rag-architect

tessl i github:jeffallan/claude-skills --skill rag-architect

Use when building RAG systems, vector databases, or knowledge-grounded AI applications requiring semantic search, document retrieval, or context augmentation.

56%

Overall

Validation — 81%

Implementation — 42%

Activation — 55%

SKILL.md

Review

Evals

Validation

81%

Warnings & errors only

Criteria	Description	Result
metadata_version	'metadata' field is not a dictionary	Warning
license_field	'license' field is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Implementation

42%

This skill excels at progressive disclosure with a well-organized reference structure, but critically lacks actionability—there are no executable code examples for any RAG operations. The content reads more like a checklist/overview than a practical implementation guide, which limits its usefulness for actually building RAG systems.

Suggestions

Add executable code examples for key operations: embedding generation, vector upsert, similarity search, and a basic retrieval pipeline

Include a concrete chunking example showing actual code with different strategies and their outputs

Add validation checkpoints to the core workflow (e.g., 'Verify embedding quality with sample queries before full ingestion')

Remove or condense the 'Knowledge Reference' section—Claude already knows these technologies exist

Dimension	Reasoning	Score
Conciseness	The content is reasonably efficient but includes some unnecessary sections like 'Role Definition' that restates obvious context, and 'Knowledge Reference' which lists technologies Claude already knows. The constraints section is valuable but could be more compact.	2 / 3
Actionability	The skill provides high-level guidance and checklists but lacks any concrete, executable code examples. No actual implementation snippets for chunking, embedding, or retrieval are provided—it describes what to do rather than showing how.	1 / 3
Workflow Clarity	The 5-step core workflow provides a clear sequence, but lacks validation checkpoints or feedback loops. For a complex multi-step process like RAG implementation, there's no guidance on how to verify each step succeeded before proceeding.	2 / 3
Progressive Disclosure	Excellent structure with a clear reference table pointing to specific topic files (vector-databases.md, chunking-strategies.md, etc.) with explicit 'Load When' guidance. References are one level deep and well-organized.	3 / 3
	Total	8 / 12 Passed

Activation

55%

The description has strong trigger terms and a clear niche but critically fails to explain what the skill actually does. It only provides 'when to use' guidance without any 'what it does' content, making it incomplete despite having good domain-specific keywords.

Suggestions

Add a 'what it does' clause before the 'Use when' section, listing specific capabilities like 'Chunks documents, generates embeddings, configures vector stores, and implements retrieval pipelines.'

Include concrete actions the skill performs such as 'index documents', 'query embeddings', 'rank results', or 'augment prompts with retrieved context'.

Dimension	Reasoning	Score
Specificity	Names the domain (RAG systems, vector databases) and mentions some actions (semantic search, document retrieval, context augmentation), but doesn't list concrete specific actions like 'chunk documents', 'generate embeddings', or 'query vector stores'.	2 / 3
Completeness	Only answers 'when' (Use when...) but completely lacks the 'what does this do' component. There's no description of what capabilities or actions the skill provides, only when to use it.	1 / 3
Trigger Term Quality	Good coverage of natural terms users would say: 'RAG', 'vector databases', 'semantic search', 'document retrieval', 'knowledge-grounded'. These are terms practitioners actually use when working in this space.	3 / 3
Distinctiveness Conflict Risk	Clear niche focused on RAG/vector database domain with distinct triggers like 'RAG systems', 'vector databases', 'semantic search' that are unlikely to conflict with other skills.	3 / 3
	Total	9 / 12 Passed

Reviewed

16 days ago

Table of Contents

Validation Implementation Activation

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.