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

79%

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 ./backend/cli/skills/llm-tools/llamaindex/SKILL.md

Quality

Content

75%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, well-structured reference with comprehensive executable examples and clear bundle-file references. Its main weakness is verbosity from promotional metrics, version numbers, and comparison tables that do not advance Claude's task execution.

Suggestions

Remove or relocate the GitHub-stars/contributors metrics, version number, and performance benchmarks table to a separate references file or drop them, since time-sensitive promotional data adds tokens without actionable value.

Trim the 'LlamaIndex vs LangChain' comparison table to a one-line pointer or move it into a reference file; the 'When to use' section already covers alternative selection.

Move the detailed agent, query-engine, and data-connector inline examples into the corresponding reference files so SKILL.md acts as a lean overview pointing one level deep, improving the progressive-disclosure split.

Dimension	Reasoning	Score
Conciseness	Mostly efficient code-centric content, but padded with time-sensitive promotional sections — '45,100+ GitHub stars', '23,000+ repositories', '1,715+ contributors', 'v0.14.7', a performance benchmarks table, and a LlamaIndex-vs-LangChain comparison — that add tokens without actionable value; above a 2 because the bulk is lean executable code.	3 / 5
Actionability	Copy-paste-ready executable code spans installation, a 5-line RAG example, connectors, indices, query engines, retrievers, agents, vector-store integrations, and evaluation — covering the common cases concretely, with only trivial placeholders for credentials.	5 / 5
Workflow Clarity	Clear load → index → persist → query sequences appear in the 5-line example and 'Common patterns', and an Evaluation section supplies verification tooling; not a 5 because validation checkpoints are not woven explicitly into the pipelines as feedback loops.	4 / 5
Progressive Disclosure	A clearly signaled one-level-deep References section links to real bundle files (query_engines.md, agents.md, data_connectors.md) and section headers aid navigation; not a 5 because substantial detail on those same topics is inlined in the body rather than split into the referenced files.	4 / 5
	Total	16 / 20 Passed

Description

83%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 well-crafted description that clearly states both the framework's capabilities and explicit use-case triggers in third person. It is comprehensive and distinct, with only minor gaps in trigger-term synonyms and action verb specificity.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities — 'document ingestion (300+ connectors), indexing, and querying' plus 'vector indices, query engines, agents, and multi-modal support' — giving broad coverage with only minor gaps; not a 5 because capabilities are named more than sharply verb-driven actions.	4 / 5
Completeness	Explicitly answers 'what' ('Data framework... Specializes in document ingestion, indexing, and querying... Features vector indices, query engines, agents') and 'when' with a concrete 'Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines' trigger clause.	5 / 5
Trigger Term Quality	Includes natural user phrases such as 'RAG', 'document Q&A', 'chatbots', 'knowledge retrieval', and 'building RAG pipelines'; good coverage but missing common synonyms or file-type triggers, so short of a 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear RAG/data-framework niche with distinct triggers ('Best for data-centric LLM applications'), but has minor overlap risk with closely related general LLM-tool skills like LangChain, keeping it just below a 5.	4 / 5
	Total	17 / 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 (571 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: synthetic-sciences/openscience
Path: backend/cli/skills/llm-tools/llamaindex/SKILL.md
Commit: 3a6c3a9

Reviewed: 1 day 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.