Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Modern find-and-replace using sd (simpler than sed) and batch replacement patterns. Triggers on: sd, find replace, batch replace, sed replacement, string replacement, rename.
.claude/skills/aiskillstore-find-replace/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -26% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -32% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -14% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -21% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -1% | 0% |
Modern find-and-replace using sd.
bash# Replace in file (in-place) sd 'oldText' 'newText' file.txt # Replace in multiple files sd 'oldText' 'newText' *.js # Preview without changing (pipe) cat file.txt | sd 'old' 'new'
| sed | sd | |-----|-----| | sed 's/old/new/g' | sd 'old' 'new' | | sed -i 's/old/new/g' | sd 'old' 'new' file | | sed 's#path/to#new/path#g' | sd 'path/to' 'new/path' |
Key difference: sd is global by default, no delimiter issues.
bash# Variable/function rename sd 'oldName' 'newName' src/**/*.ts # Word boundaries (avoid partial matches) sd '\boldName\b' 'newName' src/**/*.ts # Import path update sd "from '../utils'" "from '@/utils'" src/**/*.ts # Capture groups sd 'console\.log\((.*)\)' 'logger.info($1)' src/**/*.js
bash# 1. List affected files rg -l 'oldPattern' src/ # 2. Preview replacements rg 'oldPattern' -r 'newPattern' src/ # 3. Apply sd 'oldPattern' 'newPattern' $(rg -l 'oldPattern' src/) # 4. Verify rg 'oldPattern' src/ # Should return nothing git diff # Review changes
| Character | Escape | |-----------|--------| | . | \. | | * | \* | | [ ] | \[ \] | | $ | \$ | | \ | \\ |
| Tip | Reason | |-----|--------| | Always preview with rg -r first | Avoid mistakes | | Use git before bulk changes | Easy rollback | | Use \b for word boundaries | Avoid partial matches | | Quote patterns | Prevent shell interpretation |
For detailed patterns, load:
./references/advanced-patterns.md - Regex, batch workflows, real-world examples| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 11,656 | 5,229 | -55% | 1 | 1 | 0% | 2,033 | 1,512 | -26% | 0 | 0 | — |
case-02 | fail→pass | 10,615 | 4,000 | -62% | 1 | 1 | 0% | 1,924 | 1,305 | -32% | 0 | 0 | — |
case-03 | pass→pass | 13,333 | 11,653 | -13% | 1 | 1 | 0% | 2,338 | 2,399 | +3% | 0 | 0 | — |
case-04 | fail→fail | 10,639 | 8,545 | -20% | 1 | 1 | 0% | 1,844 | 2,106 | +14% | 0 | 0 | — |
case-05 | pass→pass | 10,062 | 5,818 | -42% | 1 | 1 | 0% | 1,859 | 1,491 | -20% | 0 | 0 | — |
case-06 | pass→pass | 11,028 | 7,717 | -30% | 1 | 1 | 0% | 2,062 | 1,947 | -6% | 0 | 0 | — |
case-07 | fail→pass | 10,934 | 5,073 | -54% | 1 | 1 | 0% | 1,686 | 1,444 | -14% | 0 | 0 | — |
case-08 | fail→pass | 11,565 | 6,123 | -47% | 1 | 1 | 0% | 1,936 | 1,525 | -21% | 0 | 0 | — |
case-09 | fail→pass | 8,763 | 5,857 | -33% | 1 | 1 | 0% | 1,493 | 1,471 | -1% | 0 | 0 | — |
case-10 | pass→pass | 4,166 | 3,055 | -27% | 1 | 1 | 0% | 693 | 1,071 | +55% | 0 | 0 | — |
case-11 | pass→pass | 9,473 | 3,594 | -62% | 1 | 1 | 0% | 1,567 | 1,121 | -28% | 0 | 0 | — |
case-12 | fail→pass | 7,950 | 3,164 | -60% | 1 | 1 | 0% | 1,395 | 1,092 | -22% | 0 | 0 | — |
case-13 | fail→pass | 11,080 | 4,388 | -60% | 1 | 1 | 0% | 1,973 | 1,334 | -32% | 0 | 0 | — |
case-14 | pass→pass | 7,125 | 3,052 | -57% | 1 | 1 | 0% | 1,221 | 923 | -24% | 0 | 0 | — |
case-15 | pass→pass | 3,627 | 2,412 | -33% | 1 | 1 | 0% | 568 | 920 | +62% | 0 | 0 | — |
case-16 | fail→pass | 6,915 | 2,472 | -64% | 1 | 1 | 0% | 1,204 | 945 | -22% | 0 | 0 | — |
case-17 | fail→pass | 5,067 | 2,943 | -42% | 1 | 1 | 0% | 780 | 994 | +27% | 0 | 0 | — |
case-18 | fail→pass | 10,036 | 5,726 | -43% | 1 | 1 | 0% | 1,777 | 1,506 | -15% | 0 | 0 | — |
case-19 | fail→pass | 10,538 | 3,159 | -70% | 1 | 1 | 0% | 1,682 | 1,051 | -38% | 0 | 0 | — |
case-20 | pass→pass | 3,758 | 2,631 | -30% | 1 | 1 | 0% | 601 | 953 | +59% | 0 | 0 | — |
case-21 | pass→fail | 8,534 | 6,303 | -26% | 1 | 1 | 0% | 1,553 | 1,627 | +5% | 0 | 0 | — |
case-22 | fail→fail | 11,693 | 12,240 | +5% | 1 | 1 | 0% | 1,979 | 2,730 | +38% | 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. The headline lift of +45 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is 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.