CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

rag

Implements document chunking, embedding generation, vector storage, and retrieval pipelines for Retrieval-Augmented Generation systems. Use when building RAG applications, creating document Q&A systems, or integrating AI with knowledge bases.

70

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is giuseppe-trisciuoglio/developer-kit

SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

A well-structured, actionable multi-step RAG guide with validation and feedback loops. Trimming minor over-explanation and linking the bundled assets would raise it further.

Suggestions

Remove or tighten low-value glosses (e.g. '(default for most cases)', 'for optimal balance') to improve conciseness.

Reference the bundled assets from the body (e.g. point to assets/retriever-pipeline.java and assets/vector-store-config.yaml) so they are discoverable and progressive disclosure is complete.

Make code examples self-contained by declaring or noting the source of referenced variables (chatModel, embeddingModel, store) to reach fully copy-paste-ready actionability.

DimensionReasoningScore

Conciseness

Mostly efficient with tables and code instead of prose, but includes a few unnecessary glosses like '(default for most cases)' and 'for optimal balance' that slightly pad the text.

4 / 5

Actionability

Provides executable Java code and concrete retrieval/filter configurations covering common cases, though several examples reference undeclared variables (chatModel, embeddingModel, store) leaving minor gaps for copy-paste completeness.

4 / 5

Workflow Clarity

Clear Steps 1-6 sequence with explicit validation checkpoints (embedding dimension check) and a batch-ingestion retry feedback loop (validate -> retry -> escalate), satisfying the destructive/batch validation requirement.

5 / 5

Progressive Disclosure

SKILL.md is a well-organized overview with clearly signaled one-level-deep references to five real reference files, but the bundled assets (retriever-pipeline.java, vector-store-config.yaml) are never referenced from the body, leaving a navigation gap.

4 / 5

Total

17

/

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.

A strong, third-person description that clearly states capabilities and triggers. Minor room for additional synonym/extension coverage in the trigger terms.

DimensionReasoningScore

Specificity

Names the domain and four concrete actions ('document chunking, embedding generation, vector storage, and retrieval pipelines'), giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both 'what' (chunking, embedding, storage, retrieval) and 'when' via a clear 'Use when...' clause with multiple concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural user phrases like 'building RAG applications', 'document Q&A systems', 'integrating AI with knowledge bases' are present, but it lacks common synonyms/variants a user might say (e.g. 'semantic search', 'retrieval', file extensions) keeping it just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear RAG niche with distinct triggers ('Retrieval-Augmented Generation', 'document Q&A', 'AI with knowledge bases') that are unlikely to collide with unrelated skills.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository

giuseppe-trisciuoglio/developer-kit

Path

plugins/developer-kit-ai/skills/rag/SKILL.md

Revision

fe73fb3

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill