mysql

Execute read-only SQL queries against multiple MySQL databases. Use when: (1) querying MySQL databases, (2) exploring database schemas/tables, (3) running SELECT queries for data analysis, (4) checking database contents. Supports multiple database connections with descriptions for intelligent auto-selection. Blocks all write operations (INSERT, UPDATE, DELETE, DROP, etc.) for safety.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

86%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 tight, well-structured body whose commands, safety claims, and CLI flags all verify against the bundled query.py. The main gaps are a referenced-but-missing requirements.txt and a workflow that lacks an explicit verification step, with error recovery relegated to the troubleshooting table.

Suggestions

Ship the referenced requirements.txt (or replace the pip line with the direct install command `pip install mysql-connector-python`) so the documented setup command actually runs.

Add an explicit verification checkpoint to the Workflow section, e.g. run EXPLAIN or a small LIMIT probe before large queries and re-check results after execution, turning the troubleshooting table into an in-workflow feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is lean and operational: config fields, troubleshooting, and database-selection guidance are compact tables; there is no explanation of concepts Claude already knows (no "what is MySQL" padding). Every section earns its place, matching anchor 5 rather than the minor-trimming of anchor 4.	5 / 5
Actionability	All usage commands (e.g. `python3 scripts/query.py --db production --query "SELECT * FROM users LIMIT 10"`) are copy-paste ready and match the script's actual CLI, and the config example is complete. One concrete gap: "pip install -r requirements.txt" references a file that is not present in the bundle, so a fresh user hits a broken command — anchor 4, not 5.	4 / 5
Workflow Clarity	The Workflow section gives a clear 4-step sequence (list → match intent → explore schema → query with LIMIT), and the skill is read-only/non-batch so the destructive-cap does not apply. However, no explicit verification checkpoint appears in the workflow itself — error recovery lives only in the separate Troubleshooting table — which fits anchor 4's "most checkpoints present, minor validation gaps" rather than anchor 5's explicit validate-and-retry loop.	4 / 5
Progressive Disclosure	Content is appropriately split: the single script lives in scripts/query.py and is referenced cleanly one level deep, while SKILL.md stays a well-organized overview with clear section headers. Nothing that belongs in a separate file is inlined, so it matches anchor 5 rather than the minor-organization-gaps of anchor 4.	5 / 5
	Total	18 / 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 with explicit what/when structure, concrete actions, and a well-differentiated read-only MySQL niche. The only weakness is limited synonym variety in the trigger terms, where every variation reduces to "query".

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Execute read-only SQL queries", "exploring database schemas/tables", "running SELECT queries for data analysis", and "Blocks all write operations (INSERT, UPDATE, DELETE, DROP, etc.)" — with comprehensive coverage and third-person voice. It does not fit anchor 4 because there are no minor gaps in the action coverage.	5 / 5
Completeness	Explicitly answers both: "what" is stated first ("Execute read-only SQL queries against multiple MySQL databases") and "when" via a concrete "Use when:" clause with four numbered triggers. This matches the anchor-5 example structure exactly, not the weaker anchor 4.	5 / 5
Trigger Term Quality	Good natural-phrase coverage across the four triggers ("querying MySQL databases", "exploring database schemas/tables", "running SELECT queries for data analysis", "checking database contents"), but the synonyms are thin — all variants of "query" with no common alternatives like "look up", "fetch", or "view records". It falls between anchors 4 and 5, so 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche — read-only MySQL querying with an explicit write-block guarantee — that is distinct from generic SQL, database-admin, or data-analysis skills. Minimal conflict risk, matching anchor 5 rather than the "minor overlap" of anchor 4.	5 / 5
	Total	19 / 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: sanjay3290/ai-skills
Path: skills/mysql/SKILL.md
Commit: 281d88d

Reviewed: 6 days 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.