rag-assistant

Knowledge base assistant that retrieves and cites documents from a curated index. Use when answering questions that must be grounded in specific source material with citations.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./modules/skills/src/main/resources/META-INF/skills/rag-assistant/SKILL.md

Quality

Content

70%

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

A compact, well-organized instruction skill with a clear retrieval workflow and guardrails. Its main weaknesses are duplicated tool/purpose content and missing concrete details on citation format and search strategy.

Suggestions

Collapse the intro tool list and the 'Tools' section into a single authoritative list to remove redundancy.

Add a one-line citation format example (e.g., '[doc-title]' or '(source: <title>)') so the citation step is unambiguous.

Give brief guidance on forming effective search_knowledge_base queries (e.g., use topic nouns, try synonyms) to lift actionability.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean, but the 'Tools' and 'Skills' sections restate the tool list and purpose already given in the intro, adding redundancy that could be tightened.	2 / 3
Actionability	Concrete numbered steps and named tools give actionable direction, but key details are missing — no citation format example and no guidance on forming effective searches.	2 / 3
Workflow Clarity	A clear 1-5 sequence for answering is given, with an explicit fallback ('If the documents don't contain enough information, say so honestly') as a validation/edge-case checkpoint; as a simple read-only skill this meets the top anchor.	3 / 3
Progressive Disclosure	Under 50 lines with no need for external references, yet organized into well-labeled sections (How to answer, Skills, Tools, Guardrails), satisfying the simple-skill top anchor.	3 / 3
	Total	10 / 12 Passed

Description

75%

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 solid third-person description that answers both what and when with an explicit trigger. It is held back from the top band by a non-comprehensive action list and trigger terms that omit common phrasings.

Suggestions

Expand the capability list with the concrete actions the body already names (search, browse sources, compare topics) so specificity reaches the top anchor.

Add natural trigger variations users would actually say, such as 'RAG', 'cite your sources', or 'look it up in the knowledge base'.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete actions ('retrieves and cites documents from a curated index') but the action list is not comprehensive — no mention of searching, browsing, or comparing sources.	2 / 3
Completeness	Clearly states what it does (retrieves and cites documents from a curated index) and when to use it ('Use when answering questions that must be grounded in specific source material with citations').	3 / 3
Trigger Term Quality	'answering questions that must be grounded in specific source material with citations' is relevant but misses common variations a user would naturally say ('cite sources', 'RAG', 'look up in the knowledge base').	2 / 3
Distinctiveness Conflict Risk	The citation-grounded retrieval niche is distinct and unlikely to trigger for non-RAG skills; the explicit grounding-with-citations requirement sharpens the boundary.	3 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 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

	Total	14 / 16 Passed

Repository: Atmosphere/atmosphere
Path: modules/skills/src/main/resources/META-INF/skills/rag-assistant/SKILL.md
Commit: 86693b6

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.