npx skills add ...
npx skills add anthropics/knowledge-work-plugins --skill search-strategy
npx skills add anthropics/knowledge-work-plugins --skill search-strategy
Query decomposition and multi-source search orchestration. Breaks natural language questions into targeted searches per source, translates queries into source-specific syntax, ranks results by relevance, and handles ambiguity and fallback strategies.
If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.
The core intelligence behind enterprise search. Transforms a single natural language question into parallel, source-specific searches and produces ranked, deduplicated results.
Turn this:
Into targeted searches across every connected source:
Then synthesize the results into a single coherent answer.
Classify the user's question to determine search strategy:
| Query Type | Example | Strategy |
|---|---|---|
| Decision | "What did we decide about X?" | Prioritize conversations (~~chat, email), look for conclusion signals |
| Status | "What's the status of Project Y?" | Prioritize recent activity, task trackers, status updates |
| Document | "Where's the spec for Z?" | Prioritize Drive, wiki, shared docs |
| Person | "Who's working on X?" | Search task assignments, message authors, doc collaborators |
| Factual | "What's our policy on X?" | Prioritize wiki, official docs, then confirmatory conversations |
| Temporal | "When did X happen?" | Search with broad date range, look for timestamps |
| Exploratory | "What do we know about X?" | Broad search across all sources, synthesize |
From the query, extract:
For each available source, create one or more targeted queries:
Prefer semantic search for:
Prefer keyword search for:
Generate multiple query variants when the topic might be referred to differently:
Semantic search (natural language questions):
Keyword search:
Filter mapping:
| Enterprise filter | ~~chat syntax |
|---|---|
from:sarah | from:sarah or from:<@USERID> |
in:engineering | in:engineering |
after:2025-01-01 | after:2025-01-01 |
before:2025-02-01 | before:2025-02-01 |
type:thread | is:thread |
type:file | has:file |
Semantic search — Use for conceptual queries:
Keyword search — Use for exact terms:
Task search:
Filter mapping:
| Enterprise filter | ~~project tracker parameter |
|---|---|
from:sarah | assignee_any or created_by_any |
after:2025-01-01 | modified_on_after: "2025-01-01" |
type:milestone | resource_subtype: "milestone" |
Score each result on these factors (weighted by query type):
| Factor | Weight (Decision) | Weight (Status) | Weight (Document) | Weight (Factual) |
|---|---|---|---|---|
| Keyword match | 0.3 | 0.2 | 0.4 | 0.3 |
| Freshness | 0.3 | 0.4 | 0.2 | 0.1 |
| Authority | 0.2 | 0.1 | 0.3 | 0.4 |
| Completeness | 0.2 | 0.3 | 0.1 | 0.2 |
Depends on query type:
For factual/policy questions:
For "what happened" / decision questions:
For status questions:
When a query is ambiguous, prefer asking one focused clarifying question over guessing:
Only ask for clarification when:
Do NOT ask for clarification when:
When a source is unavailable or returns no results:
If initial queries return too few results:
Remove constraints in this order:
Always execute searches across sources in parallel, never sequentially. The total search time should be roughly equal to the slowest single source, not the sum of all sources.