rag-architect
Use when building RAG systems, vector databases, or knowledge-grounded AI applications requiring semantic search, document retrieval, or context augmentation.
Install with Tessl CLI
npx tessl i github:jeffallan/claude-skills --skill rag-architect57
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
54%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description has strong trigger terms and clear distinctiveness for the RAG/vector database domain, but critically fails on completeness by only specifying when to use the skill without describing what it actually does. The description reads as a 'Use when' clause without the preceding capability statement.
Suggestions
Add a capability statement before the 'Use when' clause describing concrete actions (e.g., 'Chunks documents, generates embeddings, configures vector stores, and implements retrieval pipelines.')
Include specific concrete actions like 'index documents', 'query embeddings', 'configure similarity thresholds', or 'implement hybrid search' to improve specificity
Restructure to follow the pattern: '[What it does]. Use when [triggers].' rather than starting with 'Use when'
| 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 with distinct triggers around RAG/vector database domain. Terms like 'RAG systems', 'vector databases', 'semantic search' are specific enough to avoid conflicts with general document or AI skills. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides good structural organization and progressive disclosure with clear references to detailed topics, but critically lacks actionable, executable guidance. It reads more like a role description and checklist than a skill that teaches Claude how to perform specific tasks. The absence of any code examples, concrete commands, or specific implementation patterns significantly limits its utility.
Suggestions
Add executable code examples for key operations: embedding generation, vector database queries, chunking implementation, and hybrid search setup
Replace abstract constraints ('Implement hybrid search') with concrete code snippets or command examples showing exactly how to implement them
Add validation checkpoints to the workflow with specific commands or code to verify each step (e.g., 'Test retrieval with: `python evaluate.py --metrics precision@10`')
Remove or condense the 'Role Definition', 'When to Use', and 'Knowledge Reference' sections which add little value beyond what Claude already knows
| 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 'When to Use This Skill' section largely duplicates the description. | 2 / 3 |
Actionability | The skill provides no executable code, no concrete commands, and no specific examples. It describes what to do at a high level ('Implement hybrid search', 'Use reranking') but never shows how. The constraints are abstract guidelines rather than actionable instructions. | 1 / 3 |
Workflow Clarity | The 5-step core workflow provides a clear sequence, but lacks validation checkpoints, feedback loops, or concrete verification steps. For a complex domain like RAG systems involving data pipelines and deployments, missing validation guidance is a significant gap. | 2 / 3 |
Progressive Disclosure | The reference table provides clear one-level-deep navigation to detailed topics with explicit 'Load When' guidance. The structure appropriately separates overview content from detailed references in a well-organized manner. | 3 / 3 |
Total | 8 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Reviewed
Table of Contents
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.