Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Read or update the Wework project space, current Issue, attachments, deliveries, members, or board items when a Wework project or Issue context is active.
.claude/skills/wecode-ai-wework-project-space/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -50% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -63% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -44% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -44% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -63% | 0% |
Use the wework_space MCP tools for project-space work.
get_current_context before answering questions about the current Issue.get_board_item with that context before interpreting the Issue description.list_item_attachments and read_item_attachment to inspect Issue attachments.curl, scrape the browser, or parse wegent:// attachment URLs.wework_space reports an offline, authorization, or capability error.wework_space call returns an error.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 3,220 | 5,532 | +72% | 1 | 1 | 0% | 355 | 507 | +43% | 0 | 0 | — |
case-02 | fail→fail | 4,160 | 4,090 | -2% | 1 | 1 | 0% | 557 | 348 | -38% | 0 | 0 | — |
case-03 | fail→fail | 4,268 | 4,579 | +7% | 1 | 1 | 0% | 521 | 453 | -13% | 0 | 0 | — |
case-04 | fail→pass | 9,235 | 3,391 | -63% | 1 | 1 | 0% | 1,410 | 707 | -50% | 0 | 0 | — |
case-05 | fail→fail | 13,892 | 12,578 | -9% | 1 | 1 | 0% | 2,144 | 781 | -64% | 0 | 0 | — |
case-06 | fail→pass | 16,788 | 5,121 | -69% | 1 | 1 | 0% | 2,685 | 991 | -63% | 0 | 0 | — |
case-07 | fail→pass | 12,991 | 9,411 | -28% | 1 | 1 | 0% | 1,671 | 937 | -44% | 0 | 0 | — |
case-08 | pass→pass | 15,804 | 5,821 | -63% | 1 | 1 | 0% | 2,124 | 1,054 | -50% | 0 | 0 | — |
case-09 | pass→pass | 6,185 | 3,366 | -46% | 1 | 1 | 0% | 804 | 633 | -21% | 0 | 0 | — |
case-10 | fail→pass | 10,189 | 3,295 | -68% | 1 | 1 | 0% | 1,130 | 635 | -44% | 0 | 0 | — |
case-11 | fail→pass | 44,080 | 3,245 | -93% | 1 | 1 | 0% | 1,638 | 600 | -63% | 0 | 0 | — |
case-12 | fail→fail | 14,078 | 6,280 | -55% | 1 | 1 | 0% | 1,536 | 621 | -60% | 0 | 0 | — |
case-13 | fail→pass | 19,877 | 12,858 | -35% | 1 | 1 | 0% | 883 | 770 | -13% | 0 | 0 | — |
case-14 | pass→pass | 8,460 | 4,508 | -47% | 1 | 1 | 0% | 1,203 | 857 | -29% | 0 | 0 | — |
case-15 | fail→pass | 8,815 | 3,561 | -60% | 1 | 1 | 0% | 1,182 | 767 | -35% | 0 | 0 | — |
case-16 | fail→pass | 8,580 | 4,536 | -47% | 1 | 1 | 0% | 1,105 | 632 | -43% | 0 | 0 | — |
case-17 | fail→pass | 14,896 | 5,029 | -66% | 1 | 1 | 0% | 2,191 | 861 | -61% | 0 | 0 | — |
case-18 | pass→pass | 27,230 | 7,193 | -74% | 1 | 1 | 0% | 1,337 | 1,047 | -22% | 0 | 0 | — |
case-19 | fail→pass | 17,001 | 13,292 | -22% | 1 | 1 | 0% | 2,148 | 1,054 | -51% | 0 | 0 | — |
case-20 | pass→fail | 12,230 | 10,849 | -11% | 1 | 1 | 0% | 1,948 | 538 | -72% | 0 | 0 | — |
case-21 | pass→pass | 15,271 | 15,468 | +1% | 1 | 1 | 0% | 1,739 | 2,206 | +27% | 0 | 0 | — |
case-22 | pass→fail | 20,360 | 5,672 | -72% | 1 | 1 | 0% | 2,861 | 423 | -85% | 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, and 15 counted toward the lift figure. The other 7 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 +36 percentage points is the difference between those two pass rates over the 15 comparable cases. 6 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.