Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Agent assignment matrix, blocker escalation, and TDM coordination patterns. Use when assigning work to specialist agents, managing blockers across agents, coordinating multi-agent workflows, escalating issues, or verifying the pre-implementation gate. Do NOT use for direct implementation work.
.claude/skills/bybren-llc-agent-coordination/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | -35% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -30% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -40% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -25% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -36% | 0% |
Guide correct agent assignment, blocker escalation, and delivery coordination following team role boundaries.
| Work Type | Correct Agent | Never Use | | ------------------- | ----------------- | ------------------- | | Database/Migrations | Data Engineer | BE Developer | | Security/RLS | Security Engineer | QAS | | Documentation | Tech Writer | BE/FE Developer | | Specs/Planning | BSA | Any implementation | | Architecture | System Architect | Direct to developer | | API Routes | BE Developer | FE Developer | | UI Components | FE Developer | BE Developer | | Testing/QA | QAS | Implementation team | | PR/Releases | RTE | Developers |
MANDATORY before any implementation:
| Condition | Escalate To | Deadline | | ---------------------- | ----------- | ----------- | | Blocker > 1 hour | TDM | Immediately | | Blocker > 4 hours | ARCHitect | Urgent | | Architecture ambiguity | ARCHitect | Before work | | Cross-team dependency | TDM + POPM | Same day |
docs/workflow/TDM_AGENT_ASSIGNMENT_MATRIX.mddocs/sop/AGENT_WORKFLOW_SOP.md| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-03 | fail→pass | 10,021 | 4,175 | -58% | 1 | 1 | 0% | 1,724 | 1,127 | -35% | 0 | 0 | — |
case-04 | fail→pass | 13,624 | 6,703 | -51% | 1 | 1 | 0% | 2,045 | 1,424 | -30% | 0 | 0 | — |
case-01 | fail→pass | 10,738 | 3,843 | -64% | 1 | 1 | 0% | 1,823 | 1,088 | -40% | 0 | 0 | — |
case-02 | fail→pass | 15,219 | 8,974 | -41% | 1 | 1 | 0% | 2,577 | 1,934 | -25% | 0 | 0 | — |
case-05 | fail→pass | 11,837 | 4,902 | -59% | 1 | 1 | 0% | 1,799 | 1,159 | -36% | 0 | 0 | — |
case-06 | fail→pass | 9,381 | 4,450 | -53% | 1 | 1 | 0% | 1,459 | 1,056 | -28% | 0 | 0 | — |
case-07 | fail→pass | 11,878 | 3,173 | -73% | 1 | 1 | 0% | 1,740 | 895 | -49% | 0 | 0 | — |
case-08 | fail→pass | 13,189 | 3,104 | -76% | 1 | 1 | 0% | 1,969 | 837 | -57% | 0 | 0 | — |
case-09 | fail→pass | 12,173 | 4,052 | -67% | 1 | 1 | 0% | 1,824 | 1,053 | -42% | 0 | 0 | — |
case-10 | fail→pass | 11,133 | 2,974 | -73% | 1 | 1 | 0% | 1,713 | 912 | -47% | 0 | 0 | — |
case-11 | fail→pass | 8,008 | 1,883 | -76% | 1 | 1 | 0% | 1,190 | 675 | -43% | 0 | 0 | — |
case-12 | fail→pass | 14,657 | 3,756 | -74% | 1 | 1 | 0% | 2,135 | 1,013 | -53% | 0 | 0 | — |
case-13 | fail→pass | 14,172 | 4,497 | -68% | 1 | 1 | 0% | 2,049 | 1,069 | -48% | 0 | 0 | — |
case-14 | pass→pass | 14,635 | 4,249 | -71% | 1 | 1 | 0% | 2,139 | 1,086 | -49% | 0 | 0 | — |
case-15 | fail→pass | 14,748 | 4,209 | -71% | 1 | 1 | 0% | 2,059 | 1,024 | -50% | 0 | 0 | — |
case-16 | fail→pass | 10,942 | 2,220 | -80% | 1 | 1 | 0% | 1,565 | 746 | -52% | 0 | 0 | — |
case-17 | fail→pass | 8,640 | 2,598 | -70% | 1 | 1 | 0% | 1,194 | 844 | -29% | 0 | 0 | — |
case-18 | fail→pass | 9,395 | 2,268 | -76% | 1 | 1 | 0% | 1,447 | 785 | -46% | 0 | 0 | — |
case-19 | fail→pass | 14,662 | 3,216 | -78% | 1 | 1 | 0% | 2,269 | 887 | -61% | 0 | 0 | — |
case-20 | fail→pass | 14,118 | 2,832 | -80% | 1 | 1 | 0% | 1,935 | 759 | -61% | 0 | 0 | — |
case-21 | pass→pass | 8,090 | 10,099 | +25% | 1 | 1 | 0% | 1,522 | 2,071 | +36% | 0 | 0 | — |
case-22 | pass→pass | 7,374 | 8,412 | +14% | 1 | 1 | 0% | 1,401 | 2,016 | +44% | 0 | 0 | — |
case-23 | pass→pass | 4,888 | 4,982 | +2% | 1 | 1 | 0% | 861 | 1,271 | +48% | 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. The headline lift of +83 percentage points is the difference between those two pass rates over the 23 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.