Profile My skills Saved My plugins Edit profile Submit a skill

all publishers

zilliztech

@zilliztech source repo

70 published skills

  1. ▌
    Memory Config 2 · zilliztech bundle
    Diagnose and configure MemSearch memory behavior. Use when the user asks about MemSearch configuration, plugin summarization, PROJECT.md/USER.md maintenance, memory directories, index health, provider routing, prompt files, or migration/compatibility questions.
    5 installs
  2. ▌
    Memory To Skill 3 · zilliztech bundle
    Turn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under .memsearch/skill-candidates/, not the host agent's own skills system.
    5 installs
  3. ▌
    Memory To Skill · zilliztech bundle
    <!--
    5 installs
  4. ▌
    Memory To Skill 2 · zilliztech bundle
    Turn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under .memsearch/skill-candidates/, not the host agent's own skills system.
    5 installs
  5. ▌
    Sync Zilliz Plugin · zilliztech
    Use when the user asks to sync, update, or check drift of this gemini-cli extension against upstream zilliztech/zilliz-plugin. Triggers on phrases like "同步上游", "sync from zilliz-plugin", "update commands from plugin", "check if plugin upstream changed". Runs scripts/sync.mjs to regenerate commands/zilliz/*.toml from upstream skills/*/SKILL.md.
    3 installs
  6. ▌
    Milvus · zilliztech bundle
    Operate Milvus vector database with pymilvus Python SDK. Use when the user wants to connect to Milvus, create collections, insert vectors, perform similarity search, hybrid search, full-text search, manage indexes, partitions, databases, or RBAC via Python code.
    4 installs
  7. ▌
    Terraform Acc Test · zilliztech bundle
    Run Terraform provider acceptance tests from a local Go provider repository. Use when the user asks Codex to run Terraform acc tests, acceptance tests, TF_ACC tests, or a command like `TF_ACC=1 go test`, especially when they mention loading `.env.test` or `.evn.test`, locating a test case package, or running `TestAccOnDemandClusterResource`.
    3 installs
  8. ▌
    Zilliz Launchpad · zilliztech bundle
    Turn a sample document into a running Milvus / Zilliz Cloud search app in minutes. Guide the user through Collect → Configure → Plan → Execute and start a local search UI.
    5 installs
  9. ▌
    Zilliz · zilliztech bundle
    Manage Zilliz Cloud vector databases via zilliz-cli. Use when the user wants to: (1) set up zilliz-cli (install, login, configure), (2) manage clusters (create, list, describe, suspend, resume, delete, modify), (3) manage collections, indexes, partitions, databases, or aliases, (4) perform vector operations (search, query, insert, upsert, delete, hybrid search), (5) manage database users, roles, and RBAC privileges, or cloud-level access control (org/project roles, member and group grants), (6) handle backups, imports, billing, monitoring, projects, regions, or async jobs. Triggers on: zilliz, vector database, semantic search, RAG, embeddings, collection schema, vector index, similarity search, zilliz-cli.
    6 installs
  10. ▌
    Zdoc Local Doc Ops · zilliztech
    Use when a ZDoc request asks to sync SDK docs, draft a source-verified doc, verify Feishu doc code, or plan code-example patches.
    6 installs
  11. ▌
    Offline Translation · zilliztech bundle
    Translate selected zdoc documents outside the paid Translation workflow, assemble an auditable candidate, and publish it through the trusted offline Translation validation, reconciliation, and publication coordinator. Use for offline ja-JP Guides translation or recovery; do not use for ordinary Fetch, Reference translation, or direct content publication.
    4 installs
  12. ▌
    Zdoc Feishu Doc Publish · zilliztech
    Use when asked to publish Zilliz docs from Feishu/Lark doc links to UAT or production, especially requests like "@bot 请帮我发布以下文档到 UAT" with Feishu doc/wiki links. Also covers single-doc publish to a version branch, Japanese (ja-JP) offline retranslation, sidebar and localization-inventory regeneration, and the Jenkins version-branch release.
