autorag-doctor

Diagnose and repair a broken or half-working AutoRAG install so every configured source is both indexed and searchable. Checks AutoRAG, MinSync, Jikji, the embedding gateway, and every CLI-backed datasource (lazykatok, discrawl, slacrawl, wacrawl, telecrawl, notcrawl, qmd, mailcrawl, rclone, Spotlight), then fixes orphan locks, orphan processes, embedding dimension or identity mismatches, stale indexes, and missing setup. Use when search returns nothing or too little, refresh hangs or fails, a datasource disappeared from results, indexes look stale, the gateway will not start, or the user asks to check, diagnose, verify, or repair AutoRAG.

Quality

94%

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

88%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 highly actionable with a well-sequenced, validated workflow and strong section structure. It loses only minor points for slight prose verbosity and for keeping large reference tables inline rather than in dedicated files.

Suggestions

Tighten the explanatory prose rules (e.g. the upstream-bug paragraph and the embedding-mismatch rationale) to command/rule form to reach the lean conciseness anchor.

Move the Diagnostic codes table and/or the per-datasource native-check table into a references/ file (e.g. references/datasources.md) and link to it from the body, improving progressive disclosure and shrinking the inline footprint.

Consider extracting the Repair playbook subsections into a references/repair.md so the main body stays a triage-and-decide overview.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational — almost no concept-explanation padding — but prose rules like the 'A populated index plus an empty CLI result is an upstream bug' paragraph and the embedding-mismatch rationale could be trimmed slightly, so it sits just below the lean score-5 anchor.	4 / 5
Actionability	Fully executable throughout: copy-paste commands ('autorag status --json', 'autorag index rebuild --method minsync', 'pgrep -fl ...'), a concrete datasource→native-check table, and a worked report table covering the common cases per the score-5 anchor.	5 / 5
Workflow Clarity	A clear sequenced workflow (Triage → Probe datasources → Prove searchability → Repair → Report → Completion condition) with explicit validation checkpoints ('Re-run autorag status --json afterwards to confirm inFlight: false', 're-verified by re-running the failing check') and a feedback loop, satisfying the destructive/batch validation requirement.	5 / 5
Progressive Disclosure	Well-organized into clearly headed sections with easy navigation, but no bundle files exist and large reference blocks (the datasource table, the Diagnostic codes table) that could live in a separate reference file are inlined, leaving it just below the score-5 'appropriately split' anchor.	4 / 5
	Total	18 / 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.

The description is third-person, concrete, and explicitly pairs a comprehensive 'what' with a rich 'Use when' trigger clause. It is a strong match for the top anchor on every dimension.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Diagnose and repair', 'Checks AutoRAG, MinSync, Jikji, the embedding gateway', 'fixes orphan locks, orphan processes, embedding dimension or identity mismatches, stale indexes, and missing setup' — with comprehensive coverage matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers both 'what' (diagnose/repair AutoRAG so every source is indexed and searchable) and 'when' (a full 'Use when ...' clause with concrete trigger phrases), matching the score-5 anchor exactly.	5 / 5
Trigger Term Quality	The 'Use when' clause enumerates natural user phrases — 'search returns nothing or too little', 'refresh hangs or fails', 'a datasource disappeared from results', 'indexes look stale', 'the gateway will not start', 'check, diagnose, verify, or repair AutoRAG' — giving comprehensive natural-term coverage.	5 / 5
Distinctiveness Conflict Risk	A clear niche (AutoRAG install doctoring) with product-specific triggers (AutoRAG, MinSync, Jikji, named CLIs) and no realistic overlap with other skills; minimal conflict risk per the score-5 anchor.	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-doctor/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.