@output.ai/cli 0.5.0 → 0.5.1

package/dist/templates/agent_instructions/AGENTS.md.template

@@ -40,17 +40,17 @@ src/workflows/{name}/
 ## Commands
 
 ```bash
-output dev                                      # Start dev (Temporal:8080, API:3001)
-output workflow list                            # List workflows
+npx output dev                                      # Start dev (Temporal:8080, API:3001)
+npx output workflow list                            # List workflows
 
 # Sync execution (waits for result)
-output workflow run <name> --input <JSON|JSON_FILE>      # Execute and wait
+npx output workflow run <name> --input <JSON|JSON_FILE>      # Execute and wait
 
 # Async execution
-output workflow start <name> --input <JSON|JSON_FILE>    # Start workflow, returns ID
-output workflow status <workflowId>             # Check execution status
-output workflow result <workflowId>             # Get result when complete
-output workflow stop <workflowId>               # Cancel running workflow
+npx output workflow start <name> --input <JSON|JSON_FILE>    # Start workflow, returns ID
+npx output workflow status <workflowId>             # Check execution status
+npx output workflow result <workflowId>             # Get result when complete
+npx output workflow stop <workflowId>               # Cancel running workflow
 ```
 
 ## Workflow Pattern

package/dist/templates/agent_instructions/agents/workflow_debugger.md.template

@@ -30,15 +30,15 @@ For detailed command usage, Claude will automatically invoke the relevant skill.
 
 | Command | Purpose |
 |---------|---------|
-| `output dev` | Start development services |
-| `output workflow list` | List available workflows |
-| `output workflow runs list` | List execution history |
-| `output workflow run` | Execute synchronously |
-| `output workflow start` | Start asynchronously |
-| `output workflow status` | Check execution status |
-| `output workflow result` | Get execution result |
-| `output workflow stop` | Stop running workflow |
-| `output workflow debug` | Analyze execution trace |
+| `npx output dev` | Start development services |
+| `npx output workflow list` | List available workflows |
+| `npx output workflow runs list` | List execution history |
+| `npx output workflow run` | Execute synchronously |
+| `npx output workflow start` | Start asynchronously |
+| `npx output workflow status` | Check execution status |
+| `npx output workflow result` | Get execution result |
+| `npx output workflow stop` | Stop running workflow |
+| `npx output workflow debug` | Analyze execution trace |
 
 ## Temporal UI
 
@@ -73,7 +73,7 @@ Match error symptoms to solutions and verify the fix.
 **Agent**: Let me help you debug this workflow. First, let's get the execution trace:
 
 ```bash
-output workflow debug abc123 --format json
+npx output workflow debug abc123 --format json
 ```
 
 This will show us exactly where the workflow failed and what error occurred. While I analyze the trace, you can also check the Temporal UI at http://localhost:8080 for a visual timeline of the execution.
@@ -92,7 +92,7 @@ To:
 import { z } from '@output.ai/core';
 ```
 
-After making this change, run the workflow again with `output workflow run <workflowName>` to verify the fix.
+After making this change, run the workflow again with `npx output workflow run <workflowName>` to verify the fix.
 
 ---
 *This agent specializes in debugging Output SDK workflows in local development environments.*

package/dist/templates/agent_instructions/commands/debug_workflow.md.template

@@ -47,7 +47,7 @@ curl -s http://localhost:8080 > /dev/null && echo "Temporal UI accessible" || ec
     RUN: docker compose up -d
     WAIT: for services to start (30-60 seconds)
   IF output_dev_not_running:
-    RUN: output dev
+    RUN: npx output dev
     WAIT: for services to initialize
   IF all_services_running:
     PROCEED: to step 2
@@ -69,16 +69,16 @@ Identify the failing workflow execution by listing recent runs. The `output-work
 <list_commands>
 ```bash
 # List all recent workflow runs
-output workflow runs list
+npx output workflow runs list
 
 # Filter by specific workflow type (if known)
-output workflow runs list <workflowName>
+npx output workflow runs list <workflowName>
 
 # Get detailed JSON output for analysis
-output workflow runs list --format json
+npx output workflow runs list --format json
 
