Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Visual task management dashboard. Terminal-based kanban board, tiled agent status view, and progress tracking. Shows all agents, their current tasks, budget consumption, and overall workspace health at a glance. Triggers on: "board", "dashboard", "kanban", "status board", "show agents"
.claude/skills/miosa-osa-board/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | 53% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 66% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -39% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 130% | 0% |
> Visual task management — kanban board, agent status, progress dashboard.
The command center for multi-agent workspaces. Renders a terminal-based view of all active work: who's doing what, what's blocked, what's done, and how much budget remains. Three view modes: kanban (task-centric), agents (agent-centric), and summary (metrics-centric). Designed for the orchestrator to maintain situational awareness.
bash# Default kanban view /board # Agent-centric view /board agents # Summary metrics view /board summary # Filter by status /board --status in_progress # Filter by agent /board --agent researcher # Watch mode (auto-refresh) /board --watch # Compact view (fits small terminals) /board --compact
| Subcommand | Description | |------------|-------------| | (default) | Kanban board view | | agents | Agent-centric tiled view | | summary | Metrics dashboard |
| Flag | Type | Default | Description | |------|------|---------|-------------| | --status | enum] | all | Filter: backlog, ready, in_progress, blocked, done | | --agent | string | all | Filter to specific agent | | --watch | flag | false | Auto-refresh every 5 seconds | | --compact | flag | false | Condensed view for small terminals | | --since | duration | 24h | Time window for completed tasks | | --show-budget | flag | true | Show budget consumption bars | | --show-timeline | flag | false | Show task timeline (Gantt-style) |
--watch, clear and re-render every 5 seconds. Highlight changes since last refresh.╔═══════════════════════════════════════════════════════════════════════════╗
║ WORKSPACE BOARD ║
║ Agents: 4 active | Tasks: 12 total | Budget: 67% remaining ║
╠═══════════════╦═══════════════╦═══════════════╦═══════════════════════════╣
║ BACKLOG (3) ║ IN PROGRESS(4)║ BLOCKED (1) ║ DONE (4) ║
╠═══════════════╬═══════════════╬═══════════════╬═══════════════════════════╣
║ Write docs ║ ▶ Pricing ║ ⚠ Revenue ║ ✓ Competitor scan ║
║ low ║ researcher ║ analyst ║ researcher 12m ║
║ ║ 18m elapsed ║ waiting on ║ ║
║ Update tests ║ ║ task-d4e5 ║ ✓ Draft pitch v1 ║
║ normal ║ ▶ Refactor ║ ║ writer 34m ║
║ ║ coder ║ ║ ║
║ Design review ║ 6m elapsed ║ ║ ✓ Search endpoint ║
║ low ║ ║ ║ coder 22m ║
║ ║ ▶ Pitch draft ║ ║ ║
║ ║ writer ║ ║ ✓ Market analysis ║
║ ║ 2m elapsed ║ ║ analyst 45m ║