    6 installs
  13. ▌
    Mfs Find · zilliztech bundle
    Search, grep, browse, and read across registered MFS data sources via the `mfs` CLI — codebases, docs, PDFs, web crawls, databases (postgres/mysql/mongo/snowflake/bigquery), issue trackers (jira/linear/github), CRMs (hubspot), chat (slack/discord/gmail/feishu), object stores (s3/gdrive). Use whenever the user asks to find, locate, look up, look across, or read something out of an already-configured MFS index. Trigger phrases include "search the codebase for", "find anywhere about", "where is X mentioned", "look across our [slack/jira/postgres/etc]", "any past tickets/RFCs/commits about", "what does our wiki say about", "cat / head / tail / ls / tree this MFS path". Do NOT use for: registering a NEW data source (use `mfs-ingest`), changing connector config, kicking off re-ingest, or any write/delete operation — `mfs` is read-only.
    4 installs
  14. ▌
    Mfs Ingest · zilliztech bundle
    Register, update, or re-sync data sources for MFS so they become searchable — postgres / mysql / mongo / snowflake / bigquery, github / jira / linear / notion / hubspot / zendesk, slack / discord / gmail / feishu, s3 / gdrive / web / file. Use whenever the user wants to ADD a new data source to MFS, change an existing connector's config, re-ingest / re-index a source, list registered connectors, or troubleshoot a sync that's not picking up data. Trigger phrases include "add X to MFS", "ingest my [postgres/slack/github/etc]", "register this repo / database / workspace", "make X searchable", "re-sync Y", "update the slack token", "what connectors do I have". Do NOT use for: searching / finding / reading content (use `mfs-find`); raw mutation of the source itself (MFS only reads).
    3 installs
  15. ▌
    Open Tag Admin · zilliztech bundle
    Admin/control console for an Open Tag Slack tag-in workflow backed by MFS. Use to set up a new Open Tag bot from scratch, check what is currently running (backend, permitted MFS scopes, Slack channel), change settings, add or remove data sources, switch the CLI agent backend (claude -p / codex exec), invite or move the bot in Slack, run preflight checks, and troubleshoot thread context, retrieval, or task execution.
    5 installs
  16. ▌
    Deep Research · zilliztech
    Answer a broad, open-ended, or multi-part question by iteratively searching MFS-indexed sources, following up on gaps, and synthesizing a cited report — the same "reason and search over private data" job zilliztech/deep-searcher does, but as a skill on top of `mfs-find` instead of a standalone framework. Use when the user asks for a report, a comprehensive/synthesized answer, a "what do we know about X across everything we have", or a question that can't be answered from a single search hit. Trigger phrases include "write a report on X", "deep-dive into X using our data", "research X across all our sources", "give me a comprehensive answer on X with citations", "synthesize what we know about X". Do NOT use for a single fact lookup or a targeted question with an obvious one-hit answer — use `mfs-find` directly for that; this skill is for genuinely broad, multi-angle asks. Requires `mfs-find` for the underlying search/read mechanics.
    7 installs
  17. ▌
    Testing · zilliztech
    Use when running unit tests, debugging test failures, or adding new test cases using Catch2 framework
    5 installs
  18. ▌
    Building · zilliztech
    Use when building knowhere from source, configuring build options (CPU/GPU/DISKANN/ASAN), or troubleshooting compilation errors
    7 installs
  19. ▌
    Architecture · zilliztech bundle
    Use when exploring codebase structure, understanding index implementations (HNSW, IVF, DISKANN, Sparse, MinHash), working with third-party libraries (faiss, hnswlib, DiskANN, Cardinal), or locating specific functionality
    7 installs
  20. ▌
    Code Quality · zilliztech
    Use when checking code style, running pre-commit hooks, or before committing changes to ensure compliance with Google style guide
    5 installs
  21. ▌
    Git Workflow · zilliztech
    Use when committing and pushing code changes, ensures DCO compliance and pre-commit validation
    6 installs
  22. ▌
    Ray · zilliztech
    Use when user needs to process data at scale. Triggers on: batch processing, data ingestion, pipeline, parallel processing, GPU acceleration, video processing, PDF processing, large-scale.