 # Limit results to most recent
-output workflow runs list --limit 10
+npx output workflow runs list --limit 10
 ```
 </list_commands>
 
@@ -98,12 +98,12 @@ Look for:
     NOTE: workflow ID from output
     PROCEED: to step 3
   IF no_runs_found:
-    CHECK: workflow exists with `output workflow list`
+    CHECK: workflow exists with `npx output workflow list`
     IF workflow_not_found:
       REPORT: workflow doesn't exist
       SUGGEST: verify workflow name and location
     ELSE:
-      SUGGEST: run the workflow with `output workflow run <name>`
+      SUGGEST: run the workflow with `npx output workflow run <name>`
 </decision_tree>
 
 </step>
@@ -117,10 +117,10 @@ Retrieve and analyze the execution trace for the identified workflow. The `outpu
 <debug_commands>
 ```bash
 # Display execution trace (text format)
-output workflow debug <workflowId>
+npx output workflow debug <workflowId>
 
 # Display full untruncated trace (JSON format) - recommended for detailed analysis
-output workflow debug <workflowId> --format json
+npx output workflow debug <workflowId> --format json
 ```
 </debug_commands>
 
@@ -174,12 +174,12 @@ Based on the trace analysis, identify the error pattern and suggest targeted fix
 After applying fix:
 ```bash
 # Re-run the workflow to verify
-output workflow run <workflowName> <input>
+npx output workflow run <workflowName> <input>
 
 # Or start asynchronously and check result
-output workflow start <workflowName> <input>
-output workflow status <workflowId>
-output workflow result <workflowId>
+npx output workflow start <workflowName> <input>
+npx output workflow status <workflowId>
+npx output workflow result <workflowId>
 ```
 </verification>
 

package/dist/templates/agent_instructions/commands/plan_workflow.md.template

@@ -213,7 +213,7 @@ Design the testing strategy for the workflow.
 
 Generate the complete plan in markdown format.
 
-Note that every implementation should start with running the cli command `output workflow generate --skeleton` to create the workflow directory structure.
+Note that every implementation should start with running the cli command `npx output workflow generate --skeleton` to create the workflow directory structure.
 
 <file_template>
   <header>

package/dist/templates/agent_instructions/skills/output-error-direct-io/SKILL.md.template

@@ -230,8 +230,8 @@ Workflow functions should NOT contain:
 
 After moving I/O to steps:
 
-1. **Run the workflow**: `output workflow run <name> '<input>'`
-2. **Check the trace**: `output workflow debug <id> --format json`
+1. **Run the workflow**: `npx output workflow run <name> '<input>'`
+2. **Check the trace**: `npx output workflow debug <id> --format json`
 3. **Verify steps appear**: Look for your I/O steps in the trace
 4. **Confirm no errors**: No determinism warnings or hangs
 

package/dist/templates/agent_instructions/skills/output-error-http-client/SKILL.md.template

@@ -287,8 +287,8 @@ grep -rn "got\|node-fetch\|request\|superagent" src/
 
 After migrating to httpClient:
 
-1. **Run the workflow**: `output workflow run <name> '<input>'`
-2. **Check the trace**: `output workflow debug <id> --format json`
+1. **Run the workflow**: `npx output workflow run <name> '<input>'`
+2. **Check the trace**: `npx output workflow debug <id> --format json`
 3. **Verify tracing**: HTTP requests should appear in the step trace
 4. **Test retries**: Simulate failures to verify retry behavior
 

package/dist/templates/agent_instructions/skills/output-error-missing-schemas/SKILL.md.template

@@ -255,8 +255,8 @@ export const logEvent = step({
 
 After adding schemas:
 
-1. **TypeScript check**: `npm run build` should pass without type errors
-2. **Runtime test**: `output workflow run <name> '<input>'` should validate correctly
+1. **TypeScript check**: `npm run output:workflow:build` should pass without type errors
+2. **Runtime test**: `npx output workflow run <name> '<input>'` should validate correctly
 3. **Invalid input test**: Pass invalid data and verify validation errors appear
 
 ## Related Issues

package/dist/templates/agent_instructions/skills/output-error-nondeterminism/SKILL.md.template

@@ -216,7 +216,7 @@ Look at your workflow `fn` functions specifically. Non-deterministic code is onl
 ## Verification Steps
 
 1. **Fix the code** using solutions above
-2. **Run the workflow**: `output workflow run <name> '<input>'`
+2. **Run the workflow**: `npx output workflow run <name> '<input>'`
 3. **Run again with same input**: Result should be identical
 4. **Check for errors**: No "non-deterministic" messages
 
@@ -238,10 +238,10 @@ If unsure whether code is causing issues:
 
 ```bash
 # Run the workflow
-output workflow start my-workflow '{"input": "test"}'
+npx output workflow start my-workflow '{"input": "test"}'
 
