Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when the user wants to rename, extract, split, move, or restructure code safely. Examples: "Rename this function", "Extract this into a module", "Refactor this class", "Move this to a separate file"
.claude/skills/reinamaccredy-gitnexus-refactoring/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -39% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -29% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -11% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 28% | 0% |
1. gitnexus_impact({target: "X", direction: "upstream"}) → Map all dependents
2. gitnexus_query({query: "X"}) → Find execution flows involving X
3. gitnexus_context({name: "X"}) → See all incoming/outgoing refs
4. Plan update order: interfaces → implementations → callers → tests> If "Index is stale" → run npx gitnexus analyze in terminal.
- [ ] gitnexus_rename({symbol_name: "oldName", new_name: "newName", dry_run: true}) — preview all edits
- [ ] Review graph edits (high confidence) and ast_search edits (review carefully)
- [ ] If satisfied: gitnexus_rename({..., dry_run: false}) — apply edits
- [ ] gitnexus_detect_changes() — verify only expected files changed
- [ ] Run tests for affected processes- [ ] gitnexus_context({name: target}) — see all incoming/outgoing refs
- [ ] gitnexus_impact({target, direction: "upstream"}) — find all external callers
- [ ] Define new module interface
- [ ] Extract code, update imports
- [ ] gitnexus_detect_changes() — verify affected scope
- [ ] Run tests for affected processes- [ ] gitnexus_context({name: target}) — understand all callees
- [ ] Group callees by responsibility
- [ ] gitnexus_impact({target, direction: "upstream"}) — map callers to update
- [ ] Create new functions/services
- [ ] Update callers
- [ ] gitnexus_detect_changes() — verify affected scope
- [ ] Run tests for affected processesgitnexus_rename — automated multi-file rename:
gitnexus_rename({symbol_name: "validateUser", new_name: "authenticateUser", dry_run: true})
→ 12 edits across 8 files
→ 10 graph edits (high confidence), 2 ast_search edits (review)
→ Changes: [{file_path, edits: [{line, old_text, new_text, confidence}]}]gitnexus_impact — map all dependents first:
gitnexus_impact({target: "validateUser", direction: "upstream"})
→ d=1: loginHandler, apiMiddleware, testUtils
→ Affected Processes: LoginFlow, TokenRefreshgitnexus_detect_changes — verify your changes after refactoring:
gitnexus_detect_changes({scope: "all"})
→ Changed: 8 files, 12 symbols
→ Affected processes: LoginFlow, TokenRefresh
→ Risk: MEDIUMgitnexus_cypher — custom reference queries:
cypherMATCH (caller)-[:CodeRelation {type: 'CALLS'}]->(f:Function {name: "validateUser"}) RETURN caller.name, caller.filePath ORDER BY caller.filePath
| Risk Factor | Mitigation | | ------------------- | ----------------------------------------- | | Many callers (>5) | Use gitnexus_rename for automated updates | | Cross-area refs | Use detect_changes after to verify scope | | String/dynamic refs | gitnexus_query to find them | | External/public API | Version and deprecate properly |
validateUser to authenticateUser1. gitnexus_rename({symbol_name: "validateUser", new_name: "authenticateUser", dry_run: true})
→ 12 edits: 10 graph (safe), 2 ast_search (review)
→ Files: validator.ts, login.ts, middleware.ts, config.json...
2. Review ast_search edits (config.json: dynamic reference!)
3. gitnexus_rename({symbol_name: "validateUser", new_name: "authenticateUser", dry_run: false})
→ Applied 12 edits across 8 files
4. gitnexus_detect_changes({scope: "all"})
→ Affected: LoginFlow, TokenRefresh
→ Risk: MEDIUM — run tests for these flows| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 3,216 | 8,595 | +167% | 1 | 1 | 0% | 250 | 1,341 | +436% | 0 | 0 | — |
case-02 | fail→fail | 14,249 | 6,704 | -53% | 1 | 1 | 0% | 2,176 | 1,346 | -38% | 0 | 0 | — |
case-03 | fail→fail | 16,395 | 6,293 | -62% | 1 | 1 | 0% | 2,292 | 1,322 | -42% | 0 | 0 | — |
case-04 | fail→pass | 14,366 | 2,121 | -85% | 1 | 1 | 0% | 1,972 | 1,205 | -39% | 0 | 0 | — |
case-05 | fail→fail | 13,862 | 13,863 | +0% | 1 | 1 | 0% | 2,453 | 2,997 | +22% | 0 | 0 | — |
case-06 | pass→pass | 15,191 | 9,498 | -37% | 1 | 1 | 0% | 2,594 | 2,242 | -14% | 0 | 0 | — |
case-07 | fail→pass | 18,094 | 15,553 | -14% | 1 | 1 | 0% | 2,400 | 1,692 | -30% | 0 | 0 | — |
case-08 | pass→pass | 7,499 | 4,858 | -35% | 1 | 1 | 0% | 1,181 | 1,678 | +42% | 0 | 0 | — |
case-09 | fail→pass | 10,116 | 3,809 | -62% | 1 | 1 | 0% | 1,687 | 1,641 | -3% | 0 | 0 | — |
case-10 | fail→fail | 16,074 | 4,517 | -72% | 1 | 1 | 0% | 2,577 | 1,663 | -35% | 0 | 0 | — |
case-11 | pass→pass | 13,527 | 10,007 | -26% | 1 | 1 | 0% | 1,820 | 2,460 | +35% | 0 | 0 | — |
case-20 | pass→fail | 13,449 | 13,322 | -1% | 1 | 1 | 0% | 1,828 | 1,610 | -12% | 0 | 0 | — |
case-12 | fail→pass | 11,779 | 2,530 | -79% | 1 | 1 | 0% | 1,621 | 1,445 | -11% | 0 | 0 | — |
case-13 | fail→pass | 8,727 | 7,435 | -15% | 1 | 1 | 0% | 1,689 | 2,170 | +28% | 0 | 0 | — |
case-14 | fail→pass | 11,866 | 4,484 | -62% | 1 | 1 | 0% | 1,878 | 1,631 | -13% | 0 | 0 | — |
case-15 | fail→pass | 14,055 | 2,649 | -81% | 1 | 1 | 0% | 1,816 | 1,414 | -22% | 0 | 0 | — |
case-16 | fail→pass | 15,811 | 3,971 | -75% | 1 | 1 | 0% | 2,671 | 1,670 | -37% | 0 | 0 | — |
case-17 | fail→fail | 16,329 | 6,785 | -58% | 1 | 1 | 0% | 2,784 | 1,396 | -50% | 0 | 0 | — |
case-18 | fail→pass | 8,132 | 4,021 | -51% | 1 | 1 | 0% | 951 | 1,487 | +56% | 0 | 0 | — |
case-19 | pass→pass | 8,615 | 5,221 | -39% | 1 | 1 | 0% | 1,178 | 1,685 | +43% | 0 | 0 | — |
case-21 | pass→fail | 18,454 | 5,196 | -72% | 1 | 1 | 0% | 2,777 | 1,263 | -55% | 0 | 0 | — |
case-22 | pass→fail | 13,949 | 6,444 | -54% | 1 | 1 | 0% | 1,826 | 1,380 | -24% | 0 | 0 | — |
case-23 | fail→pass | 13,009 | 4,700 | -64% | 1 | 1 | 0% | 1,745 | 1,563 | -10% | 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. 23 cases were attempted, and 16 counted toward the lift figure. The other 7 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 +30 percentage points is the difference between those two pass rates over the 16 comparable cases. 3 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.