autorag-setup

Install and configure AutoRAG, or repair its single search model, approved document roots, retrieval indexes, datasource skills, and health checks without exposing credentials. Use when autorag is missing, init/refresh/health fails, indexes are stale, or the user wants to add folders or datasources.

Quality

89%

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

Quality

Content

78%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-sequenced setup guide with strong validation gates and a completion checklist. Its main weakness is progressive disclosure: substantial reference material is inlined in one long file rather than split into one-level-deep reference files.

Suggestions

Move the large datasource catalog (builtin template names + JSONC example) and embedder/default reference detail into separate reference files (e.g. references/datasources.md, references/embedders.md) linked one level deep from SKILL.md.

Add an explicit fix-and-retry loop for refresh/index build failures (e.g. what to inspect and re-run when `autorag refresh` or `health` fails) to strengthen workflow_clarity feedback loops.

Trim a few explanatory prose passages (e.g. the librarian-agent architecture paragraph) to the minimum needed for action, keeping conciseness at the top of the scale.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and densely packed with AutoRAG-specific operational detail Claude would not know (config keys, datasource CLIs, version gotchas), with only minor prose that could be trimmed; it avoids explaining generic concepts.	4 / 5
Actionability	Provides fully executable, copy-paste-ready commands (`bun install -g @autorag/librarian`, `autorag init --search-paths ...`, `autorag setup --format json`, `autorag health --json`) and complete JSON config examples covering the common cases.	5 / 5
Workflow Clarity	Clear sequenced flow from install through inspect, configure, approve roots, initialize, probe datasources, verify indexes, to a final 'Completion condition' validation checklist, with most checkpoints present; minor gaps in explicit fix-and-retry loops for some stages.	4 / 5
Progressive Disclosure	Well-sectioned with clear headers and tables, but it is a ~300-line monolithic file with reference-style content (datasource JSONC catalog, embedder defaults) inlined and no external reference files to split the detail into.	3 / 5
	Total	16 / 20 Passed

Description

100%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, third-person description that concisely states multiple concrete capabilities and pairs them with an explicit, natural-language 'Use when' trigger clause. It is distinctive, complete, and free of fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Install and configure AutoRAG, or repair its single search model, approved document roots, retrieval indexes, datasource skills, and health checks' — covering install, configure, and several distinct repair targets comprehensively.	5 / 5
Completeness	Explicitly answers both what ('Install and configure AutoRAG, or repair...') and when ('Use when autorag is missing, init/refresh/health fails, indexes are stale...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases a user would say are present — 'autorag is missing', 'init/refresh/health fails', 'indexes are stale', 'add folders or datasources' — including CLI subcommands and synonyms.	5 / 5
Distinctiveness Conflict Risk	Targets a named tool (AutoRAG) with tool-specific triggers (autorag CLI, retrieval indexes, datasource skills), giving it a clear niche with minimal overlap risk.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Marker-Inc-Korea/AutoRAG
Path: skills/autorag-setup/SKILL.md
Commit: fd4441a

Reviewed: 4 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.