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

75%

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 ./backend/cli/skills/llm-tools/chroma/SKILL.md

Quality

Content

65%

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

Highly actionable with comprehensive executable code, but the body is a long monolith that duplicates integration content already in the reference file and carries marketing/time-sensitive fluff that hurts token efficiency. Workflow clarity is capped by absent validation checkpoints on destructive and batch operations.

Suggestions

Replace the inline LangChain/LlamaIndex sections with a one-line pointer to references/integration.md (e.g., "**Integrations**: See [integration.md](references/integration.md)") to remove duplication and properly use the bundle file.

Drop marketing metrics (star/fork counts, ⭐) and move the version number out of the body or into a clearly labeled section to satisfy the conciseness guideline for time-sensitive info.

Add validation/verification steps for destructive and batch operations — e.g., confirm IDs exist before delete, verify count after a bulk add — so destructive workflows include a feedback loop.

Dimension	Reasoning	Score
Conciseness	Mostly efficient code examples, but padded with marketing fluff ("24,300+ GitHub stars", "1,900+ forks", the ⭐ in Resources) and time-sensitive version numbers (v1.3.3) that the guideline says should penalize conciseness unless isolated in a deprecated section; the LangChain/LlamaIndex code is also duplicated verbatim in the reference file.	2 / 3
Actionability	Provides concrete, copy-paste-ready executable code across all core operations (add, query, get, update, delete, filtering) plus specific install commands, matching the level-3 anchor; minor placeholder elements ("return embeddings", "[0.1, 0.2, ...]") keep it just short of flawless but the guidance is fully actionable.	3 / 3
Workflow Clarity	Operations are numbered (1-6) but there is no sequenced multi-step workflow with validation checkpoints, and destructive/batch operations (delete, bulk add) lack validation steps — the guideline caps workflow clarity at 2 when validation is missing for such operations.	2 / 3
Progressive Disclosure	The body has clear section headers but is a ~400-line monolith; the provided references/integration.md is never linked from the body, and its LangChain/LlamaIndex content is duplicated inline rather than split out, so content that should be separate is inline and the reference is poorly signaled.	2 / 3
	Total	9 / 12 Passed

Description

85%

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

A strong description that names concrete capabilities and provides an explicit use-when trigger, distinguishing it from managed alternatives. Trigger-term coverage is solid but could enumerate more natural variations of the core concepts.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Store embeddings and metadata, perform vector and full-text search, filter by metadata" — matching the level-3 anchor that expects several specific concrete actions rather than vague language.	3 / 3
Completeness	Explicitly answers both what ("Store embeddings and metadata, perform vector and full-text search, filter by metadata") and when ("Use for semantic search, RAG applications, or document retrieval"), satisfying the level-3 anchor requiring explicit triggers.	3 / 3
Trigger Term Quality	The trigger clause "Use for semantic search, RAG applications, or document retrieval" supplies natural user terms, but coverage is thinner than the level-3 example (which lists many variations); common variants like "vector database" and "embeddings" appear only in tags, not the description text.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (open-source embedding database) and the closing "Best for local development and open-source projects" distinguishes it from managed offerings, giving it distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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: synthetic-sciences/openscience
Path: backend/cli/skills/llm-tools/chroma/SKILL.md
Commit: 52845c3

Reviewed: about 14 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.