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

82%

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

Quality

Content

65%

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

Highly actionable with thorough executable examples, but the body is over-long and padded with marketing metrics, version pins, and redundant comparisons. Reference files exist and are well-linked, yet much detailed content remains inline rather than split out.

Suggestions

Remove the Metrics block (GitHub stars, contributors, version) and the Performance benchmarks table—marketing/time-sensitive content that does not help Claude execute the task.

Move the Vector store integrations, Multi-modal RAG, Evaluation, and Customization sections into reference files (mirroring the existing query_engines/agents/data_connectors pattern) to slim the SKILL.md overview.

Add an explicit validation/persistence check (e.g., verify the index loads from storage before querying) to the ingestion and document-Q&A workflows so batch operations have a feedback checkpoint.

Dimension	Reasoning	Score
Conciseness	The ~560-line body includes marketing noise ("45,100+ GitHub stars", "1,715+ contributors"), a time-sensitive version pin (v0.14.7), and redundant LangChain comparison/benchmark tables that could be trimmed.	2 / 3
Actionability	Extensive copy-paste-ready, executable code for installation, indexing, query engines, agents, and vector-store integrations—concrete and specific throughout.	3 / 3
Workflow Clarity	Sequences like load→index→persist→query are shown but lack validation checkpoints, and batch ingestion has no verify step, capping workflow clarity at 2 per the rubric.	2 / 3
Progressive Disclosure	Three reference files are clearly signaled one-level-deep, but the body keeps large inline sections (vector stores, multi-modal, evaluation, customization) that should be offloaded to reference files.	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, third-person description that states concrete capabilities, includes an explicit "Use for..." trigger, and carves out a clear RAG niche. Minor note: it does not name itself with a 'when the user mentions X' phrasing, but the trigger guidance is explicit and sufficient.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions—"document ingestion (300+ connectors), indexing, and querying" plus "vector indices, query engines, agents, and multi-modal support"—matching the multiple-specific-actions anchor.	3 / 3
Completeness	Clearly answers what ("Data framework... Specializes in... Features...") and when via an explicit "Use for..." trigger clause, satisfying both halves.	3 / 3
Trigger Term Quality	"Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines" gives good coverage of natural terms a user would say, not just jargon.	3 / 3
Distinctiveness Conflict Risk	The RAG/data-centric niche with triggers like "document ingestion" and "building RAG pipelines" is distinct and unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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: 52845c3

Reviewed: about 13 hours 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.