"search", "find", "query"?
search (full-text) or semantic_search (meaning)
← Skill registry
Agent infrastructurePublic skills
Search Engine
Full-text and semantic search for AI agents — query, index, vector search, autocomplete, ranking debug, synonym management, and search analytics.
What this skill teaches
A reusable playbook for a specific kind of work.
An MCP server tells an agent which actions are available. A skill adds the judgment around those actions: how to recognize the job, which sequence to follow, what to avoid, and how to decide that the result is complete.
Orchestrate search operations — full-text search, vector/semantic search, autocomplete, index management, synonym configuration, and search analytics. Use when searching documents, building search indexes, running semantic queries, managing synonyms, analyzing search performance, or debugging ranking.
Architecture
How Search Engine guides an ADK-Rust agent.
The skill stays readable and portable because it contains instructions rather than service credentials or business data. ADK-Rust supplies it to the agent, the agent chooses from its reviewed tool boundary, and the connected MCP server performs the authenticated operation.
01
User request
The agent receives a goal expressed in ordinary language.
02
Search Engine skill
Matches intent, supplies the decision guide, and narrows the tool boundary.
03
ADK-Rust agent
Plans the workflow and streams each meaningful step through the runtime.
04
mcp-search
Executes authenticated operations against the system that owns the capability.
05
Verified result
The skill's completion rules shape the evidence returned to the user.
Decision guide
How the agent turns a request into the right action.
These routes come directly from the skill instructions. They help the model recognize intent and select a focused tool or workflow instead of improvising across the entire capability surface.
"similar", "like this", "related"?
find_similar / query_vectors
"autocomplete", "suggest"?
suggest
"index", "add document", "ingest"?
index_document / upsert_vectors
"create index", "schema"?
create_index
"why ranked", "explain", "debug"?
explain_ranking / test_query
"analytics", "performance", "zero results"?
get_search_analytics
"synonyms"?
get_synonyms / update_synonyms
Proven workflows
Repeatable sequences for useful outcomes.
A workflow joins several tool calls into a task the user actually recognizes. The skill explains the sequence and the intended result while ADK-Rust streams the agent's progress through the shared runtime.
011 calls
Full-Text Search
Keyword search with filters
021 calls
Semantic Search
Meaning-based (vector)
031 calls
Index Document
Add/update in index
042 calls
Debug Ranking
Explain why doc ranked where
052 calls
Improve Relevance
Find zero-results → add synonyms
06Best For calls
Mode
Tool
Tool boundary
The skill may use 20 documented tools.
This allowlist is declared by the skill. It keeps the agent focused on the actions needed for this job while mcp-search retains responsibility for authentication, validation, and the connected system.
search
semantic_search
multi_search
suggest
find_similar
list_indexes
get_index
create_index
index_document
delete_document
upsert_vectors
query_vectors
list_namespaces
get_vector_stats
get_search_analytics
get_index_stats
explain_ranking
test_query
get_synonyms
update_synonyms
Working rules
What the agent should do.
- Use semantic_search when user intent matters more than exact keywords
- Check get_search_analytics regularly for zero-result queries
- Add synonyms for common terms that return no results
- Use explain_ranking to debug unexpected ordering
Operating boundaries
What the agent should avoid.
- Don't use full-text search for vague/conceptual queries (use semantic)
- Don't index without specifying searchable fields
- Don't ignore zero-result queries (they indicate gaps)
Install and connect
Add the skill beside the capability it expects.
Install the repository where your ADK-Rust skill loader can discover it, connect mcp-search, and confirm the declared tools are available before asking the agent to use the workflow.
Install the skill
git clone https://github.com/zavora-ai/skill-search-engine.git \
~/.skills/skills/search-engineADK-Rust loading shape
let skills = SkillLoader::from_dir("~/.skills/skills").await?;
let skill = skills.load("search-engine").await?;
let agent = LlmAgentBuilder::new("agent")
.instruction(skill.instructions())
.tools(skill.allowed_tools(toolset)?)
.build()?;The repository's compatibility statement: Requires mcp-search server connected (Meilisearch, Typesense, Elasticsearch, Pinecone, or custom).
Official documentation
Read the complete skill package.
The repository remains authoritative for its exact instructions, examples, helper scripts, assets, MCP requirements, license, and later updates.
Keep exploring
More in agent infrastructure.
A2A Agent OrchestrationMulti-agent coordination — discover capabilities, dispatch tasks, stream results, and manage remote agent lifecycles via the A2A protocol.10 allowed toolsACP Workspace ManagementCoding agent workspace control — start sessions, delegate tasks to coding agents, review proposed patches, manage permissions, and publish agents with governance gates.9 allowed toolsArtifact LifecycleGoverned artifact management — versioned storage, provenance tracking, integrity verification, derivation chains, and export packaging for build outputs and documents.10 allowed tools
Source record
Repository metadata for this skill entry.
- License
- Apache-2.0
- Allowed tools
- 20
- References
- 3
- Revision
- b72a8a4f88bd
- Updated
- May 31, 2026