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

72%Weight 40%Scale 1-5

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

The body is highly actionable with comprehensive executable examples, but it wastes tokens by duplicating integration content that already lives in a reference file, omits validation for destructive operations, and underuses its single reference.

Suggestions

Remove the inline LangChain and LlamaIndex sections and replace them with a one-line pointer to references/integration.md to eliminate duplication and fix progressive disclosure.

Add explicit validation/verification steps (e.g., confirm collection exists before delete, verify deletion count) to the destructive delete operations so workflow clarity can exceed the cap of 3.

Drop the time-sensitive 'Metrics' block (GitHub stars, forks, v1.3.3 version) or move it to a reference, since version numbers and star counts decay and add tokens without aiding execution.

Dimension	Reasoning	Score
Conciseness	Mostly lean and code-forward, but the LangChain/LlamaIndex integration is duplicated inline and in references/integration.md, and the time-sensitive 'Metrics' block (stars, forks, v1.3.3) adds padding that could be trimmed.	4 / 5
Actionability	Extensive copy-paste-ready executable Python covering add/query/get/update/delete, filters, embedding functions, persistence, and server mode, matching the score-5 anchor for fully executable guidance.	5 / 5
Workflow Clarity	Individual operations are sequenced, but destructive operations (delete collection/documents) and batch adds have no validation/verification steps, which per the rubric caps workflow_clarity at 3.	3 / 5
Progressive Disclosure	Sections are well-organized, but the one reference file (integration.md) is duplicated inline rather than pointed to, and there is no signaled navigation to it, matching the score-3 anchor.	3 / 5
	Total	15 / 20 Passed

Description

92%Weight 40%Scale 1-5

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: it concisely states concrete capabilities and gives explicit, natural-language use triggers with a clear niche. The only gap is slightly incomplete trigger-term coverage (missing synonyms/extensions).

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Store embeddings and metadata, perform vector and full-text search, filter by metadata' — with comprehensive coverage of core operations, matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers both 'what' (store/search/filter embeddings) and 'when' ('Use for semantic search, RAG applications, or document retrieval') with concrete trigger phrases, matching the score-5 anchor.	5 / 5
Trigger Term Quality	Good natural-term coverage ('semantic search, RAG applications, or document retrieval', 'embeddings') but missing common synonyms and file extensions, so it falls short of the comprehensive score-5 anchor.	4 / 5
Distinctiveness Conflict Risk	Clear niche as an open-source, local/self-hosted embedding database with distinct RAG/semantic-search triggers and minimal overlap risk with managed alternatives, matching the score-5 anchor.	5 / 5
	Total	19 / 20 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: OpenLAIR/dr-claw
Path: skills/rag/chroma/SKILL.md
Commit: 4b35756

Reviewed: 1 day 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.