output-build-workflow
Implement an Output SDK workflow from a plan document. Use when the user asks to build, implement, or code a workflow from an…
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 Code
$ npx -y skills add growthxai/output --skill output-workflow-runs-list --agent claude-code
Codex
$ npx skills add growthxai/output --skill output-workflow-runs-list -a codex -y
Cursor
$ npx skills add growthxai/output --skill output-workflow-runs-list -a cursor -y
Gemini CLI
$ npx skills add growthxai/output --skill output-workflow-runs-list -a gemini-cli -y
GitHub Copilot
$ npx skills add growthxai/output --skill output-workflow-runs-list -a github-copilot -y
OpenCode
$ npx skills add growthxai/output --skill output-workflow-runs-list -a opencode -y
Windsurf
$ npx skills add growthxai/output --skill output-workflow-runs-list -a windsurf -y
name: output-workflow-runs-list description: 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. allowed-tools: [Bash]
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.
npx 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 |
npx output workflow runs list <workflowName>
This shows only runs for the specified workflow type.
npx 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
# 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
# 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
# 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
# Get all recent runs as JSON for external analysis npx output workflow runs list --json > workflow-runs.json
**Scenario**: Find when failures started
# 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})'1. **Multiple FAILED runs**: Indicates a persistent bug 2. **Mix of COMPLETED and FAILED**: Could be input-dependent issues 3. **All recent runs TERMINATED**: Someone may be stopping workflows 4. **Long RUNNING times**: Possible hang or performance issue
1. Copy the workflow ID from the run 2. Get the execution trace: `npx output workflow debug <workflowId> --json` 3. Analyze the trace to identify the failure 4. Apply the appropriate fix based on the error pattern
The open-source TypeScript framework for building AI workflows and agents. Designed for Claude Code — describe what you want, Claude builds it, with all the best practices already in place. One framework.
Implement an Output SDK workflow from a plan document. Use when the user asks to build, implement, or code a workflow from an…
View, edit, and set encrypted credentials in an Output.ai project. Use when adding secrets, updating API keys, verifying…
Wire encrypted credentials to environment variables using the credential: convention. Use when setting up LLM provider keys…
Initialize encrypted credentials for an Output.ai project. Use when setting up credentials for the first time, adding…
Debug Output SDK workflow issues. Use when user reports a workflow failing, erroring, hanging, producing wrong results, or asks…
Use the Agent class for multi-step tool loops, conversation history, streaming progress, and reusable LLM agents. Use when…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.