Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Configures 2-Agent workflow between PM and implementation roles. Use when user mentions 2-Agent, 2エージェント, PM連携設定, Cursor設定, Cursor連携, 2-agent運用. Do NOT load for: 単独運用, ワークフロー実行, ハンドオフ処理.
.claude/skills/aiskillstore-2agent/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | -62% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -86% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -63% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -73% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -75% | 0% |
2-Agent ワークフローの設定を担当するスキル群です。
| スキル | 用途 | |--------|------| | setup-2agent-files | 2-Agent 運用用ファイル設定 | | update-2agent-files | 2-Agent ファイルの更新 | | setup-cursor | Cursor 連携セットアップ |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | fail→pass | 12,644 | 7,445 | -41% | 1 | 1 | 0% | 1,191 | 453 | -62% | 0 | 0 | — |
case-01 | fail→fail | 24,574 | 7,184 | -71% | 1 | 1 | 0% | 3,581 | 450 | -87% | 0 | 0 | — |
case-03 | fail→pass | 16,859 | 13,645 | -19% | 1 | 1 | 0% | 2,714 | 387 | -86% | 0 | 0 | — |
case-04 | fail→fail | 14,884 | 21,450 | +44% | 1 | 1 | 0% | 2,712 | 1,289 | -52% | 0 | 0 | — |
case-05 | fail→pass | 16,482 | 8,231 | -50% | 1 | 1 | 0% | 1,793 | 656 | -63% | 0 | 0 | — |
case-06 | fail→pass | 27,848 | 10,015 | -64% | 1 | 1 | 0% | 3,467 | 947 | -73% | 0 | 0 | — |
case-07 | fail→pass | 17,363 | 7,216 | -58% | 1 | 1 | 0% | 1,840 | 463 | -75% | 0 | 0 | — |
case-08 | fail→pass | 13,955 | 9,315 | -33% | 1 | 1 | 0% | 1,898 | 673 | -65% | 0 | 0 | — |
case-09 | fail→pass | 10,973 | 6,847 | -38% | 1 | 1 | 0% | 1,856 | 392 | -79% | 0 | 0 | — |
case-10 | fail→pass | 14,685 | 6,801 | -54% | 1 | 1 | 0% | 1,547 | 469 | -70% | 0 | 0 | — |
case-11 | fail→pass | 15,486 | 6,664 | -57% | 1 | 1 | 0% | 1,548 | 384 | -75% | 0 | 0 | — |
case-12 | fail→pass | 14,221 | 6,707 | -53% | 1 | 1 | 0% | 1,486 | 429 | -71% | 0 | 0 | — |
case-13 | fail→fail | 7,145 | 17,030 | +138% | 1 | 1 | 0% | 1,126 | 2,041 | +81% | 0 | 0 | — |
case-14 | fail→fail | 23,059 | 16,189 | -30% | 1 | 1 | 0% | 2,962 | 457 | -85% | 0 | 0 | — |
case-15 | pass→pass | 18,474 | 17,511 | -5% | 1 | 1 | 0% | 2,485 | 2,414 | -3% | 0 | 0 | — |
case-16 | pass→pass | 22,127 | 17,625 | -20% | 1 | 1 | 0% | 3,089 | 2,439 | -21% | 0 | 0 | — |
case-17 | pass→pass | 14,690 | 16,544 | +13% | 1 | 1 | 0% | 1,970 | 2,068 | +5% | 0 | 0 | — |
case-18 | fail→pass | 18,989 | 9,274 | -51% | 1 | 1 | 0% | 2,262 | 890 | -61% | 0 | 0 | — |
case-19 | pass→pass | 12,298 | 6,776 | -45% | 1 | 1 | 0% | 1,079 | 363 | -66% | 0 | 0 | — |
case-20 | pass→pass | 18,722 | 8,940 | -52% | 1 | 1 | 0% | 2,056 | 739 | -64% | 0 | 0 | — |
case-21 | pass→pass | 11,242 | 8,563 | -24% | 1 | 1 | 0% | 1,732 | 699 | -60% | 0 | 0 | — |
case-22 | fail→pass | 17,356 | 7,553 | -56% | 1 | 1 | 0% | 1,907 | 565 | -70% | 0 | 0 | — |
case-23 | fail→pass | 20,631 | 8,066 | -61% | 1 | 1 | 0% | 2,854 | 653 | -77% | 0 | 0 | — |
case-24 | fail→pass | 20,188 | 8,292 | -59% | 1 | 1 | 0% | 2,407 | 554 | -77% | 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. 24 cases were attempted, and 23 counted toward the lift figure. The other 1 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 +58 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.