╚═══════════════╩═══════════════╩═══════════════╩═══════════════════════════╝markdown## Agents ### researcher (agent-a1b2) — healthy - **Task:** Pricing benchmark analysis (18m elapsed) - **Budget:** ████████░░ 23,400/50,000 (47%) - **Completed today:** 2 tasks ### writer (agent-c3d4) — healthy - **Task:** Pitch deck draft v2 (2m elapsed) - **Budget:** ███░░░░░░░ 11,200/30,000 (37%) - **Completed today:** 1 task ### analyst (agent-e5f6) — STALLED - **Task:** Revenue report (blocked on task-d4e5) - **Budget:** █████████░ 45,100/50,000 (90%) - **Alert:** No heartbeat for 4m 12s ### coder (agent-g7h8) — idle - **Task:** — - **Budget:** ░░░░░░░░░░ 0/100,000 (0%) - **Available for work**
markdown## Workspace Summary | Metric | Value | Trend | |--------|-------|-------| | Active agents | 4 | — | | Tasks completed (24h) | 4 | +2 vs yesterday | | Tasks in progress | 4 | — | | Tasks blocked | 1 | new | | Total budget used | 79,700 / 230,000 | 35% | | Avg task duration | 28m | -5m vs yesterday | | Throughput | 1.2 tasks/hr | +0.3 |
/heartbeat — Agent health data/budget — Budget consumption data/checkout — Lock status| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-05 | fail→pass | 9,588 | 5,622 | -41% | 1 | 1 | 0% | 1,410 | 2,153 | +53% | 0 | 0 | — |
case-15 | fail→pass | 14,706 | 6,135 | -58% | 1 | 1 | 0% | 2,385 | 2,324 | -3% | 0 | 0 | — |
case-01 | fail→fail | 10,157 | 4,768 | -53% | 1 | 1 | 0% | 1,651 | 2,114 | +28% | 0 | 0 | — |
case-02 | fail→pass | 15,669 | 16,876 | +8% | 1 | 1 | 0% | 2,658 | 4,420 | +66% | 0 | 0 | — |
case-03 | fail→pass | 21,698 | 4,249 | -80% | 1 | 1 | 0% | 3,140 | 1,929 | -39% | 0 | 0 | — |
case-04 | fail→pass | 21,236 | 54,944 | +159% | 1 | 1 | 0% | 3,967 | 9,108 | +130% | 0 | 0 | — |
case-06 | fail→pass | 6,823 | 4,174 | -39% | 1 | 1 | 0% | 1,075 | 2,054 | +91% | 0 | 0 | — |
case-07 | fail→pass | 9,531 | 8,037 | -16% | 1 | 1 | 0% | 1,365 | 2,511 | +84% | 0 | 0 | — |
case-08 | fail→fail | 7,678 | 3,376 | -56% | 1 | 1 | 0% | 795 | 1,977 | +149% | 0 | 0 | — |
case-09 | fail→pass | 9,715 | 5,504 | -43% | 1 | 1 | 0% | 1,394 | 2,263 | +62% | 0 | 0 | — |
case-10 | fail→pass | 8,975 | 9,538 | +6% | 1 | 1 | 0% | 1,344 | 2,908 | +116% | 0 | 0 | — |
case-11 | fail→pass | 38,767 | 15,582 | -60% | 1 | 1 | 0% | 8,209 | 4,470 | -46% | 0 | 0 | — |
case-12 | fail→pass | 10,054 | 4,956 | -51% | 1 | 1 | 0% | 1,868 | 2,284 | +22% | 0 | 0 | — |
case-13 | fail→pass | 8,359 | 6,055 | -28% | 1 | 1 | 0% | 1,394 | 2,378 | +71% | 0 | 0 | — |
case-14 | fail→pass | 12,839 | 4,141 | -68% | 1 | 1 | 0% | 2,162 | 2,031 | -6% | 0 | 0 | — |
case-16 | fail→fail | 5,512 | 4,130 | -25% | 1 | 1 | 0% | 832 | 2,053 | +147% | 0 | 0 | — |
case-17 | fail→pass | 19,461 | 11,714 | -40% | 1 | 1 | 0% | 3,600 | 3,527 | -2% | 0 | 0 | — |
case-18 | fail→pass | 16,408 | 3,990 | -76% | 1 | 1 | 0% | 3,130 | 1,972 | -37% | 0 | 0 | — |
case-19 | pass→pass | 15,479 | 10,386 | -33% | 1 | 1 | 0% | 2,740 | 3,320 | +21% | 0 | 0 | — |
case-20 | fail→pass | 19,613 | 13,134 | -33% | 1 | 1 | 0% | 3,151 | 3,676 | +17% | 0 | 0 | — |
case-21 | pass→pass | 8,758 | 7,968 | -9% | 1 | 1 | 0% | 1,402 | 2,756 | +97% | 0 | 0 | — |
case-22 | pass→pass | 3,258 | 4,502 | +38% | 1 | 1 | 0% | 550 | 2,150 | +291% | 0 | 0 | — |
case-23 | pass→pass | 5,501 | 7,022 | +28% | 1 | 1 | 0% | 860 | 2,635 | +206% | 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. 23 cases were attempted, and 22 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 +70 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.