 # Get the workflow ID and run debug to see replay behavior
-output workflow debug <workflowId> --format json
+npx output workflow debug <workflowId> --format json
 ```
 
 Look for errors or warnings about non-determinism in the trace.

package/dist/templates/agent_instructions/skills/output-error-try-catch/SKILL.md.template

@@ -216,9 +216,9 @@ Do NOT use FatalError to wrap other errors unless you're certain they shouldn't
 
 After removing try-catch:
 
-1. **Test normal operation**: `output workflow run <name> '<valid-input>'`
+1. **Test normal operation**: `npx output workflow run <name> '<valid-input>'`
 2. **Test failure scenarios**: Use input that causes step failures
-3. **Check retry behavior**: Look for retry attempts in `output workflow debug <id>`
+3. **Check retry behavior**: Look for retry attempts in `npx output workflow debug <id>`
 
 ## Related Issues
 

package/dist/templates/agent_instructions/skills/output-error-zod-import/SKILL.md.template

@@ -145,7 +145,7 @@ npm run build
 ### 3. Run the workflow
 
 ```bash
-output workflow run <workflowName> '<input>'
+npx output workflow run <workflowName> '<input>'
 ```
 
 ## Prevention

package/dist/templates/agent_instructions/skills/output-services-check/SKILL.md.template

@@ -55,7 +55,7 @@ curl -s http://localhost:8080 > /dev/null && echo "Temporal UI accessible" || ec
 ### If services are not running:
 ```bash
 # Start all development services
-output dev
+npx output dev
 ```
 
 Wait 30-60 seconds for all services to initialize, then re-run the checks.
@@ -80,7 +80,7 @@ IF docker_not_running:
   WAIT: for Docker to initialize
 
 IF no_output_containers:
-  RUN: output dev
+  RUN: npx output dev
   WAIT: 30-60 seconds for services
 
 IF api_not_responding:
@@ -105,7 +105,7 @@ docker ps | grep output
 # Output: (empty - no containers)
 
 # Start services
-output dev
+npx output dev
 
 # Wait and verify
 sleep 60

package/dist/templates/agent_instructions/skills/output-workflow-list/SKILL.md.template

@@ -23,7 +23,7 @@ This skill helps you discover all available workflows in an Output SDK project.
 ### List All Workflows
 
 ```bash
-output workflow list
+npx output workflow list
 ```
 
 This command scans the project and displays all available workflows.
@@ -67,7 +67,7 @@ ls -la src/workflows/<workflowName>/
 **Scenario**: Discover available workflows in a project
 
 ```bash
-output workflow list
+npx output workflow list
 
 # Example output:
 # Name          Description                    Location
@@ -81,18 +81,18 @@ output workflow list
 
 ```bash
 # Check if "email-sender" workflow exists
-output workflow list | grep email-sender
+npx output workflow list | grep email-sender
 
 # If no output, the workflow doesn't exist
 # If found, proceed with running it
-output workflow run email-sender '{"to": "user@example.com"}'
+npx output workflow run email-sender '{"to": "user@example.com"}'
 ```
 
 **Scenario**: Explore workflow implementation
 
 ```bash
 # List workflows
-output workflow list
+npx output workflow list
 
 # Find the location and examine it
 cat src/workflows/simple/workflow.ts
@@ -112,6 +112,6 @@ cat src/workflows/simple/workflow.ts
 
 ## Related Commands
 
-- `output workflow run <name>` - Execute a workflow synchronously
-- `output workflow start <name>` - Start a workflow asynchronously
-- `output workflow runs list` - View execution history
+- `npx output workflow run <name>` - Execute a workflow synchronously
+- `npx output workflow start <name>` - Start a workflow asynchronously
+- `npx output workflow runs list` - View execution history

package/dist/templates/agent_instructions/skills/output-workflow-result/SKILL.md.template

@@ -8,7 +8,7 @@ allowed-tools: [Bash]
 
 ## Overview
 
-This skill retrieves the result (return value) of a completed workflow execution. Use it after a workflow started with `output workflow start` has completed, or to retrieve results from historical runs.
+This skill retrieves the result (return value) of a completed workflow execution. Use it after a workflow started with `npx output workflow start` has completed, or to retrieve results from historical runs.
 
 ## When to Use This Skill
 
@@ -22,14 +22,14 @@ This skill retrieves the result (return value) of a completed workflow execution
 
 - The workflow must have completed (status: COMPLETED)
 - You need the workflow ID
-- For FAILED workflows, use `output workflow debug` instead
+- For FAILED workflows, use `npx output workflow debug` instead
 
 ## Instructions
 
 ### Get Result
 
