Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →List Output SDK workflow execution history. Use when finding failed runs, reviewing past executions, identifying workflow IDs for debugging, filtering runs by workflow type, or investigating recent workflow activity.
.claude/skills/growthxai-output-workflow-runs-list/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -5% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -39% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -34% | 0% |
This skill helps you view the execution history of workflows. Use it to find failed runs, identify workflow IDs for debugging, and review past executions.
bashnpx output workflow runs list
By default, this shows the 100 most recent workflow executions across all workflow types.
| Flag | Description | Default | |------|-------------|---------| | --limit <n> | Number of runs to display | 100 | | --format <type> | Output format: table, text | table | | --json | Output machine-readable JSON | false |
bashnpx output workflow runs list <workflowName>
This shows only runs for the specified workflow type.
bashnpx output workflow runs list --json
Use JSON format for programmatic analysis or when you need full details.
| Status | Meaning | Action | |--------|---------|--------| | RUNNING | Workflow is currently executing | Wait or monitor | | COMPLETED | Workflow finished successfully | No action needed | | FAILED | Workflow encountered an error | Debug with trace | | TERMINATED | Workflow was manually stopped | Review if expected | | TIMED_OUT | Workflow exceeded time limit | Check for long operations |
When viewing runs, pay attention to:
Scenario: Find failed workflow runs
bash# List recent runs and look for FAILED status npx output workflow runs list --limit 20 # Or use JSON format with jq to filter npx output workflow runs list --json | jq '.[] | select(.status == "FAILED")'
Scenario: Get workflow ID for debugging
bash# List runs for a specific workflow npx output workflow runs list my-workflow --limit 5 # Note the workflow ID from the output (e.g., "abc123xyz") # Then debug it npx output workflow debug abc123xyz --json
Scenario: Review recent activity for a specific workflow
bash# See the last 10 runs of the data-pipeline workflow npx output workflow runs list data-pipeline --limit 10
Scenario: Export run history for analysis
bash# Get all recent runs as JSON for external analysis npx output workflow runs list --json > workflow-runs.json
Scenario: Find when failures started
bash# Look at more history to find patterns npx output workflow runs list --limit 50 --json | jq 'group_by(.status) | map({status: .[0].status, count: length})'
npx output workflow debug <workflowId> --jsonnpx output workflow debug <id> - Analyze execution tracenpx output workflow status <id> - Check current statusnpx output workflow result <id> - Get execution resultnpx output workflow list - List available workflows| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 7,132 | 1,410 | -80% | 1 | 1 | 0% | 1,161 | 1,105 | -5% | 0 | 0 | — |
case-02 | fail→pass | 6,461 | 2,400 | -63% | 1 | 1 | 0% | 1,060 | 1,102 | +4% | 0 | 0 | — |
case-03 | fail→pass | 6,322 | 1,319 | -79% | 1 | 1 | 0% | 984 | 1,066 | +8% | 0 | 0 | — |
case-13 | pass→pass | 7,429 | 2,640 | -64% | 1 | 1 | 0% | 1,061 | 1,253 | +18% | 0 | 0 | — |
case-04 | pass→pass | 9,202 | 1,471 | -84% | 1 | 1 | 0% | 1,505 | 1,126 | -25% | 0 | 0 | — |
case-05 | fail→pass | 11,865 | 2,007 | -83% | 1 | 1 | 0% | 1,945 | 1,193 | -39% | 0 | 0 | — |
case-06 | fail→pass | 13,393 | 2,485 | -81% | 1 | 1 | 0% | 1,970 | 1,305 | -34% | 0 | 0 | — |
case-07 | fail→pass | 8,690 | 1,942 | -78% | 1 | 1 | 0% | 1,284 | 1,268 | -1% | 0 | 0 | — |
case-08 | fail→pass | 5,745 | 2,009 | -65% | 1 | 1 | 0% | 875 | 1,210 | +38% | 0 | 0 | — |
case-09 | fail→pass | 12,888 | 2,151 | -83% | 1 | 1 | 0% | 2,129 | 1,243 | -42% | 0 | 0 | — |
case-10 | fail→pass | 8,990 | 2,962 | -67% | 1 | 1 | 0% | 1,442 | 1,385 | -4% | 0 | 0 | — |
case-11 | fail→pass | 10,352 | 2,354 | -77% | 1 | 1 | 0% | 1,536 | 1,264 | -18% | 0 | 0 | — |
case-12 | fail→pass | 20,141 | 1,372 | -93% | 1 | 1 | 0% | 3,187 | 1,091 | -66% | 0 | 0 | — |
case-14 | pass→pass | 8,801 | 1,656 | -81% | 1 | 1 | 0% | 1,238 | 1,140 | -8% | 0 | 0 | — |
case-15 | fail→pass | 12,541 | 1,985 | -84% | 1 | 1 | 0% | 1,987 | 1,229 | -38% | 0 | 0 | — |
case-16 | fail→pass | 12,465 | 4,031 | -68% | 1 | 1 | 0% | 2,006 | 1,628 | -19% | 0 | 0 | — |
case-17 | pass→pass | 8,804 | 1,542 | -82% | 1 | 1 | 0% | 1,233 | 1,139 | -8% | 0 | 0 | — |
case-18 | pass→pass | 9,697 | 1,887 | -81% | 1 | 1 | 0% | 1,366 | 1,201 | -12% | 0 | 0 | — |
case-19 | fail→pass | 9,477 | 2,246 | -76% | 1 | 1 | 0% | 1,557 | 1,250 | -20% | 0 | 0 | — |
case-20 | fail→pass | 11,675 | 3,048 | -74% | 1 | 1 | 0% | 1,801 | 1,427 | -21% | 0 | 0 | — |
case-21 | fail→pass | 8,611 | 2,661 | -69% | 1 | 1 | 0% | 1,390 | 1,300 | -6% | 0 | 0 | — |
case-22 | fail→pass | 17,384 | 2,063 | -88% | 1 | 1 | 0% | 2,888 | 1,221 | -58% | 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 +77 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.