Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use this skill to break down complex, multi-stage projects into sequential micro-goals that persist across sessions. It prevents state loss and ensures only the current active goal can be executed, verified, or updated.
.claude/skills/bilal140202-joonghyun-lee-frieren-oh-my-antigravity/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -12% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -13% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -35% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -35% | 0% |
Use this skill to break down complex, multi-stage projects into sequential micro-goals that persist across sessions. It prevents state loss and ensures only the current active goal can be executed, verified, or updated.
.omg/ultragoal/brief.md containing the overall mission and constraints..omg/ultragoal/goals.json mapping goals to statuses (todo, in-progress, completed, blocked, failed)..omg/ultragoal/ledger.jsonl to log transition records, timestamps, and verification evidence.todo goal and set its status to in-progress.in-progress goal is marked completed with clear validation evidence./oma:goal or /oma:team command using the --intent pin pattern for the current active goal.markdown## Active Goal - ID: ... - Intent: ... ## Progress Overview - Completed: X / Y goals - Active: [Goal Description] ## Goal Registry | ID | Goal | Status | Verification Criteria | Evidence / Blockers | | --- | --- | --- | --- | --- | | ... | ... | ... | ... | ... | ## Handoff Directive - Command: `/oma:goal "..."`
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 8,525 | 6,838 | -20% | 1 | 1 | 0% | 1,626 | 1,852 | +14% | 0 | 0 | — |
case-02 | fail→pass | 15,296 | 10,411 | -32% | 1 | 1 | 0% | 3,080 | 2,708 | -12% | 0 | 0 | — |
case-03 | fail→pass | 10,621 | 6,808 | -36% | 1 | 1 | 0% | 2,090 | 1,815 | -13% | 0 | 0 | — |
case-04 | fail→fail | 21,331 | 12,597 | -41% | 1 | 1 | 0% | 4,002 | 3,407 | -15% | 0 | 0 | — |
case-05 | fail→fail | 15,746 | 8,149 | -48% | 1 | 1 | 0% | 3,445 | 2,130 | -38% | 0 | 0 | — |
case-06 | fail→pass | 13,400 | 6,884 | -49% | 1 | 1 | 0% | 2,861 | 1,868 | -35% | 0 | 0 | — |
case-07 | fail→pass | 20,936 | 9,374 | -55% | 1 | 1 | 0% | 4,102 | 2,684 | -35% | 0 | 0 | — |
case-08 | fail→pass | 18,902 | 9,141 | -52% | 1 | 1 | 0% | 3,343 | 2,359 | -29% | 0 | 0 | — |
case-09 | fail→fail | 15,020 | 7,190 | -52% | 1 | 1 | 0% | 2,544 | 2,037 | -20% | 0 | 0 | — |
case-10 | fail→pass | 7,565 | 7,050 | -7% | 1 | 1 | 0% | 1,254 | 1,917 | +53% | 0 | 0 | — |
case-11 | fail→pass | 12,986 | 6,401 | -51% | 1 | 1 | 0% | 2,319 | 1,783 | -23% | 0 | 0 | — |
case-12 | fail→pass | 15,620 | 7,835 | -50% | 1 | 1 | 0% | 2,817 | 2,148 | -24% | 0 | 0 | — |
case-13 | fail→pass | 16,691 | 8,159 | -51% | 1 | 1 | 0% | 3,251 | 2,221 | -32% | 0 | 0 | — |
case-14 | pass→pass | 13,108 | 7,636 | -42% | 1 | 1 | 0% | 2,288 | 1,908 | -17% | 0 | 0 | — |
case-15 | pass→pass | 13,209 | 5,623 | -57% | 1 | 1 | 0% | 2,384 | 1,677 | -30% | 0 | 0 | — |
case-16 | fail→pass | 15,837 | 7,425 | -53% | 1 | 1 | 0% | 2,804 | 1,870 | -33% | 0 | 0 | — |
case-17 | fail→fail | 18,922 | 9,048 | -52% | 1 | 1 | 0% | 3,230 | 2,275 | -30% | 0 | 0 | — |
case-18 | fail→pass | 15,934 | 7,982 | -50% | 1 | 1 | 0% | 2,730 | 2,016 | -26% | 0 | 0 | — |
case-19 | pass→pass | 16,072 | 8,812 | -45% | 1 | 1 | 0% | 2,790 | 2,096 | -25% | 0 | 0 | — |
case-20 | fail→pass | 18,904 | 5,559 | -71% | 1 | 1 | 0% | 3,109 | 1,534 | -51% | 0 | 0 | — |
case-21 | fail→fail | 19,224 | 8,174 | -57% | 1 | 1 | 0% | 3,289 | 1,963 | -40% | 0 | 0 | — |
case-22 | pass→fail | 2,874 | 5,580 | +94% | 1 | 1 | 0% | 372 | 1,478 | +297% | 0 | 0 | — |
case-23 | pass→pass | 7,365 | 4,439 | -40% | 1 | 1 | 0% | 1,295 | 1,175 | -9% | 0 | 0 | — |
case-24 | pass→pass | 7,838 | 4,398 | -44% | 1 | 1 | 0% | 1,656 | 1,285 | -22% | 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. The headline lift of +50 percentage points is the difference between those two pass rates over the 24 comparable cases. 1 case got worse with the skill loaded, and it is 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.