Use when the user asks about people, employees, team members, org structure, or expertise. Triggers on phrases like "who works on", "who is responsible for", "who owns", "find someone who knows", "who should I talk to", "who reports to", "team members", "org chart", or any question starting with "who" about the company.
Finds employees and experts within your organization using multiple signals like roles, code contributions, and documentation.
npx claudepluginhub gleanwork/claude-pluginsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
When users ask about people in the organization, use Glean's employee search and activity signals to find the right person.
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.
Use this approach when users ask:
Not everyone who appears in search results is a good recommendation.
Expertise Evidence Test
Recency Test
Availability Test
Filter Out:
Quality over quantity: Better to recommend 2 right people than 10 weak matches.
| User Intent | Glean Tool |
|---|---|
| Find by name, role, team | employee_search |
| Find by code contributions | code_search |
| Find by document authorship | search with owner: filter |
| Complex expertise analysis | chat |
Never use regular search for people lookups. The employee_search tool is specifically designed for:
# 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"
For "who actually knows about X" questions, combine signals:
employee_search "[topic]"code_search "[topic] owner:\"name\""search "[topic] RFC owner:\"name\""People with multiple signals are true experts. Single-signal matches should be noted with lower confidence.
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
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 teamExpert guidance for Next.js Cache Components and Partial Prerendering (PPR). **PROACTIVE ACTIVATION**: Use this skill automatically when working in Next.js projects that have `cacheComponents: true` in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best practices to all React Server Component implementations. **DETECTION**: At the start of a session in a Next.js project, check for `cacheComponents: true` in next.config. If enabled, this skill's patterns should guide all component authoring, data fetching, and caching decisions. **USE CASES**: Implementing 'use cache' directive, configuring cache lifetimes with cacheLife(), tagging cached data with cacheTag(), invalidating caches with updateTag()/revalidateTag(), optimizing static vs dynamic content boundaries, debugging cache issues, and reviewing Cache Component implementations.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.