 ```bash
-output workflow result <workflowId>
+npx output workflow result <workflowId>
 ```
 
 The result is the return value of the workflow function, typically JSON.
@@ -39,10 +39,10 @@ The result is the return value of the workflow function, typically JSON.
 Before getting results, verify the workflow completed:
 
 ```bash
-output workflow status <workflowId>
+npx output workflow status <workflowId>
 # Should show: COMPLETED
 
-output workflow result <workflowId>
+npx output workflow result <workflowId>
 ```
 
 ## Understanding Results
@@ -62,7 +62,7 @@ export default workflow({
 
 ```bash
 # Result output
-output workflow result abc123
+npx output workflow result abc123
 # { "processed": true, "count": 42 }
 ```
 
@@ -70,13 +70,13 @@ output workflow result abc123
 
 If you try to get the result of a failed workflow:
 - You'll get an error message
-- Use `output workflow debug` instead to see what went wrong
+- Use `npx output workflow debug` instead to see what went wrong
 
 ### No Result (void workflows)
 
 Some workflows don't return a value:
 ```bash
-output workflow result abc123
+npx output workflow result abc123
 # null
 ```
 
@@ -86,15 +86,15 @@ output workflow result abc123
 
 ```bash
 # Start workflow
-output workflow start calculate '{"values": [1, 2, 3]}'
+npx output workflow start calculate '{"values": [1, 2, 3]}'
 # Output: Workflow ID: calc-abc123
 
 # Wait for completion
-output workflow status calc-abc123
+npx output workflow status calc-abc123
 # Status: COMPLETED
 
 # Get the result
-output workflow result calc-abc123
+npx output workflow result calc-abc123
 # { "sum": 6, "average": 2 }
 ```
 
@@ -102,21 +102,21 @@ output workflow result calc-abc123
 
 ```bash
 # Extract specific field
-output workflow result abc123 | jq '.total'
+npx output workflow result abc123 | jq '.total'
 
 # Format for display
-output workflow result abc123 | jq '.'
+npx output workflow result abc123 | jq '.'
 
 # Save to file
-output workflow result abc123 > result.json
+npx output workflow result abc123 > result.json
 ```
 
 **Scenario**: Compare results between runs
 
 ```bash
 # Get results from two runs
-output workflow result run-1-abc > result1.json
-output workflow result run-2-xyz > result2.json
+npx output workflow result run-1-abc > result1.json
+npx output workflow result run-2-xyz > result2.json
 
 # Compare
 diff result1.json result2.json
@@ -128,17 +128,17 @@ diff result1.json result2.json
 WORKFLOW_ID="abc123"
 
 # Wait for completion
-while [[ $(output workflow status $WORKFLOW_ID) == *"RUNNING"* ]]; do
+while [[ $(npx output workflow status $WORKFLOW_ID) == *"RUNNING"* ]]; do
   sleep 5
 done
 
 # Check if completed successfully
-if [[ $(output workflow status $WORKFLOW_ID) == *"COMPLETED"* ]]; then
-  RESULT=$(output workflow result $WORKFLOW_ID)
+if [[ $(npx output workflow status $WORKFLOW_ID) == *"COMPLETED"* ]]; then
+  RESULT=$(npx output workflow result $WORKFLOW_ID)
   echo "Workflow result: $RESULT"
 else
   echo "Workflow did not complete successfully"
-  output workflow debug $WORKFLOW_ID
+  npx output workflow debug $WORKFLOW_ID
 fi
 ```
 
@@ -146,25 +146,25 @@ fi
 
 ### JSON Objects
 ```bash
-output workflow result abc123
+npx output workflow result abc123
 # { "key": "value", "nested": { "data": true } }
 ```
 
 ### Arrays
 ```bash
-output workflow result abc123
+npx output workflow result abc123
 # [1, 2, 3, 4, 5]
 ```
 
 ### Primitive Values
 ```bash
-output workflow result abc123
+npx output workflow result abc123
 # 42
 
-output workflow result abc123
+npx output workflow result abc123
 # "success"
 
