Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Deprecated — forwards to bmad-project-context. Use when the user says "generate project context" or "create project context"
.claude/skills/bmad-code-org-bmad-generate-project-context/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -28% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -81% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -58% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -63% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -81% | 0% |
Tell the user: this skill is deprecated — bmad-project-context now owns this job. Instead of one generated project-context.md, it writes a small verified block inside the repo's AGENTS.md, and any existing project-context.md is offered up for absorption rather than left orphaned. Invoke bmad-project-context next time.
Then invoke bmad-project-context with setup intent, forwarding the user's original request and any inputs they supplied (architecture doc, spec, standards, preferences), verbatim. It takes the workflow from here.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 20,217 | 3,420 | -83% | 1 | 1 | 0% | 881 | 636 | -28% | 0 | 0 | — |
case-02 | fail→pass | 20,121 | 9,916 | -51% | 1 | 1 | 0% | 3,042 | 593 | -81% | 0 | 0 | — |
case-03 | fail→pass | 13,170 | 9,449 | -28% | 1 | 1 | 0% | 2,169 | 901 | -58% | 0 | 0 | — |
case-04 | fail→pass | 25,974 | 5,798 | -78% | 1 | 1 | 0% | 2,873 | 1,068 | -63% | 0 | 0 | — |
case-05 | fail→pass | 23,917 | 3,917 | -84% | 1 | 1 | 0% | 2,962 | 550 | -81% | 0 | 0 | — |
case-06 | fail→pass | 33,903 | 3,429 | -90% | 1 | 1 | 0% | 3,303 | 658 | -80% | 0 | 0 | — |
case-07 | fail→pass | 15,505 | 3,669 | -76% | 1 | 1 | 0% | 2,772 | 690 | -75% | 0 | 0 | — |
case-08 | fail→pass | 5,598 | 3,943 | -30% | 1 | 1 | 0% | 765 | 723 | -5% | 0 | 0 | — |
case-09 | fail→pass | 17,369 | 4,273 | -75% | 1 | 1 | 0% | 2,945 | 687 | -77% | 0 | 0 | — |
case-10 | fail→pass | 40,575 | 3,464 | -91% | 1 | 1 | 0% | 1,739 | 638 | -63% | 0 | 0 | — |
case-11 | fail→pass | 17,730 | 4,269 | -76% | 1 | 1 | 0% | 3,063 | 717 | -77% | 0 | 0 | — |
case-12 | fail→pass | 12,223 | 3,616 | -70% | 1 | 1 | 0% | 1,841 | 660 | -64% | 0 | 0 | — |
case-13 | fail→pass | 14,902 | 9,466 | -36% | 1 | 1 | 0% | 2,869 | 620 | -78% | 0 | 0 | — |
case-14 | fail→pass | 21,526 | 3,597 | -83% | 1 | 1 | 0% | 3,517 | 640 | -82% | 0 | 0 | — |
case-15 | fail→pass | 23,452 | 4,296 | -82% | 1 | 1 | 0% | 3,418 | 645 | -81% | 0 | 0 | — |
case-16 | fail→pass | 16,243 | 4,373 | -73% | 1 | 1 | 0% | 2,410 | 561 | -77% | 0 | 0 | — |
case-17 | fail→pass | 43,542 | 6,558 | -85% | 1 | 1 | 0% | 2,980 | 681 | -77% | 0 | 0 | — |
case-18 | fail→pass | 24,889 | 3,915 | -84% | 1 | 1 | 0% | 3,770 | 621 | -84% | 0 | 0 | — |
case-19 | fail→pass | 19,302 | 4,689 | -76% | 1 | 1 | 0% | 2,942 | 611 | -79% | 0 | 0 | — |
case-20 | pass→fail | 8,682 | 14,774 | +70% | 1 | 1 | 0% | 1,316 | 958 | -27% | 0 | 0 | — |
case-21 | pass→fail | 13,620 | 34,502 | +153% | 1 | 1 | 0% | 1,596 | 1,236 | -23% | 0 | 0 | — |
case-22 | pass→fail | 18,508 | 3,054 | -83% | 1 | 1 | 0% | 2,017 | 558 | -72% | 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 +73 percentage points is the difference between those two pass rates over the 22 comparable cases. 3 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.