Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Search vault content by keyword using Grep. Zero dependencies — works in any vault without indexes or plugins. Groups results by directory for easy scanning.
.claude/skills/ballred-search/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | -12% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -33% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -29% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -11% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -33% | 0% |
Fast keyword search across all vault markdown files using the Grep tool. No indexes, no plugins, no setup — just structured search with directory grouping.
/search <term>Examples:
/search project planning/search weekly review/search TODOWhen the user invokes /search <term>:
Use the Grep tool to search all .md files for the term:
Grep:
pattern: <search term>
glob: "*.md"
output_mode: content
-n: true
-C: 1Exclude hidden directories (.claude/, .obsidian/) and templates:
Grep:
pattern: <search term>
glob: "*.md"
path: .
output_mode: content
-n: true
-C: 1Filter out results from .claude/, .obsidian/, and Templates/ directories.
Organise matches into sections by their parent directory:
Format output as:
markdown## Search: "<term>" ### Daily Notes/ - **2024-01-15.md** (line 23): ...matching context... - **2024-01-14.md** (line 8): ...matching context... ### Projects/ - **Project Alpha.md** (line 45): ...matching context... ### Goals/ - **2024 Goals.md** (line 12): ...matching context... **Found X matches across Y files**
After showing results, check if any matched files contain [[wiki-links]] to other notes. If so, briefly mention:
💡 Related notes mentioned in results: [[Note A]], [[Note B]]If no matches are found:
Archives/ if not already included-i: true to the Grep call for case-insensitive searchtask.*complete, #tag-name/daily to quickly find when something was mentioned| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 3,668 | 4,584 | +25% | 1 | 1 | 0% | 643 | 937 | +46% | 0 | 0 | — |
case-02 | fail→fail | 5,262 | 5,105 | -3% | 1 | 1 | 0% | 881 | 1,013 | +15% | 0 | 0 | — |
case-20 | pass→fail | 4,388 | 6,372 | +45% | 1 | 1 | 0% | 855 | 909 | +6% | 0 | 0 | — |
case-03 | fail→fail | 9,936 | 9,016 | -9% | 1 | 1 | 0% | 2,017 | 894 | -56% | 0 | 0 | — |
case-04 | pass→pass | 2,291 | 2,302 | +0% | 1 | 1 | 0% | 432 | 1,003 | +132% | 0 | 0 | — |
case-05 | fail→pass | 6,495 | 1,635 | -75% | 1 | 1 | 0% | 1,066 | 933 | -12% | 0 | 0 | — |
case-06 | fail→pass | 10,707 | 3,111 | -71% | 1 | 1 | 0% | 1,751 | 1,177 | -33% | 0 | 0 | — |
case-07 | pass→pass | 7,288 | 3,163 | -57% | 1 | 1 | 0% | 1,276 | 1,112 | -13% | 0 | 0 | — |
case-08 | fail→pass | 7,013 | 1,931 | -72% | 1 | 1 | 0% | 1,376 | 973 | -29% | 0 | 0 | — |
case-09 | fail→pass | 6,165 | 1,788 | -71% | 1 | 1 | 0% | 1,046 | 931 | -11% | 0 | 0 | — |
case-10 | pass→pass | 5,075 | 3,197 | -37% | 1 | 1 | 0% | 867 | 1,125 | +30% | 0 | 0 | — |
case-11 | pass→pass | 7,985 | 3,430 | -57% | 1 | 1 | 0% | 1,430 | 1,204 | -16% | 0 | 0 | — |
case-12 | pass→pass | 6,924 | 3,262 | -53% | 1 | 1 | 0% | 1,183 | 1,233 | +4% | 0 | 0 | — |
case-13 | pass→pass | 6,093 | 2,329 | -62% | 1 | 1 | 0% | 1,095 | 1,044 | -5% | 0 | 0 | — |
case-14 | pass→pass | 4,651 | 1,642 | -65% | 1 | 1 | 0% | 778 | 885 | +14% | 0 | 0 | — |
case-21 | pass→fail | 9,877 | 4,550 | -54% | 1 | 1 | 0% | 1,780 | 1,281 | -28% | 0 | 0 | — |
case-15 | fail→pass | 10,984 | 3,622 | -67% | 1 | 1 | 0% | 1,800 | 1,214 | -33% | 0 | 0 | — |
case-16 | pass→pass | 7,140 | 2,219 | -69% | 1 | 1 | 0% | 1,158 | 1,026 | -11% | 0 | 0 | — |
case-17 | pass→pass | 8,949 | 2,720 | -70% | 1 | 1 | 0% | 1,700 | 1,199 | -29% | 0 | 0 | — |
case-18 | fail→pass | 5,329 | 1,522 | -71% | 1 | 1 | 0% | 830 | 906 | +9% | 0 | 0 | — |
case-19 | pass→fail | 6,445 | 1,450 | -78% | 1 | 1 | 0% | 1,062 | 843 | -21% | 0 | 0 | — |
case-22 | pass→fail | 5,955 | 6,836 | +15% | 1 | 1 | 0% | 1,055 | 1,138 | +8% | 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 17 counted toward the lift figure. The other 5 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 +9 percentage points is the difference between those two pass rates over the 17 comparable cases. 4 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.