    7 installs
  23. ▌
    Pilot · zilliztech bundle
    Use when user wants to build AI applications, data pipelines, or any development project. Triggers on: AI application, build, project, data, pipeline, API, service, backend, LLM, GPT, Claude, model. Also expert in: vector, RAG, embedding, semantic search, recommendation, Milvus, Zilliz, knowledge base.
    5 installs
  24. ▌
    Rerank · zilliztech
    Use when user needs to improve search relevance with reranking. Triggers on: rerank, relevance, cross-encoder, search quality, top-k reranking, second-stage ranking.
    6 installs
  25. ▌
    Chunking · zilliztech
    Use when user needs to split documents into chunks for RAG or search. Triggers on: chunking, split, chunk size, text splitter, token limit, overlap.
    5 installs
  26. ▌
    Indexing · zilliztech
    Use when user needs to create collections, indexes in Milvus. Triggers on: indexing, collection, create index, HNSW, IVF, schema, Milvus collection, vector storage.
    4 installs
  27. ▌
    Embedding · zilliztech bundle
    Use when user needs to convert text/images to vectors. Triggers on: embedding, vectorize, encode, text-to-vector, model selection, sentence-transformers, OpenAI embeddings, BGE, CLIP.
    8 installs
  28. ▌
    RAG · zilliztech bundle
    Use when user wants to build RAG, Q&A system, or knowledge base with documents. Triggers on: RAG, retrieval augmented generation, Q&A system, knowledge base, document Q&A, chat with docs, ChatGPT for docs, LLM + retrieval, semantic search over documents, ground LLM with facts, reduce hallucination, enterprise search.
    6 installs
  29. ▌
    Local Setup · zilliztech
    Use when user needs to set up Milvus locally. Triggers on: local setup, install milvus, docker, docker-compose, dev environment, milvus standalone, milvus lite.
    6 installs
  30. ▌
    Agentic RAG · zilliztech bundle
    Use when user needs an autonomous RAG agent that decides when and what to retrieve dynamically. Triggers on: agentic RAG, agent, autonomous retrieval, tool use, function calling, research agent, conversational RAG, dynamic retrieval, self-directed search, RAG with tools, intelligent assistant, adaptive retrieval.
    5 installs
  31. ▌
    Item To Item · zilliztech bundle
    Use when user needs to find similar items. Triggers on: similar items, related content, related products, more like this, similar products, related articles, content-based recommendation, you may also like.
    6 installs
  32. ▌
    User To Item · zilliztech bundle
    Use when user needs personalized recommendations based on user profile. Triggers on: personalized, user recommendation, personalized recommendations, for you, feed, user preference, homepage recommendations.
    7 installs
  33. ▌
    Clustering · zilliztech bundle
    Use when user needs to group similar items together. Triggers on: clustering, group similar, topic modeling, user segmentation, categorization, automatic classification, unsupervised grouping.
    6 installs
  34. ▌
    Chat Memory · zilliztech bundle
    Use when user needs long-term memory for chatbots. Triggers on: chat memory, conversation history, long-term memory, chatbot memory, memory retrieval, persistent memory, remember conversations.
    5 installs
  35. ▌
    Multi Hop RAG · zilliztech bundle
    Use when user needs multi-step reasoning with iterative retrieval for complex questions. Triggers on: multi-hop, multi-step RAG, complex questions, chain of retrieval, iterative retrieval, complex reasoning, cross-document reasoning, question decomposition, research questions, fact synthesis, connecting information across documents.
    7 installs
  36. ▌
    RAG With Rerank · zilliztech bundle
    Use when user needs high-precision RAG with reranking for domains where accuracy is critical. Triggers on: rag rerank, precise RAG, cross-encoder, reranking RAG, legal QA, medical QA, high-precision QA, two-stage retrieval, semantic reranking, improve RAG accuracy, relevance scoring, document ranking.
    6 installs
  37. ▌
    Hybrid Search · zilliztech bundle
    Use when user needs both keyword and semantic search combined. Triggers on: hybrid search, keyword + semantic, BM25, full-text search, combined search, lexical search, exact match with meaning.
    5 installs
  38. ▌
    Filtered Search · zilliztech bundle
    Use when user needs vector search with scalar field filtering. Triggers on: filtered search, filter by category, metadata filter, faceted search, conditional search, attribute filtering, search with constraints.
