rag-implementation

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

2.12x

Quality

—

Does it follow best practices?

Impact

70%

2.12x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

65%

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

A highly actionable, code-rich RAG reference that scores well on executable guidance but is let down by its monolithic single-file structure and verbose, somewhat over-explaining prose. Consolidating peripheral configs/patterns into reference files and tightening explanatory passages would lift both conciseness and progressive disclosure.

Suggestions

Split vector-store configurations, advanced retrieval patterns, and evaluation tooling into separate reference files (e.g. references/vector-stores.md, references/advanced-patterns.md) and keep SKILL.md as a lean overview with one-level-deep links, lifting progressive_disclosure to 3.

Trim explanatory prose that restates concepts Claude already knows (per-tool 'Purpose' lines, the 'When to Use' bullet list, the descriptive sentences in Core Components) to move conciseness toward 3.

Add an explicit end-to-end production workflow with validation checkpoints — index → retrieve → evaluate → fix chunking/embeddings → re-run — using the existing evaluation metrics as a feedback loop, raising workflow_clarity to 3.

Dimension	Reasoning	Score
Conciseness	The ~565-line body is mostly efficient code but padded with redundant prose (the 'When to Use' bullets, per-tool 'Purpose' lines restating what reranking/metadata filtering are) that assumes less of Claude than it should; it avoids explaining truly basic concepts so it is above score 1, but the volume exceeds the lean score-3 bar.	2 / 3
Actionability	Extensive copy-paste-ready executable code with concrete imports and parameters across quick start, hybrid search, HyDE, chunking, vector stores, and evaluation, matching the 'fully executable, copy-paste ready' anchor.	3 / 3
Workflow Clarity	The Quick Start shows a clear retrieve→generate sequence, but the skill presents patterns rather than a single end-to-end production workflow, and validation checkpoints (e.g. wire the evaluation metrics into a validate→fix→retry loop) are implicit rather than explicit.	2 / 3
Progressive Disclosure	No bundle files exist and the entire skill is one monolithic 565-line SKILL.md with vector-store configs, advanced patterns, and evaluation all inline; headings give some structure, but content that should be split into references is not, matching the score-2 anchor.	2 / 3
	Total	9 / 12 Passed

Description

100%

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, well-constructed description that names concrete capabilities and provides an explicit, naturally-worded 'Use when' trigger clause covering multiple realistic user phrasings. It is concise, distinct, and uses appropriate third-person voice.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Build Retrieval-Augmented Generation (RAG) systems', 'with vector databases and semantic search') matching the 'multiple specific concrete actions' anchor rather than the domain-only score-2 anchor.	3 / 3
Completeness	Explicitly answers both 'what' ('Build RAG systems... with vector databases and semantic search') and 'when' via an explicit 'Use when...' clause, matching the score-3 anchor with explicit triggers.	3 / 3
Trigger Term Quality	Covers natural user phrasings — 'RAG', 'document Q&A systems', 'semantic search', 'knowledge-grounded AI', 'external knowledge bases' — giving good coverage of terms users would actually say, not just jargon.	3 / 3
Distinctiveness Conflict Risk	RAG/knowledge-grounded AI is a clear niche with distinct triggers unlikely to conflict with other skills; third person voice is used correctly throughout.	3 / 3
	Total	12 / 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
skill_md_line_count	SKILL.md is long (571 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: Dicklesworthstone/pi_agent_rust
Commit: e9f9b67

Reviewed: 4 days 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.