chroma

Embedding database for RAG and semantic search.

Quality

55%

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

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/mlops/chroma/SKILL.md

Quality

Content

57%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 a thorough, actionable API reference with strong executable examples, but it duplicates integration content that already lives in a reference file, lacks validation checkpoints for batch/database operations, and includes time-sensitive and generic material that adds tokens without proportional value.

Suggestions

Replace the inlined LangChain/LlamaIndex sections with a one-line pointer to references/integration.md to avoid duplication and surface the existing bundle.

Add an explicit validation step (e.g. checking collection counts or query results) after batch add/delete operations to provide a feedback loop for database operations.

Move time-sensitive version and latency figures into a clearly labeled section or remove the generic best-practices list to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly code-forward and efficient, but inlines a 10-item generic best-practices list and a time-sensitive performance table with version/latency figures that are not isolated in a deprecated section, which the rubric penalizes.	3 / 5
Actionability	Provides extensive concrete, executable code across collections, queries, filtering, persistence, and server mode that is largely copy-paste ready, with only minor gaps such as the placeholder custom embedding logic and undefined embeddings variable.	4 / 5
Workflow Clarity	Content is organized by operation rather than as a sequenced workflow, and because the skill involves batch add and database operations, the absence of explicit validation/feedback-loop checkpoints caps workflow clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	Sections are well structured, but the LangChain and LlamaIndex integration sections are fully inlined even though a references/integration.md bundle exists that is never linked from the body, leaving integration content inlined and the reference orphaned.	3 / 5
	Total	13 / 20 Passed

Description

53%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 concise and identifies a clear niche but stops at stating what Chroma is without naming concrete actions or any 'Use when' trigger guidance. Adding concrete verbs and an explicit use-case trigger would lift specificity and completeness.

Suggestions

Add concrete actions to the description, e.g. 'Store, query, and filter embeddings for RAG and semantic search.'

Append an explicit trigger clause such as 'Use when building RAG pipelines, semantic search, or needing a local vector database.'

Include common synonyms users say, like 'vector database' and 'embeddings', to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Embedding database') and two applications ('RAG', 'semantic search') but states no concrete actions/verbs like store, query, or filter, matching the anchor for naming domain plus 1-2 items without comprehensive coverage.	3 / 5
Completeness	Has a clear 'what' (an embedding database for RAG/semantic search) but no 'Use when...' trigger guidance, and the rubric explicitly caps completeness at 3 when that clause is missing.	3 / 5
Trigger Term Quality	Includes two natural terms users would say ('RAG', 'semantic search') but misses common synonyms and variations such as 'vector database', 'embeddings', or 'document retrieval', so keyword coverage is partial rather than comprehensive.	3 / 5
Distinctiveness Conflict Risk	The niche is clear (embedding database for RAG/semantic search) and unlikely to trigger the wrong skill, but the absence of explicit trigger phrases keeps it just below the fully-distinct anchor 5.	4 / 5
	Total	13 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/mlops/chroma/SKILL.md
Commit: 6680afb

Reviewed: about 2 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.