CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

autorag-lite-setup

Install and register the model-free AutoRAG Lite MCP server, configure approved roots and datasources, build indexes, and verify MCP discovery and search. Use when autorag-mcp is missing, MCP connection fails, indexes are stale, or the user wants document search without configuring a search model.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

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.

Highly actionable and dense with executable commands, precise failure modes, and strong validation checkpoints culminating in an explicit completion condition. Weaknesses are moderate: a sequencing inconsistency around datasource setup vs. registration, and reference-grade detail inlined in a single long file rather than split into well-signaled bundle files.

Suggestions

Move the datasource template catalog, Hister setup details, and supported-format list into clearly signaled reference files (e.g., 'See references/datasources.md') so SKILL.md reads as an overview rather than a full manual.

Reorder sections so 'Probe and configure datasources' precedes 'Register and verify the MCP connection', matching the stated 'After config and datasource setup, register the server' sequence.

Either promote the docs/datasource-skills.md pointer to a clearly signaled reference or remove the buried parenthetical so navigation to deeper material is explicit.

DimensionReasoningScore

Conciseness

The body is imperative and dense with operational specifics (exact flags, env vars, error codes) and never explains concepts Claude already knows, but sections like the ~20-line star-the-repository procedure and the clause-stacked Hister paragraph could be trimmed — efficient with minor over-explanation, not the every-token-earns-its-place of 5.

4 / 5

Actionability

Guidance is copy-paste ready throughout: `bun install -g @autorag/librarian`, `claude mcp add --transport stdio …`, `autorag lite init --search-paths …`, concrete MCP payloads like `{"methods":["parsed","minsync"]}`, and exact error codes ("index-not-ready", "retrieval-method-failed") paired with remediation commands covering the common cases.

5 / 5

Workflow Clarity

The phased sequence (install → init → register/verify → datasources → refresh → verify search → completion checklist) has explicit validation checkpoints and error-recovery loops, but the 'Register and verify' section precedes 'Probe and configure datasources' while stating registration happens after datasource setup — a minor sequencing contradiction that keeps it below 5.

4 / 5

Progressive Disclosure

The single ~290-line file inlines reference-like material (the datasource template catalog, Hister setup details, the supported-format list) that would fit separate reference files, and its lone reference (docs/datasource-skills.md) is buried in parentheses rather than clearly signaled — some structure with content that should be separate inline, though clear headers keep it above 2.

3 / 5

Total

16

/

20

Passed

Description

92%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 description: concrete action list, explicit 'Use when…' triggers tied to specific failure modes, and a clearly delineated niche. The only weakness is modest keyword coverage — a few natural synonyms users might say are missing.

DimensionReasoningScore

Specificity

The description lists five-plus concrete actions — "Install and register the model-free AutoRAG Lite MCP server, configure approved roots and datasources, build indexes, and verify MCP discovery and search" — giving comprehensive coverage with no gaps, matching the score-5 anchor rather than the 'minor gaps' of 4.

5 / 5

Completeness

It explicitly answers both questions: the what is the concrete install/register/configure/build/verify action list, and the when is an explicit "Use when…" clause with four concrete trigger conditions, exactly matching the score-5 anchor.

5 / 5

Trigger Term Quality

"autorag-mcp is missing", "MCP connection fails", "indexes are stale", and "document search" are natural user phrases, but common variations (e.g., "set up AutoRAG", "RAG", "search my documents") are absent — good coverage with a few natural terms missing, above the 'some relevant keywords' of 3.

4 / 5

Distinctiveness Conflict Risk

"model-free AutoRAG Lite MCP server" establishes a clear niche and the triggers are product-specific failure modes; the one broad phrase ("document search") is qualified by "without configuring a search model", keeping conflict risk minimal as in the score-5 anchor.

5 / 5

Total

19

/

20

Passed

Validation

100%

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-lite-setup/SKILL.md

Reviewed

Table of Contents

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.