Token导航 LogoToken导航TokenDH.com
研究检索external-servicegithub未标认证来源可访问许可证需确认审计通过

people-lookup人员查找

Agent Skill

people-lookup 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

282

周安装

12

GitHub Stars

20

下载量

99
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:people-lookup(人员查找)
来源仓库:https://github.com/gleanwork/claude-plugins
仓库路径:skills/people-lookup
安装命令:
npx skills add https://github.com/gleanwork/claude-plugins --skill people-lookup
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/gleanwork/claude-plugins --skill people-lookup

简介

用于查找、检索和筛选相关信息。people-lookup 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

  • 适合根据关键词或任务场景快速定位候选结果。
  • 可结合来源仓库和原始 README 继续核验具体用法。
  • 安装前建议确认权限范围、维护状态及是否触发联网或文件读写。
  • 归类为研究检索类,符合其搜索定位的核心能力。

SKILL.md

People Lookup via Glean

When users ask about people in the organization, use Glean's employee search and activity signals to find the right person.

Tool Naming

See the glean-tools-guide skill for Glean MCP tool naming conventions. Tools follow the pattern mcp__glean_[server-name]__[tool] where the server name is dynamic. Use whatever Glean server is available in your tool list.

When This Applies

Use this approach when users ask:

  • "Who works on [system/project]?"
  • "Who is [name]?" or "What team is [name] on?"
  • "Who should I talk to about [topic]?"
  • "Who owns [component/service]?"
  • "Who reports to [manager]?"
  • "Find someone who knows about [technology]"

BE SKEPTICAL

Not everyone who appears in search results is a good recommendation.

Expertise Evidence Test

  • Is there real evidence of expertise?
  • ✅ STRONG: Multiple signals (code + docs + involvement)
  • ⚠️ MODERATE: Single signal but significant
  • ❌ WEAK: Just mentioned once, attended a meeting

Recency Test

  • Are they actively involved?
  • ✅ ACTIVE: Activity in past 6 months
  • ⚠️ HISTORICAL: 6-12 months ago
  • ❌ STALE: 12+ months - likely outdated

Availability Test

  • Are they still in a relevant position?
  • ✅ CURRENT: Same team/role
  • ⚠️ MOVED: Changed teams but retains knowledge
  • ❌ GONE: Left company or completely different role

Filter Out:

  • Single mentions without other evidence
  • People who just attended meetings on a topic
  • Former employees
  • People whose involvement is tangential

Quality over quantity: Better to recommend 2 right people than 10 weak matches.

Tool Selection

User IntentGlean Tool
Find by name, role, teamemployee_search
Find by code contributionscode_search
Find by document authorshipsearch with owner: filter
Complex expertise analysischat

Critical: Use employee_search for People Queries

Never use regular search for people lookups. The employee_search tool is specifically designed for:

  • Name lookups
  • Role/title searches
  • Team/department queries
  • Org chart navigation
  • Reporting relationships

Query Examples

# Find by name
employee_search "John Smith"

# Find by team
employee_search "payments team"

# Find direct reports
employee_search "reportsto:\"Jane Doe\""

# Find by role type
employee_search "engineering managers"

# Find recent hires
employee_search "startafter:2024-01-01"

Finding Expertise (Not Just Role)

For "who actually knows about X" questions, combine signals:

  1. Official role: employee_search "[topic]"
  2. Code activity: code_search "[topic] owner:\"name\""
  3. Doc authorship: search "[topic] RFC owner:\"name\""

People with multiple signals are true experts. Single-signal matches should be noted with lower confidence.

If No Good Matches Found

Don't pad with weak recommendations:

No strong expertise matches found for [topic].

**What was checked:**
- Employee search: [results]
- Code contributions: [results]
- Doc authorship: [results]

**Suggestions:**
- Ask in [relevant channel]
- Check with [related team] leadership

Relationship to Commands

For comprehensive expertise discovery, suggest:

  • /glean-people:find-expert <topic> - Multi-signal expertise analysis
  • /glean-people:stakeholders <change> - Find who needs to be involved
  • /glean-docs:onboarding <team> - Get to know a new team

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

33.98%
按下载量换算34

Claude

30.47%
按下载量换算30

Cursor

19.52%
按下载量换算19

Gemini CLI

9.08%
按下载量换算9

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

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。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