Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →You are an expert team communication specialist focused on async-first standup practices, AI-assisted note generation from commit history, and effective remote team coordination patterns.
.claude/skills/dokhacgiakhoa-team-collaboration-standup-notes/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | 116% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -31% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 80% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | -8% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 15% | 0% |
You are an expert team communication specialist focused on async-first standup practices, AI-assisted note generation from commit history, and effective remote team coordination patterns.
Modern remote-first teams rely on async standup notes to maintain visibility, coordinate work, and identify blockers without synchronous meetings. This tool generates comprehensive daily standup notes by analyzing multiple data sources: Obsidian vault context, Jira tickets, Git commit history, and calendar events. It supports both traditional synchronous standups and async-first team communication patterns, automatically extracting accomplishments from commits and formatting them for maximum team visibility.
Arguments: $ARGUMENTS (optional)
Required MCP Integrations:
mcp-obsidian: Vault access for daily notes and project updatesatlassian: Jira ticket queries (graceful fallback if unavailable)resources/implementation-playbook.md.resources/implementation-playbook.md for detailed patterns and examples.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 10,508 | 19,363 | +84% | 1 | 1 | 0% | 865 | 2,681 | +210% | 0 | 0 | — |
case-02 | fail→fail | 5,297 | 11,509 | +117% | 1 | 1 | 0% | 825 | 2,179 | +164% | 0 | 0 | — |
case-03 | fail→fail | 13,162 | 10,659 | -19% | 1 | 1 | 0% | 1,402 | 2,113 | +51% | 0 | 0 | — |
case-04 | pass→pass | 11,517 | 13,806 | +20% | 1 | 1 | 0% | 1,887 | 1,738 | -8% | 0 | 0 | — |
case-05 | pass→pass | 15,791 | 20,970 | +33% | 1 | 1 | 0% | 2,555 | 2,936 | +15% | 0 | 0 | — |
case-06 | pass→pass | 18,614 | 18,985 | +2% | 1 | 1 | 0% | 2,374 | 2,724 | +15% | 0 | 0 | — |
case-07 | pass→pass | 13,526 | 22,053 | +63% | 1 | 1 | 0% | 1,355 | 1,741 | +28% | 0 | 0 | — |
case-08 | fail→fail | 5,260 | 13,669 | +160% | 1 | 1 | 0% | 835 | 1,628 | +95% | 0 | 0 | — |
case-09 | pass→pass | 13,229 | 8,689 | -34% | 1 | 1 | 0% | 1,383 | 1,719 | +24% | 0 | 0 | — |
case-10 | fail→fail | 6,941 | 5,918 | -15% | 1 | 1 | 0% | 273 | 1,343 | +392% | 0 | 0 | — |
case-11 | fail→pass | 4,345 | 12,839 | +195% | 1 | 1 | 0% | 739 | 1,594 | +116% | 0 | 0 | — |
case-12 | pass→pass | 9,095 | 6,633 | -27% | 1 | 1 | 0% | 612 | 1,422 | +132% | 0 | 0 | — |
case-13 | pass→pass | 4,512 | 11,345 | +151% | 1 | 1 | 0% | 814 | 1,430 | +76% | 0 | 0 | — |
case-14 | pass→pass | 16,946 | 12,256 | -28% | 1 | 1 | 0% | 2,031 | 2,241 | +10% | 0 | 0 | — |
case-15 | fail→pass | 25,416 | 21,916 | -14% | 1 | 1 | 0% | 4,867 | 3,351 | -31% | 0 | 0 | — |
case-16 | pass→pass | 8,484 | 12,084 | +42% | 1 | 1 | 0% | 1,379 | 1,492 | +8% | 0 | 0 | — |
case-17 | pass→pass | 13,236 | 16,872 | +27% | 1 | 1 | 0% | 2,107 | 2,396 | +14% | 0 | 0 | — |
case-18 | fail→pass | 6,213 | 13,196 | +112% | 1 | 1 | 0% | 957 | 1,727 | +80% | 0 | 0 | — |
case-19 | pass→pass | 4,681 | 11,680 | +150% | 1 | 1 | 0% | 783 | 1,364 | +74% | 0 | 0 | — |
case-20 | pass→pass | 12,336 | 12,200 | -1% | 1 | 1 | 0% | 1,150 | 1,505 | +31% | 0 | 0 | — |
case-21 | pass→pass | 8,366 | 14,571 | +74% | 1 | 1 | 0% | 1,294 | 1,893 | +46% | 0 | 0 | — |
case-22 | pass→pass | 15,473 | 9,161 | -41% | 1 | 1 | 0% | 1,655 | 1,820 | +10% | 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 +14 percentage points is the difference between those two pass rates over the 22 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.