Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Reorganize the user's X and LinkedIn network with review-first pruning, add/follow recommendations, and channel-specific warm outreach drafted in the user's real voice. Use when the user wants to clean up following lists, grow toward current priorities, or rebalance a social graph around higher-signal relationships.
.claude/skills/bilal140202-connections-optimizer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -26% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 71% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 104% | 0% |
Reorganize the user's network instead of treating outbound as a one-way prospecting list.
This skill handles:
Collect or infer:
light-pass, default, or aggressiveIf the user does not specify a mode, use default.
x-api for X graph inspection and recent activitylead-intelligence for target discovery and warm-path rankingsocial-graph-ranker when the user wants bridge value scored independently of the broader lead workflowbrand-voice before drafting outboundlight-passdefaultaggressiveUse these positive signals:
Use these negative signals:
Mutuals and real warm-path bridges should be penalized less aggressively than one-way follows.
lead-intelligence plus research surfaces to rank expansion candidates.brand-voice before drafting messages.textCONNECTIONS OPTIMIZER REPORT ============================ Mode: Platforms: Priority Set: Prune Queue - handle / profile reason: confidence: action: Review Queue - handle / profile reason: risk: Keep / Protect - handle / profile bridge value: Add / Follow Targets - person why now: warm path: preferred channel: Drafts - X DM: - LinkedIn: - Apple Mail:
brand-voice for the reusable voice profilesocial-graph-ranker for the standalone bridge-scoring and warm-path mathlead-intelligence for weighted target and warm-path discoveryx-api for X graph access, drafting, and optional apply flowscontent-engine when the user also wants public launch content around network moves| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 31,014 | 15,764 | -49% | 1 | 1 | 0% | 4,684 | 3,484 | -26% | 0 | 0 | — |
case-02 | pass→pass | 31,563 | 15,493 | -51% | 1 | 1 | 0% | 4,105 | 3,598 | -12% | 0 | 0 | — |
case-03 | fail→pass | 22,258 | 16,597 | -25% | 1 | 1 | 0% | 3,272 | 3,551 | +9% | 0 | 0 | — |
case-04 | fail→pass | 14,576 | 7,738 | -47% | 1 | 1 | 0% | 2,142 | 2,233 | +4% | 0 | 0 | — |
case-05 | fail→pass | 8,817 | 8,953 | +2% | 1 | 1 | 0% | 1,468 | 2,513 | +71% | 0 | 0 | — |
case-06 | fail→pass | 6,792 | 6,102 | -10% | 1 | 1 | 0% | 995 | 2,027 | +104% | 0 | 0 | — |
case-07 | fail→pass | 12,133 | 7,634 | -37% | 1 | 1 | 0% | 1,691 | 2,324 | +37% | 0 | 0 | — |
case-08 | fail→pass | 14,996 | 6,200 | -59% | 1 | 1 | 0% | 2,127 | 2,028 | -5% | 0 | 0 | — |
case-09 | fail→fail | 10,237 | 7,038 | -31% | 1 | 1 | 0% | 1,605 | 2,232 | +39% | 0 | 0 | — |
case-10 | pass→pass | 9,880 | 8,768 | -11% | 1 | 1 | 0% | 1,541 | 2,574 | +67% | 0 | 0 | — |
case-11 | pass→pass | 11,102 | 5,946 | -46% | 1 | 1 | 0% | 1,491 | 1,935 | +30% | 0 | 0 | — |
case-12 | pass→pass | 10,751 | 6,487 | -40% | 1 | 1 | 0% | 1,602 | 2,119 | +32% | 0 | 0 | — |
case-13 | fail→fail | 8,248 | 4,954 | -40% | 1 | 1 | 0% | 1,355 | 1,902 | +40% | 0 | 0 | — |
case-14 | pass→pass | 13,347 | 2,853 | -79% | 1 | 1 | 0% | 2,091 | 1,549 | -26% | 0 | 0 | — |
case-15 | fail→pass | 14,641 | 10,248 | -30% | 1 | 1 | 0% | 2,140 | 2,347 | +10% | 0 | 0 | — |
case-16 | pass→pass | 16,556 | 10,073 | -39% | 1 | 1 | 0% | 2,457 | 2,670 | +9% | 0 | 0 | — |
case-17 | fail→pass | 11,297 | 7,230 | -36% | 1 | 1 | 0% | 1,679 | 2,138 | +27% | 0 | 0 | — |
case-18 | pass→pass | 10,324 | 2,026 | -80% | 1 | 1 | 0% | 1,670 | 1,422 | -15% | 0 | 0 | — |
case-19 | fail→pass | 16,279 | 6,601 | -59% | 1 | 1 | 0% | 2,433 | 2,224 | -9% | 0 | 0 | — |
case-20 | pass→pass | 8,039 | 7,015 | -13% | 1 | 1 | 0% | 1,289 | 2,058 | +60% | 0 | 0 | — |
case-21 | pass→pass | 11,748 | 12,186 | +4% | 1 | 1 | 0% | 2,222 | 3,304 | +49% | 0 | 0 | — |
case-22 | pass→pass | 18,845 | 16,643 | -12% | 1 | 1 | 0% | 2,932 | 3,762 | +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. The headline lift of +45 percentage points is the difference between those two pass rates over the 22 comparable cases.
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.