Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Run SQL queries against the WordPress development database. Use when querying database tables, inspecting Simple History events, checking WordPress data, or debugging database issues.
.claude/skills/microck-sql/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | 98% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 3% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 40% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 82% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -2% | 0% |
You are tasked with running SQL queries against the WordPress development database.
CLAUDE.local.md under "Database Access"bashdocker compose exec mariadb mysql -u<USER> -p<PASSWORD> <DATABASE> -e "YOUR_SQL_HERE"
Refer to CLAUDE.local.md for the actual credentials and connection details.
bashdocker compose exec mariadb mysql -u<USER> -p<PASSWORD> <DATABASE> -e "SHOW TABLES;"
bashdocker compose exec mariadb mysql -u<USER> -p<PASSWORD> <DATABASE> -e "SELECT * FROM wp_simple_history ORDER BY id DESC LIMIT 10;"
bashdocker compose exec mariadb mysql -u<USER> -p<PASSWORD> <DATABASE> -e "DESCRIBE wp_simple_history;"
bashdocker compose exec mariadb mysql -u<USER> -p<PASSWORD> <DATABASE> -e "SELECT COUNT(*) FROM wp_posts;"
The database contains multiple WordPress installations with different prefixes:
| Prefix | Installation | |--------|--------------| | wp_ | Main install (wordpress_mariadb) | | wp_nightly_ | Nightly build | | wp_6_0_ to wp_6_6_ | Version-specific installs | | wp_multisite_ | Multisite install | | wp_php74_ | PHP 7.4 install | | wp_subfolder_ | Subfolder install |
The main Simple History tables (using wp_ prefix):
wp_simple_history - Main events tablewp_simple_history_contexts - Event context/metadataCLAUDE.local.md\G at the end for vertical output| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-16 | pass→pass | 3,089 | 2,714 | -12% | 1 | 1 | 0% | 447 | 890 | +99% | 0 | 0 | — |
case-01 | fail→fail | 4,194 | 6,031 | +44% | 1 | 1 | 0% | 700 | 825 | +18% | 0 | 0 | — |
case-02 | fail→fail | 9,171 | 5,184 | -43% | 1 | 1 | 0% | 1,747 | 771 | -56% | 0 | 0 | — |
case-03 | fail→fail | 5,076 | 5,946 | +17% | 1 | 1 | 0% | 797 | 700 | -12% | 0 | 0 | — |
case-04 | fail→fail | 7,432 | 6,842 | -8% | 1 | 1 | 0% | 1,208 | 706 | -42% | 0 | 0 | — |
case-05 | fail→pass | 4,605 | 5,391 | +17% | 1 | 1 | 0% | 706 | 1,399 | +98% | 0 | 0 | — |
case-06 | fail→pass | 6,048 | 2,407 | -60% | 1 | 1 | 0% | 946 | 977 | +3% | 0 | 0 | — |
case-07 | fail→pass | 7,223 | 7,470 | +3% | 1 | 1 | 0% | 1,235 | 1,735 | +40% | 0 | 0 | — |
case-08 | fail→fail | 12,368 | 5,263 | -57% | 1 | 1 | 0% | 2,239 | 757 | -66% | 0 | 0 | — |
case-09 | fail→fail | 11,472 | 2,571 | -78% | 1 | 1 | 0% | 1,835 | 878 | -52% | 0 | 0 | — |
case-10 | fail→fail | 6,360 | 4,622 | -27% | 1 | 1 | 0% | 1,113 | 684 | -39% | 0 | 0 | — |
case-15 | fail→fail | 4,797 | 2,494 | -48% | 1 | 1 | 0% | 667 | 682 | +2% | 0 | 0 | — |
case-11 | fail→pass | 5,200 | 9,264 | +78% | 1 | 1 | 0% | 872 | 1,586 | +82% | 0 | 0 | — |
case-12 | fail→fail | 5,915 | 6,854 | +16% | 1 | 1 | 0% | 953 | 842 | -12% | 0 | 0 | — |
case-13 | pass→pass | 5,773 | 2,660 | -54% | 1 | 1 | 0% | 875 | 958 | +9% | 0 | 0 | — |
case-14 | fail→pass | 4,956 | 2,788 | -44% | 1 | 1 | 0% | 805 | 786 | -2% | 0 | 0 | — |
case-17 | fail→pass | 7,832 | 3,351 | -57% | 1 | 1 | 0% | 956 | 1,053 | +10% | 0 | 0 | — |
case-18 | pass→pass | 4,590 | 3,462 | -25% | 1 | 1 | 0% | 400 | 884 | +121% | 0 | 0 | — |
case-19 | fail→fail | 4,451 | 5,945 | +34% | 1 | 1 | 0% | 709 | 802 | +13% | 0 | 0 | — |
case-20 | pass→fail | 7,850 | 7,992 | +2% | 1 | 1 | 0% | 1,199 | 738 | -38% | 0 | 0 | — |
case-21 | pass→pass | 10,868 | 9,357 | -14% | 1 | 1 | 0% | 1,959 | 1,920 | -2% | 0 | 0 | — |
case-22 | pass→pass | 9,039 | 11,856 | +31% | 1 | 1 | 0% | 1,514 | 1,855 | +23% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 13 counted toward the lift figure. The other 9 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +23 percentage points is the difference between those two pass rates over the 13 comparable cases. 6 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.