ambisql

ambisql is a Databases & SQL skill for AI agents, published by JustinzjDing in the AmbiSQL repository on GitHub. Skillspace rates ambisql D (69/100) and it passed the safety scan; the rating is based on static analysis only.

Detects and resolves natural language query ambiguities before SQL generation, preventing incorrect SQL from unclear user intent. Applies AmbiSQL's 7-type taxonomy (AmbiSchema, AmbiValue, AmbiView, AmbiSource, AmbiContext, AmbiFallacy, AmbiRef) to classify ambiguous phrases, generates intuitive multi-choice clarification questions, and rewrites queries into precise, unambiguous form with evidence. Use this skill whenever a user asks a database question in natural language, requests Text-to-SQL or NL2SQL conversion, writes a query that could map to multiple SQL interpretations, mentions table or column names ambiguously, uses vague filters like "top", "best", "popular", "recent", or "latest", references dates imprecisely like "after the World Cup" or "yesterday", asks about data where the question seems underspecified, or discusses improving SQL query accuracy. Even if the user doesn't explicitly mention "ambiguity", activate for any natural language database query that could benefit…

Grade
D
Quality
69 / 100
Safety
Passed
GitHub stars
21

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, so go by its current files.

Our review

Architecture
78 / 100
Maturity
Structured: ships references or scripts
Security scan
No issues found
License
Apache-2.0
Adoption
Adopted by 0 other repositories, in 0 collections

Not checked 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.