    1 install
  39. ▌
    Semantic Search · zilliztech bundle
    Use when user wants to build semantic/text search. Triggers on: semantic search, text search, full-text search, natural language search, find similar text, vector search, meaning-based search, conceptual search.
    5 installs
  40. ▌
    Image Search · zilliztech bundle
    Use when user wants to build image search or similar image finding. Triggers on: image search, similar image, visual search, image retrieval, CLIP, reverse image search, image matching, find similar photos.
    6 installs
  41. ▌
    Video Search · zilliztech bundle
    Use when user needs to search video content by text or image. Triggers on: video search, video retrieval, video clips, meeting recordings, tutorial videos, surveillance playback, find moment in video.
    5 installs
  42. ▌
    Duplicate Detection · zilliztech bundle
    Use when user needs to find duplicate or similar content. Triggers on: duplicate, deduplication, plagiarism detection, similar content, near-duplicate, similarity detection, content dedup, find copies.
    5 installs
  43. ▌
    Multimodal RAG · zilliztech bundle
    Use when user needs RAG on documents with images and text. Triggers on: multimodal RAG, image-text mixed, document with images, PDF with charts, visual RAG, visual Q&A, documents with figures.
    7 installs
  44. ▌
    Multi Vector Search · zilliztech bundle
    Use when user needs to search across multiple vector fields. Triggers on: multi-vector, multiple embeddings, multi-field search, title + content, combined vectors, different aspects of same item.
    3 installs
  45. ▌
    Contextual Retrieval · zilliztech bundle
    Use when user needs parent-child document retrieval with context expansion. Triggers on: contextual retrieval, parent document, hierarchical chunking, context window, small-to-big, child chunks with parent context.
    5 installs
  46. ▌
    Text To Image Search · zilliztech bundle
    Use when user needs to search images using natural language descriptions. Triggers on: text to image, describe and find, natural language image search, image caption search, find image by description, describe to find.
    4 installs
  47. ▌
    External Collection · zilliztech
    Use when the user wants to trigger, describe, or list refresh jobs for an external collection (a collection backed by an external data source such as Vector Lake). Note this is the data-plane refresh workflow, not collection CRUD -- for create/drop/load see the collection skill.
    6 installs
  48. ▌
    Acl · zilliztech
    Use when the user wants to manage Zilliz Cloud access control -- custom org or project roles and their policies, granting or revoking a role for an organization member, or binding roles to a SCIM user group. This is cloud-level RBAC over organizations, projects, and clusters -- for database users and privileges inside Milvus see the user-role skill.
    7 installs
  49. ▌
    Job · zilliztech
    Use when the user wants to check the status of an async Cloud Job (backup, restore, migration, import, or clone). Also use when the user wants to wait for a long-running operation to complete.
    5 installs
  50. ▌
    Index · zilliztech
    Use when the user wants to create, list, describe, or drop indexes on Milvus collections.
    3 installs
  51. ▌
    Setup · zilliztech
    Use when the user needs to install zilliz-cli, log in to Zilliz Cloud, configure credentials, or set the active cluster context. Also use when any other skill reports a missing prerequisite.
    9 installs
  52. ▌
    Backup · zilliztech
    Use when the user wants to create, list, describe, delete, export, or restore backups, or manage backup policies on Zilliz Cloud.
    3 installs
  53. ▌
    Import · zilliztech
    Use when the user wants to import bulk data into a Milvus collection via Zilliz Cloud import jobs, or manage import stages (pre-uploaded file holders that import jobs reference).
    5 installs
  54. ▌
    Status · zilliztech
    Use when the user wants a comprehensive overview of their current Zilliz Cloud environment — context, cluster details, databases, and collections with stats.
    7 installs
  55. ▌
    Vector · zilliztech
    Use when the user wants to search, query, insert, upsert, get, or delete vectors in a Milvus collection.
    7 installs
  56. ▌
    Billing · zilliztech
    Use when the user wants to check usage, view invoices, or manage payment methods on Zilliz Cloud.
