llamaindex

Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM applications.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/agents/llamaindex/SKILL.md

Quality

Content

68%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 highly actionable, code-rich reference with solid progressive disclosure via real reference files. Its main weaknesses are conciseness padding (metrics, comparison tables) and the absence of explicit validation feedback loops in the batch ingestion/indexing workflows.

Suggestions

Move the vector-store integrations and data-ingestion pattern sections into reference files and summarize them inline, trimming the body toward a lean overview and improving both conciseness and progressive disclosure.

Remove the GitHub-star metrics block and the LlamaIndex-vs-LangChain comparison table, or relocate them to a reference file; they are time-sensitive padding that penalize conciseness.

Add an explicit end-to-end RAG workflow with a validation checkpoint (e.g., verify the index persisted and re-load it, or run RelevancyEvaluator before returning) to lift workflow clarity above the batch-operation cap of 3.

Dimension	Reasoning	Score
Conciseness	The ~570-line body is code-dense and mostly useful, but includes unnecessary padding Claude already knows — GitHub-star metrics ('45,100+ GitHub stars'), a full LlamaIndex-vs-LangChain comparison table, 'Best for…' prose, and verbose inline comments — matching the 'mostly efficient but could be tightened' anchor rather than the lean 4.	3 / 5
Actionability	Abundant copy-paste-ready, executable code covering the common cases — ingestion, indexing, querying, agents, vector stores, customization, evaluation — matching 'fully executable; copy-paste ready code covering the common cases', with only trivial assumptions about pre-existing variables.	5 / 5
Workflow Clarity	Sections are organized as a conceptual progression, but there is no explicit sequenced multi-step workflow with validation checkpoints; per the rubric's destructive/batch-operation cap, the ingestion/indexing pipeline (a batch operation) lacks any validate→fix→retry feedback loop, holding workflow clarity at 3 even though steps are individually clear.	3 / 5
Progressive Disclosure	Good structure with well-signaled, verified one-level-deep references (references/query_engines.md, agents.md, data_connectors.md are real files linked from a References section); held at 4 because substantial content that could live in separate files (vector-store integrations, ingestion patterns) is inlined rather than split out.	4 / 5
	Total	15 / 20 Passed

Description

75%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, specific description that covers what the framework does and when to use it, with good natural trigger terms. It is held below top marks by slightly generic 'when' phrasing and the absence of synonym/extension trigger terms.

Suggestions

Add an explicit 'Use when the user mentions…' clause naming concrete triggers like 'RAG', 'document Q&A', or 'vector search' to push completeness toward 5.

Include common synonyms or file/format triggers (e.g., 'knowledge bases', 'embeddings', '.pdf/.docx ingestion') to broaden trigger-term coverage.

Tighten 'Best for data-centric LLM applications' into a sharper differentiator against LangChain to reduce overlap risk.

Dimension	Reasoning	Score
Specificity	Names the RAG/data domain plus several concrete actions — 'document ingestion (300+ connectors)', 'indexing, and querying', 'vector indices, query engines, agents, and multi-modal support' — with only minor gaps in coverage, matching the 'lists several specific actions' anchor rather than the comprehensive 5.	4 / 5
Completeness	Explicitly states both what it does ('Data framework for building LLM applications with RAG…') and when to use it ('Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines'), but the 'when' could be more specific (no 'Use when the user mentions…' phrasing), keeping it at 4 rather than 5.	4 / 5
Trigger Term Quality	Includes natural user phrases like 'document Q&A', 'chatbots', 'knowledge retrieval', and 'building RAG pipelines'; good coverage but missing common synonyms and concrete file/extension triggers, so it sits above the 3 anchor but below the comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	The RAG/data-centric framing and 'Best for data-centric LLM applications' carve a distinct niche from general agent frameworks, with only minor overlap risk against LangChain-like skills; not a fully unambiguous 5 but clearly above the 3 anchor.	4 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (570 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: OpenLAIR/dr-claw
Path: skills/agents/llamaindex/SKILL.md
Commit: 4b35756

Reviewed: 3 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.