chroma

Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with complete executable examples, but it is weakened by vanity-metric padding and time-sensitive version info, missing validation checkpoints on destructive/batch operations, and a monolithic structure that duplicates rather than links its existing reference file.

Suggestions

Move the LangChain/LlamaIndex integration sections into references/integration.md and link to it from the body, eliminating the duplication and turning the monolith into a lean overview with one-level-deep references.

Drop the marketing padding (GitHub stars/forks metrics, the 'AI-native database' tagline, the approximate latency table) and relocate version numbers to a versioned/deprecated section so the body stays evergreen and token-lean.

Add explicit verification/checkpoint steps to destructive and batch operations (e.g., confirm collection.delete targets, verify batch adds succeeded) to lift workflow clarity above 2.

Dimension	Reasoning	Score
Conciseness	The body is mostly code-forward and avoids explaining concepts Claude already knows, but carries non-instructional padding (the 'AI-native database' tagline, a vanity metrics block of GitHub stars/forks, an approximate latency table) and time-sensitive version numbers (v1.3.3) outside any deprecated section, keeping it from the lean anchor.	2 / 3
Actionability	Provides fully executable, copy-paste-ready Python for every core operation — client/collection creation, add, query with filters, get, update, delete, persistent storage, embedding functions including a custom EmbeddingFunction subclass, and server mode.	3 / 3
Workflow Clarity	Operations are organized into clear numbered sections, but the destructive and batch operations (collection.delete, batch collection.add) have no validation or verification checkpoints, which caps workflow clarity at 2 per the destructive/batch guideline.	2 / 3
Progressive Disclosure	The body is a ~395-line monolith with the full API reference inline, and a references/integration.md bundle exists yet is never linked or signaled from the body — instead the LangChain/LlamaIndex integration is duplicated inline, the 'content that should be separate is inline' pattern.	2 / 3
	Total	9 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong across all dimensions: it states concrete capabilities, provides natural trigger terms, explicitly covers both what and when, and occupies a distinct niche. No changes needed.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Store embeddings and metadata', 'perform vector and full-text search', 'filter by metadata' — matching the anchor for listing multiple specific concrete actions rather than just naming a domain.	3 / 3
Completeness	Explicitly answers both 'what' (store/search/filter) and 'when' via the explicit 'Use for semantic search, RAG applications, or document retrieval' trigger clause, satisfying the what-AND-when requirement.	3 / 3
Trigger Term Quality	Covers natural terms users would say — 'semantic search', 'RAG applications', 'document retrieval', 'embeddings', 'vector database' — giving good coverage of common phrasings.	3 / 3
Distinctiveness Conflict Risk	Has a clear niche as an open-source self-hosted embedding/vector database with distinct triggers (RAG, semantic search, document retrieval), unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Orchestra-Research/AI-Research-SKILLs
Path: 15-rag/chroma/SKILL.md
Commit: 773a529

Reviewed: about 13 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.