Name: llamaindex
Rating: 55.2 (1 reviews)
Author: membranedev

llamaindex

LlamaIndex integration. Manage data, records, and automate workflows. Use when the user wants to interact with LlamaIndex data.

Quality

63%

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 ./skills/llamaindex/SKILL.md

Quality

Content

63%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 body is a strongly actionable, well-sequenced CLI integration guide with concrete commands and a real validation/polling loop. Its weaknesses are an unnecessary introductory concept explanation, slightly inconsistent step numbering, and a monolithic single-file structure with no progressive disclosure references.

Suggestions

Remove the opening paragraph defining what LlamaIndex is and trim auth-plumbing commentary; Claude already knows the framework.

Fix step numbering so the connect/wait flow has a labeled Step 1 and Step 2 matching the "skip to Step 2" references.

Move the detailed clientAction state reference and proxy flag table into a references file (e.g., references/connection-states.md) and link to it from the main flow.

Dimension	Reasoning	Score
Conciseness	Mostly efficient command examples, but the opening paragraph ("LlamaIndex is a data framework for building LLM applications over custom data sources...") explains what LlamaIndex is and "so you can focus on the integration logic rather than auth plumbing" adds padding Claude does not need. Not a 4 because the concept re-explanation and softening prose could be trimmed; not a 2 because the bulk is useful executable command reference.	3 / 5
Actionability	Concrete, copy-paste-ready commands throughout (install, login, connection ensure/get, action list/run, request) with specific flags and an options table. Not a 5 because some guidance around the clientAction state machine is narrative rather than directly executable steps.	4 / 5
Workflow Clarity	Clear install → authenticate → connect → poll-for-ready → search → run sequence with an explicit polling validation checkpoint and feedback loop (re-poll after user action, check error field on failure). Not a 5 because step numbering is inconsistent ("skip to Step 2" and "1b" without a labeled 1a/Step 1), leaving minor sequencing gaps.	4 / 5
Progressive Disclosure	The file has clear section headers but is a single ~140-line monolith with no external references or bundle files, and detailed material that could be split (the clientAction state machine, the proxy flag table) is inlined. Not a 4 because there are no signaled one-level-deep references; not a 2 because section structure is present and organized.	3 / 5
	Total	14 / 20 Passed

Description

62%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 is well-targeted to a specific named integration and correctly pairs a what-clause with a Use-when trigger. Its main weakness is generic action verbs and limited keyword variation, which keep specificity and trigger quality in the mid-range.

Suggestions

Replace generic verbs with concrete LlamaIndex actions (e.g., "ingest and index documents, build query engines, run retrieval queries").

Add natural trigger synonyms a user might say, such as "indexing data", "query engines", "retrieval", or "LlamaIndex docs".

Broaden the Use-when clause to cover common intents like building indexes or querying custom data, not just "interact with LlamaIndex data".

Dimension	Reasoning	Score
Specificity	The description names the domain (LlamaIndex) and 2-3 actions ("Manage data, records, and automate workflows") but the actions are generic rather than concrete, matching the anchor for naming domain and a few non-comprehensive actions. Not a 2 because it lists multiple actions beyond a single minimal one; not a 4 because the actions lack specific concrete detail.	3 / 5
Completeness	It provides both a "what" (manage data, records, automate workflows) and an explicit "when" ("Use when the user wants to interact with LlamaIndex data"), so it is not capped at 3. Not a 5 because the "when" trigger is somewhat narrow and the "what" lacks concrete trigger phrases.	4 / 5
Trigger Term Quality	It includes relevant keywords ("LlamaIndex", "data", "records", "workflows") and a natural trigger phrase ("interact with LlamaIndex data"), but misses common variations or synonyms a user might say. Not a 4 because coverage of natural phrasings is thin rather than merely missing a few.	3 / 5
Distinctiveness Conflict Risk	The explicit binding to "LlamaIndex" gives it a clear niche with minimal conflict risk versus other skills. Not a 5 because the generic action verbs (manage data, records, workflows) introduce minor overlap risk with adjacent data-skills.	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: membranedev/application-skills
Path: skills/llamaindex/SKILL.md
Commit: f484c82

Reviewed: 6 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.