Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when the user asks how code works, wants to understand architecture, trace execution flows, or explore unfamiliar parts of the codebase. Examples: "How does X work?", "What calls this function?", "Show me the auth flow"
.claude/skills/reinamaccredy-gitnexus-exploring/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -55% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -57% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 26% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -43% | 0% |
1. READ gitnexus://repos → Discover indexed repos
2. READ gitnexus://repo/{name}/context → Codebase overview, check staleness
3. gitnexus_query({query: "<what you want to understand>"}) → Find related execution flows
4. gitnexus_context({name: "<symbol>"}) → Deep dive on specific symbol
5. READ gitnexus://repo/{name}/process/{name} → Trace full execution flow> If step 2 says "Index is stale" → run npx gitnexus analyze in terminal.
- [ ] READ gitnexus://repo/{name}/context
- [ ] gitnexus_query for the concept you want to understand
- [ ] Review returned processes (execution flows)
- [ ] gitnexus_context on key symbols for callers/callees
- [ ] READ process resource for full execution traces
- [ ] Read source files for implementation details| Resource | What you get | | --------------------------------------- | ------------------------------------------------------- | | gitnexus://repo/{name}/context | Stats, staleness warning (~150 tokens) | | gitnexus://repo/{name}/clusters | All functional areas with cohesion scores (~300 tokens) | | gitnexus://repo/{name}/cluster/{name} | Area members with file paths (~500 tokens) | | gitnexus://repo/{name}/process/{name} | Step-by-step execution trace (~200 tokens) |
gitnexus_query — find execution flows related to a concept:
gitnexus_query({query: "payment processing"})
→ Processes: CheckoutFlow, RefundFlow, WebhookHandler
→ Symbols grouped by flow with file locationsgitnexus_context — 360-degree view of a symbol:
gitnexus_context({name: "validateUser"})
→ Incoming calls: loginHandler, apiMiddleware
→ Outgoing calls: checkToken, getUserById
→ Processes: LoginFlow (step 2/5), TokenRefresh (step 1/3)1. READ gitnexus://repo/my-app/context → 918 symbols, 45 processes
2. gitnexus_query({query: "payment processing"})
→ CheckoutFlow: processPayment → validateCard → chargeStripe
→ RefundFlow: initiateRefund → calculateRefund → processRefund
3. gitnexus_context({name: "processPayment"})
→ Incoming: checkoutHandler, webhookHandler
→ Outgoing: validateCard, chargeStripe, saveTransaction
4. Read src/payments/processor.ts for implementation details| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 13,422 | 4,687 | -65% | 1 | 1 | 0% | 1,744 | 876 | -50% | 0 | 0 | — |
case-02 | fail→fail | 21,163 | 6,718 | -68% | 1 | 1 | 0% | 1,641 | 882 | -46% | 0 | 0 | — |
case-03 | fail→fail | 14,835 | 4,883 | -67% | 1 | 1 | 0% | 2,141 | 899 | -58% | 0 | 0 | — |
case-04 | fail→pass | 11,917 | 2,619 | -78% | 1 | 1 | 0% | 2,101 | 938 | -55% | 0 | 0 | — |
case-05 | fail→fail | 9,181 | 4,733 | -48% | 1 | 1 | 0% | 1,622 | 837 | -48% | 0 | 0 | — |
case-06 | fail→pass | 17,249 | 2,610 | -85% | 1 | 1 | 0% | 2,674 | 1,148 | -57% | 0 | 0 | — |
case-12 | fail→pass | 15,025 | 6,191 | -59% | 1 | 1 | 0% | 1,998 | 1,685 | -16% | 0 | 0 | — |
case-07 | fail→pass | 6,019 | 2,639 | -56% | 1 | 1 | 0% | 883 | 1,116 | +26% | 0 | 0 | — |
case-08 | fail→fail | 10,119 | 2,306 | -77% | 1 | 1 | 0% | 1,769 | 1,065 | -40% | 0 | 0 | — |
case-09 | fail→pass | 9,771 | 2,804 | -71% | 1 | 1 | 0% | 1,841 | 1,049 | -43% | 0 | 0 | — |
case-10 | fail→pass | 11,231 | 3,438 | -69% | 1 | 1 | 0% | 1,547 | 1,029 | -33% | 0 | 0 | — |
case-11 | fail→pass | 10,544 | 2,278 | -78% | 1 | 1 | 0% | 1,914 | 990 | -48% | 0 | 0 | — |
case-13 | pass→pass | 46,952 | 31,615 | -33% | 1 | 1 | 0% | 1,019 | 1,378 | +35% | 0 | 0 | — |
case-14 | pass→pass | 37,322 | 7,775 | -79% | 1 | 1 | 0% | 2,285 | 1,220 | -47% | 0 | 0 | — |
case-15 | fail→fail | 9,977 | 4,904 | -51% | 1 | 1 | 0% | 1,558 | 1,240 | -20% | 0 | 0 | — |
case-16 | pass→pass | 19,675 | 9,738 | -51% | 1 | 1 | 0% | 2,715 | 2,384 | -12% | 0 | 0 | — |
case-17 | fail→pass | 6,555 | 3,883 | -41% | 1 | 1 | 0% | 938 | 1,130 | +20% | 0 | 0 | — |
case-18 | fail→pass | 13,113 | 2,453 | -81% | 1 | 1 | 0% | 1,794 | 1,037 | -42% | 0 | 0 | — |
case-19 | fail→pass | 11,004 | 3,076 | -72% | 1 | 1 | 0% | 1,666 | 1,141 | -32% | 0 | 0 | — |
case-20 | pass→fail | 12,987 | 8,051 | -38% | 1 | 1 | 0% | 1,942 | 1,235 | -36% | 0 | 0 | — |
case-21 | pass→pass | 27,087 | 10,586 | -61% | 1 | 1 | 0% | 2,253 | 2,684 | +19% | 0 | 0 | — |
case-22 | pass→fail | 8,544 | 12,992 | +52% | 1 | 1 | 0% | 1,659 | 1,197 | -28% | 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 +36 percentage points is the difference between those two pass rates over the 17 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.