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"
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.
6.8Kcode-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.
4.5Ktask-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.
3.8Kdocumentation
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.
3.6Ksystem-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.
3.6Kmemory-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.
3.5K