sql-doc-autofix

sql-doc-autofix is a Docs quality & drift control skill for AI agents, published by StarRocks in the starrocks repository on GitHub. Skillspace rates sql-doc-autofix F (15/100) and the safety scan rated it unsafe; the rating is based on static analysis only.

Propose verified fixes for documentation SQL examples that fail the doc-rot checker (docs/scripts/run_sql_samples.py). Checks all three languages (docs/en, docs/zh, docs/ja) against every supported version (auto-discovered), classifies each FAILing example, and only for genuinely fixable ones proposes a corrected statement, verifies it against a live cluster of each version via the StarRocks MCP server, applies it to every language that carries the example, lints every file it touched with Vale (the same gate CI runs), and opens DRAFT [Doc] PRs whose backport boxes match exactly the versions each fix was verified on. Also emits a cross-language parity report. Never auto-merges.

Grade
F
Quality
15 / 100
Safety
Unsafe
GitHub stars
12,101

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since.

Our review

Architecture
96 / 100
Maturity
Basic: a single SKILL.md
Security scan
Critical-risk patterns
License
Not declared. Check the repository before reusing it.

What the scanner flagged

  • destructive rm -rf on home/root
  • mentions secrets in text

Not checked yet

  • Category is a classifier prediction; no model has read this skill yet
  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.