Agent skill
vector-store
Transient vector store service for fast similarity search (FAISS)
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/vector-store
Metadata
Additional technical details for this skill
- port
- 8600
- endpoints
-
[ "/index", "/search", "/reset", "/info" ]
SKILL.md
Vector Store Skill
Transient vector store service for fast similarity search using FAISS (IndexFlatIP). Designed to be used by other skills (memory, edge-verifier) to accelerate KNN search.
Configuration
VECTOR_STORE_PORT: Port to listen on (default: 8600)
API
POST /index
Add vectors to the index.
{
"ids": ["id1", "id2"],
"vectors": [[0.1, 0.2, ...], [0.3, 0.4, ...]],
"reset": false
}
POST /search
Search for nearest neighbors.
{
"query": [0.1, 0.2, ...],
"k": 10
}
Returns:
{
"ids": ["id2", "id1"],
"scores": [0.95, 0.88]
}
DELETE /reset
Clear the index.
GET /info
Get index stats.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?