    7 installs
  57. ▌
    Cluster · zilliztech
    Use when the user wants to create, list, describe, delete, suspend, resume, or modify Zilliz Cloud clusters.
    13 installs
  58. ▌
    Database · zilliztech
    Use when the user wants to create, list, describe, or drop databases in Milvus.
    11 installs
  59. ▌
    Diagnose · zilliztech
    Use when the user reports that a Zilliz Cloud cluster or Milvus collection is unhealthy, slow, stuck, returning errors, hitting quotas, or otherwise misbehaving — or when they ask "what's wrong with...", "why is ... slow", "diagnose ...", "troubleshoot ...".
    8 installs
  60. ▌
    Partition · zilliztech
    Use when the user wants to create, list, load, release, or drop partitions in a Milvus collection.
    6 installs
  61. ▌
    User Role · zilliztech
    Use when the user wants to manage database users, roles, passwords, or access privileges in Milvus.
    5 installs
  62. ▌
    Ask Zilliz · zilliztech bundle
    Zilliz Cloud onboarding and usage assistant. Helps users understand Zilliz Cloud, choose the right plan, estimate costs, write code, debug issues, and adopt new features like Functions, Volumes, and Global Clusters. Use this skill whenever the user asks about Zilliz Cloud — including plan selection, pricing, cost estimation, capacity planning, cluster configuration, SDK usage, schema design, search patterns, migration, troubleshooting, MCP server setup, Terraform, auto-scaling, metrics/alerts, backup/restore, or any "how do I do X with Zilliz Cloud" question. Also trigger when the user mentions keywords like: "Zilliz", "zilliz cloud", "vector database", "which plan", "serverless vs dedicated", "CU", "vCU", "Milvus cloud", "pymilvus", "collection", "embedding function", "hybrid search", "rerank", "BM25", "global cluster", "BYOC", "tiered storage", "volume", "data import", "MCP server", "partition key", or error messages from Zilliz Cloud.
    10 installs
  63. ▌
    Collection · zilliztech
    Use when the user wants to create, list, describe, drop, rename, load, release, or manage collections and collection aliases in Milvus.
    4 installs
  64. ▌
    Monitoring · zilliztech
    Use when the user wants to check cluster status, collection statistics, load states, or get an overview of their Zilliz Cloud resources.
    12 installs
  65. ▌
    Quickstart · zilliztech
    Use when the user wants to set up, install, authenticate, or configure the Zilliz Cloud CLI and cluster context for the first time (one-shot onboarding).
    7 installs
  66. ▌
    Privatelink · zilliztech
    Use when the user wants to list available PrivateLink endpoint services, list/create/delete PrivateLink endpoints for a project, or manage the endpoint whitelist on Zilliz Cloud.
    10 installs
  67. ▌
    Project Region · zilliztech
    Use when the user wants to manage Zilliz Cloud projects or storage volumes. For cloud regions and providers, see the cluster skill.
    7 installs
  68. ▌
    On Demand Cluster · zilliztech
    Use when the user wants to create, list, describe, or delete an on-demand (Vector Lake / VectorLake) cluster. On-demand clusters auto-suspend after an idle TTL and are intended for ad-hoc query workloads against a Vector Lake.
    7 installs
  69. ▌
    Memory Config · zilliztech
    Diagnose and configure MemSearch memory behavior. Use when the user asks about MemSearch configuration, plugin summarization, PROJECT.md/USER.md maintenance, memory directories, index health, provider routing, prompt files, or migration/compatibility questions.
    11 installs
  70. ▌
    Memory Recall · zilliztech
    Search and recall relevant memories from past sessions via memsearch. Use when the user's question could benefit from historical context, past decisions, debugging notes, previous conversations, or project knowledge -- especially questions like 'what did I decide about X', 'why did we do Y', or 'have I seen this before'. Also use when you see `[memsearch] Recall available if needed` capability hints injected via SessionStart or UserPromptSubmit. Typical flow: search for 3-5 chunks, expand the most relevant, optionally deep-drill into original transcripts via the anchor format. Skip when the question is purely about current code state (use Read/Grep), ephemeral (today's task only), or the user has explicitly asked to ignore memory.
    13 installs