Name: rag-implementation
Rating: 51.2 (1 reviews)
Author: administrakt0r

rag-implementation

RAG (Retrieval-Augmented Generation) implementation workflow covering embedding selection, vector database setup, chunking strategies, and retrieval optimization.

Quality

56%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/rag-implementation/SKILL.md

The canonical home for this skill is rag-implementation in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

53%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.

The content presents a well-sequenced 8-phase RAG workflow with clear structure and concrete skill-invocation prompts, but it lacks inter-phase validation checkpoints and its per-phase action steps are generic rather than executable specifics.

Suggestions

Add validation checkpoints between phases (e.g., 'Confirm retrieval quality passes before proceeding to Phase 6: LLM Integration') to lift workflow clarity.

Tighten the generic per-phase 'Actions' lists into specific, actionable guidance — name concrete decisions, parameters, or criteria instead of verbs like 'Select model'.

De-duplicate the Overview against the frontmatter description and consider moving detailed phase content into one-level-deep reference files for better progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with no concept-explanation padding, but the Overview restates the frontmatter description and each of the 8 phases repeats the same template with generic 5-step action lists that could be tightened.	3 / 5
Actionability	Concrete guidance is present via named skill invocations and copy-paste prompts, but the per-phase 'Actions' lists are high-level verbs ('Select model', 'Configure indexes') without specific commands, parameters, or decision criteria.	3 / 5
Workflow Clarity	The 8 phases are clearly sequenced and a terminal Quality Gates checklist exists, but there are no inter-phase validation checkpoints or feedback loops (e.g., 'verify retrieval before LLM integration'), leaving validation implicit.	3 / 5
Progressive Disclosure	The body is well-structured with clear section headers and easy navigation, and no external references are strictly needed; it stops short of 5 only because the 197-line file inlines all 8 detailed phases rather than splitting any into one-level-deep reference files.	4 / 5
	Total	13 / 20 Passed

Description

58%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.

The description conveys a clear 'what' with several concrete RAG sub-tasks, but omits any explicit 'when to use' trigger guidance, which the rubric caps at completeness 3. Trigger-term coverage is decent but lacks common synonyms.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases, e.g. 'Use when building RAG applications, semantic search, or document Q&A systems.'

Broaden trigger terms with user-natural synonyms such as 'semantic search', 'knowledge base', and 'document Q&A'.

Reflect the full workflow scope (LLM integration, caching, evaluation) to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete sub-tasks — 'embedding selection, vector database setup, chunking strategies, and retrieval optimization' — giving good coverage of the RAG domain, though it omits phases present in the body (LLM integration, caching, evaluation), leaving minor gaps.	4 / 5
Completeness	Clearly states the 'what' (RAG implementation workflow covering four sub-tasks) but provides no explicit 'when' guidance; per the rubric, a missing 'Use when...' clause caps completeness at 3.	3 / 5
Trigger Term Quality	Includes relevant natural keywords ('RAG', 'Retrieval-Augmented Generation', 'vector database', 'embedding', 'retrieval') but misses common synonyms a user might say ('semantic search', 'knowledge base', 'document Q&A') and has no 'Use when...' trigger phrasing.	3 / 5
Distinctiveness Conflict Risk	'RAG implementation workflow' is a clear, fairly distinct niche, with only minor overlap risk against closely related skills it itself references (rag-engineer, embedding-strategies).	4 / 5
	Total	14 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/rag-implementation/SKILL.md
Commit: 57c135b

Reviewed: 2 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.