Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Find dead code, complexity hotspots, and refactoring candidates in indexed source code. Use when the user asks about source-code quality, dead code, unused functions, zero callers, complexity, cyclomatic complexity, hotspots, refactoring candidates, or code smell questions. Do not use Grep, Glob, rg, or manual reference search for unused code; Memtrace uses graph reachability and complexity metrics.
.claude/skills/syncable-dev-memtrace-quality/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 32% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -17% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -14% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 10% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -23% | 0% |
Code quality via graph analysis — dead code, complexity hotspots, repository stats.
| Tool | Purpose | Required | Key optional | |------|---------|----------|--------------| | find_dead_code | Zero-caller symbols | repo_id | include_tests, limit, kinds[] | | find_most_complex_functions | Ranked complexity hotspots | repo_id | top_n (def 20) — not limit | | calculate_cyclomatic_complexity | Score one symbol | repo_id, target | — | | get_repository_stats | Repository overview | repo_id | branch |
> Parameter types: numbers must be JSON numbers — limit: 20, never "20" (MCP error -32602).
Full parameter spec for every Memtrace tool: references/mcp-parameters.md (bundled at the memtrace-skills plugin root).
json{ "repo_id": "memdb" }
json{ "repo_id": "memdb", "include_tests": false, "limit": 50 }
Exported symbols and entry points excluded by default. Results are candidates, not proof — callers via dynamic dispatch or reflection are invisible to the graph; verify before deleting.
json{ "repo_id": "memdb", "top_n": 10 }
Ordered by call-graph out-degree.
| Score | Rating | Action | |-------|--------|--------| | <5 | Low | Fine | | 5-10 | Medium | Consider simplifying | | 10-20 | High | Refactor candidate | | >20 | Critical | Refactor priority |
json{ "repo_id": "memdb", "target": "processOrder" }
| Result | Carries | |--------|---------| | Dead-code entry (find_dead_code) | Symbol name + kind with zero graph callers — e.g. format_legacy (Function) | | Complexity row (find_most_complex_functions) | Symbol, complexity score, risk level — e.g. processOrder — 27, Critical | | Single score (calculate_cyclomatic_complexity) | Cyclomatic complexity for target | | Stats (get_repository_stats) | Node counts by kind, edge counts, community and process counts for repo_id/branch |
| Mistake | Reality | |---------|---------| | find_most_complex_functions(limit: 10) | Param is top_n | | calculate_cyclomatic_complexity(symbol_id=...) | Required param is target | | Only looking at the highest complexity | Medium-complexity functions that are growing (check get_evolution) are often more urgent |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-05 | pass→fail | 6,118 | 8,989 | +47% | 1 | 1 | 0% | 1,046 | 990 | -5% | 0 | 0 | — |
case-01 | fail→fail | 6,808 | 5,684 | -17% | 1 | 1 | 0% | 1,174 | 953 | -19% | 0 | 0 | — |
case-02 | fail→fail | 6,512 | 5,306 | -19% | 1 | 1 | 0% | 502 | 1,015 | +102% | 0 | 0 | — |
case-03 | fail→fail | 7,895 | 4,673 | -41% | 1 | 1 | 0% | 556 | 859 | +54% | 0 | 0 | — |
case-04 | fail→pass | 4,893 | 2,499 | -49% | 1 | 1 | 0% | 770 | 1,017 | +32% | 0 | 0 | — |
case-06 | fail→fail | 7,852 | 5,321 | -32% | 1 | 1 | 0% | 1,128 | 973 | -14% | 0 | 0 | — |
case-07 | fail→fail | 7,940 | 7,673 | -3% | 1 | 1 | 0% | 429 | 1,266 | +195% | 0 | 0 | — |
case-08 | fail→pass | 13,761 | 6,645 | -52% | 1 | 1 | 0% | 2,063 | 1,708 | -17% | 0 | 0 | — |
case-09 | fail→fail | 14,295 | 5,497 | -62% | 1 | 1 | 0% | 1,452 | 952 | -34% | 0 | 0 | — |
case-10 | fail→pass | 10,527 | 3,172 | -70% | 1 | 1 | 0% | 1,429 | 1,235 | -14% | 0 | 0 | — |
case-11 | fail→pass | 5,689 | 2,076 | -64% | 1 | 1 | 0% | 847 | 933 | +10% | 0 | 0 | — |
case-12 | pass→pass | 11,601 | 3,880 | -67% | 1 | 1 | 0% | 1,754 | 1,248 | -29% | 0 | 0 | — |
case-13 | pass→pass | 6,912 | 1,815 | -74% | 1 | 1 | 0% | 1,124 | 938 | -17% | 0 | 0 | — |
case-14 | pass→pass | 15,082 | 9,291 | -38% | 1 | 1 | 0% | 2,145 | 2,046 | -5% | 0 | 0 | — |
case-15 | fail→pass | 12,925 | 5,415 | -58% | 1 | 1 | 0% | 1,937 | 1,496 | -23% | 0 | 0 | — |
case-16 | fail→fail | 8,607 | 5,153 | -40% | 1 | 1 | 0% | 1,462 | 862 | -41% | 0 | 0 | — |
case-17 | pass→pass | 10,748 | 1,912 | -82% | 1 | 1 | 0% | 1,635 | 961 | -41% | 0 | 0 | — |
case-18 | pass→pass | 12,709 | 5,265 | -59% | 1 | 1 | 0% | 1,732 | 1,360 | -21% | 0 | 0 | — |
case-19 | pass→pass | 10,598 | 2,897 | -73% | 1 | 1 | 0% | 1,758 | 1,151 | -35% | 0 | 0 | — |
case-20 | pass→fail | 7,757 | 8,056 | +4% | 1 | 1 | 0% | 1,432 | 1,048 | -27% | 0 | 0 | — |
case-21 | pass→pass | 5,995 | 10,357 | +73% | 1 | 1 | 0% | 1,001 | 2,168 | +117% | 0 | 0 | — |
case-22 | pass→pass | 10,433 | 24,443 | +134% | 1 | 1 | 0% | 1,845 | 2,210 | +20% | 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 14 counted toward the lift figure. The other 8 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 +14 percentage points is the difference between those two pass rates over the 14 comparable cases. 2 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.