chromadb
Assists with storing, searching, and managing vector embeddings using ChromaDB. Use when building RAG pipelines, semantic search engines, or recommendation systems. Trigger words: chromadb, chroma, vector database, embeddings, semantic search, similarity search, vector store, rag.
What this skill does
# ChromaDB
## Overview
ChromaDB is an open-source vector database for storing, searching, and managing embeddings. It provides a simple API for document ingestion, semantic similarity search, and metadata filtering, supporting both Python and JavaScript/TypeScript clients with embedded, server, and cloud deployment options.
## Instructions
- When initializing, use `get_or_create_collection` for idempotent collection setup, choose `PersistentClient` for development and `HttpClient` for production server connections.
- When adding documents, batch `add()` calls in chunks of 5,000 documents, always store source metadata (filename, URL, page number) for RAG citations, and use `upsert()` for incremental updates to avoid duplicates.
- When querying, use `collection.query(query_texts=..., n_results=...)` for text-based search, combine metadata `where` filters to narrow results before semantic search, and set `n_results` based on the LLM's context window (5-10 for most RAG pipelines).
- When choosing embeddings, use the default Sentence Transformers for local development without API keys, OpenAI or Cohere embedding functions for production, or pass pre-computed vectors directly.
- When filtering metadata, use operators like `$eq`, `$gt`, `$in` with `$and`/`$or` logical operators, and combine with `where_document` for content-based filtering alongside semantic similarity.
- When deploying, use the embedded `PersistentClient` for single-node applications, Docker for server mode, or Chroma Cloud for managed hosting with multi-tenancy support.
- When tuning performance, configure HNSW parameters (`hnsw:M`, `hnsw:construction_ef`, `hnsw:search_ef`) for the quality-speed tradeoff and choose `cosine` distance for normalized embeddings (OpenAI, Cohere).
## Examples
### Example 1: Build a document Q&A pipeline
**User request:** "Set up a RAG pipeline with ChromaDB for answering questions about our docs"
**Actions:**
1. Load documents and split into chunks with metadata (source, page)
2. Create a collection with OpenAI embedding function
3. Batch-add document chunks with `upsert()` for idempotent ingestion
4. Query with `collection.query()` and pass retrieved chunks as context to the LLM
**Output:** A semantic search pipeline that retrieves relevant document chunks for LLM-powered Q&A.
### Example 2: Add filtered semantic search to an application
**User request:** "Implement product search that combines text similarity with category filters"
**Actions:**
1. Create a collection with product descriptions and category metadata
2. Implement search combining `query_texts` with `where={"category": "electronics"}`
3. Return results with distances for relevance ranking
4. Add price range filtering with `$gte` and `$lte` operators
**Output:** A filtered semantic search that narrows by metadata before ranking by text similarity.
## Guidelines
- Use `get_or_create_collection` for idempotent collection initialization; it is safe for restarts.
- Batch `add()` calls in chunks of 5,000 documents to manage memory usage.
- Always store source metadata (filename, URL, page number); it is essential for RAG citations.
- Use `upsert()` for incremental updates to avoid duplicate documents when re-ingesting.
- Set `n_results` based on the LLM's context window: 5-10 results for most RAG pipelines.
- Use metadata filtering to narrow results before semantic search to reduce noise.
- Choose `cosine` distance for normalized embeddings (OpenAI, Cohere) and `l2` for unnormalized.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.