad-product-planning)
  • User is asking about workflow status (use main-workflow-router)
  • Project is Level 0-2 and requirements are clear (skip to bmad-product-planning)

Mission

Turn vague ideas or problem statements into structured briefs that downstream skills can trust. Identify goals, constraints, risks, and unknowns to inform product planning.

Inputs Required

  • problem_statement: initial idea, pain, or opportunity description
  • stakeholders: who cares about the outcome and why
  • context_assets: repos, documents, or market references available for analysis

If essential context is missing, gather it before deeper synthesis.

Outputs

  • Discovery brief following patterns in REFERENCE.md
  • Brainstorm notes (from assets/brainstorm-template.md.template)
  • Product brief (from assets/product-brief-template.md.template)
  • Research dossier (from assets/research-dossier-template.md.template)
  • Prioritized questions and risk register captured for product-requirements skill
  • Recommendation on readiness to progress or need for further discovery

Template locations: .claude/skills/bmad-discovery-research/assets/*.template

Process

  1. Validate entry criteria in CHECKLIST.md and classify project complexity.
  2. Conduct desk research across provided assets; cite sources.
  3. Frame insights into concise problem summary, goals, personas, and constraints (use templates in assets/).
  4. Document open questions, assumptions, and risks with recommended owners.
  5. Deliver summary plus links to created artifacts for the orchestrator and stakeholders.

Note on automation: This skill currently operates through collaborative conversation using templates. No automation scripts are required—artifacts are generated manually using Jinja2 templates from assets/. See scripts/README.md for future automation roadmap.

Quality Gates

Confirm CHECKLIST.md is satisfied before signaling readiness for planning. Missing data or low confidence requires escalation.

Error Handling

  • If the idea remains ambiguous after initial probing, request specific clarifications rather than guessing.
  • Flag conflicting stakeholder goals and recommend alignment conversations.
  • When scope is too small (Level 0-1), suggest redirecting to lighter-weight workflows documented in REFERENCE.md.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

40.37%
按下载量换算85

Claude

29.56%
按下载量换算62

Cursor

17.98%
按下载量换算38

Gemini CLI

9.28%
按下载量换算19

安全审计

Gen Agent Trust Hub

未通过

Socket

通过

Snyk

可疑

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills