knowledge-synthesis
Deduplicates and synthesizes search results from multiple sources into coherent, attributed answers with confidence scoring.
- Merges duplicate information across sources using signals like matching content, authors, timestamps, and cross-references; prioritizes complete versions, authoritative sources, and recent updates
- Assigns confidence levels based on freshness (today vs. older than a month) and authority (official wiki > email > chat > drafts), and explicitly surfaces conflicting information when sources disagree
- Adapts output format to result set size: detailed presentation for 1–5 results, thematic grouping for 5–15 results, high-level synthesis with drill-down options for 15+ results
- Requires inline and end-of-answer source attribution including source type, location, date, author, and document titles; avoids listing raw results or organizing by source type
Knowledge Synthesis
The last mile of enterprise search. Takes raw results from multiple sources and produces a coherent, trustworthy answer.
The Goal
Transform this:
~~chat result: "Sarah said in #eng: 'let's go with REST, GraphQL is overkill for our use case'"
~~email result: "Subject: API Decision — Sarah's email confirming REST approach with rationale"
~~cloud storage result: "API Design Doc v3 — updated section 2 to reflect REST decision"
~~project tracker result: "Task: Finalize API approach — marked complete by Sarah"
Into this:
The team decided to go with REST over GraphQL for the API redesign. Sarah made the
call, noting that GraphQL was overkill for the current use case. This was discussed
in #engineering on Tuesday, confirmed via email Wednesday, and the design doc has
More from anthropics/knowledge-work-plugins
data-visualization
Create effective data visualizations with Python (matplotlib, seaborn, plotly). Use when building charts, choosing the right chart type for a dataset, creating publication-quality figures, or applying design principles like accessibility and color theory.
6.4Kcode-review
Review code changes for security, performance, and correctness. Trigger with a PR URL or diff, "review this before I merge", "is this code safe?", or when checking a change for N+1 queries, injection risks, missing edge cases, or error handling gaps.
4.2Ktask-management
Simple task management using a shared TASKS.md file. Reference this when the user asks about their tasks, wants to add/complete tasks, or needs help tracking commitments.
3.5Ksystem-design
Design systems, services, and architectures. Trigger with "design a system for", "how should we architect", "system design for", "what's the right architecture for", or when the user needs help with API design, data modeling, or service boundaries.
3.3Kdocumentation
Write and maintain technical documentation. Trigger with "write docs for", "document this", "create a README", "write a runbook", "onboarding guide", or when the user needs help with any form of technical writing — API docs, architecture docs, or operational runbooks.
3.3Kmemory-management
Two-tier memory system that makes Claude a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so Claude understands requests like a colleague would. CLAUDE.md for working memory, memory/ directory for the full knowledge base.
3.3K