-output workflow result abc123
+npx output workflow result abc123
 # true
 ```
 
@@ -172,20 +172,20 @@ output workflow result abc123
 
 For large results, redirect to a file:
 ```bash
-output workflow result abc123 > large-result.json
+npx output workflow result abc123 > large-result.json
 ```
 
 ## Error Handling
 
 ### "Workflow not found"
 - Check the workflow ID is correct
-- Use `output workflow runs list` to find valid IDs
+- Use `npx output workflow runs list` to find valid IDs
 
 ### "Workflow not completed"
-- Check status: `output workflow status <id>`
+- Check status: `npx output workflow status <id>`
 - Wait for COMPLETED status before getting result
 - If RUNNING, wait and try again
-- If FAILED, use `output workflow debug`
+- If FAILED, use `npx output workflow debug`
 
 ### "No result available"
 - The workflow may return void/undefined
@@ -193,7 +193,7 @@ output workflow result abc123 > large-result.json
 
 ## Related Commands
 
-- `output workflow status <id>` - Check if workflow completed
-- `output workflow debug <id>` - Debug failed workflows
-- `output workflow run <name>` - Run and get result in one step
-- `output workflow runs list` - Find workflow IDs
+- `npx output workflow status <id>` - Check if workflow completed
+- `npx output workflow debug <id>` - Debug failed workflows
+- `npx output workflow run <name>` - Run and get result in one step
+- `npx output workflow runs list` - Find workflow IDs

package/dist/templates/agent_instructions/skills/output-workflow-run/SKILL.md.template

@@ -20,7 +20,7 @@ This skill executes a workflow synchronously, meaning the command waits for the
 
 ## When to Use Async Instead
 
-Consider using `output workflow start` (async) when:
+Consider using `npx output workflow start` (async) when:
 - The workflow takes a long time (minutes to hours)
 - You need to run multiple workflows in parallel
 - You want to disconnect and check results later
@@ -31,8 +31,8 @@ Consider using `output workflow start` (async) when:
 ### Basic Syntax
 
 ```bash
-output workflow run <workflowName> --input '<json-input>'
-output workflow run <workflowName> --input <path-to-json-file>
+npx output workflow run <workflowName> --input '<json-input>'
+npx output workflow run <workflowName> --input <path-to-json-file>
 ```
 
 The `--input` flag is required when the workflow expects input data.
@@ -44,7 +44,7 @@ The `--input` flag is required when the workflow expects input data.
 Pass JSON directly on the command line:
 
 ```bash
-output workflow run example --input '{"question": "who really is ada lovelace?"}'
+npx output workflow run example --input '{"question": "who really is ada lovelace?"}'
 ```
 
 #### 2. File Path (Recommended)
@@ -52,7 +52,7 @@ output workflow run example --input '{"question": "who really is ada lovelace?"}
 Reference a JSON file containing the input:
 
 ```bash
-output workflow run simple --input src/simple/scenarios/question_ada_lovelace.json
+npx output workflow run simple --input src/simple/scenarios/question_ada_lovelace.json
 ```
 
 This is the recommended approach because:
@@ -96,26 +96,26 @@ src/
 
 3. Run the workflow referencing the scenario:
    ```bash
-   output workflow run my_workflow --input src/my_workflow/scenarios/test_user.json
+   npx output workflow run my_workflow --input src/my_workflow/scenarios/test_user.json
    ```
 
 ### Input Examples
 
 ```bash
 # Inline JSON - simple object
-output workflow run my-workflow --input '{"userId": "123"}'
+npx output workflow run my-workflow --input '{"userId": "123"}'
 
 # Inline JSON - complex nested input
-output workflow run data-pipeline --input '{"source": "api", "options": {"limit": 100}}'
+npx output workflow run data-pipeline --input '{"source": "api", "options": {"limit": 100}}'
 
 # File path - reference a scenario file
-output workflow run simple --input src/simple/scenarios/basic.json
+npx output workflow run simple --input src/simple/scenarios/basic.json
 
 # File path - relative to current directory
-output workflow run batch-processor --input ./test_inputs/batch1.json
+npx output workflow run batch-processor --input ./test_inputs/batch1.json
 
 # No input (only if workflow doesn't require it)
-output workflow run health-check
+npx output workflow run health-check
 ```
 
 ## Understanding the Output
@@ -129,7 +129,7 @@ The workflow's return value is displayed, typically as JSON.
 If the workflow fails, you'll see:
 - Error message
 - The workflow ID (for further debugging)
-- Suggestion to use `output workflow debug` for details
+- Suggestion to use `npx output workflow debug` for details
 
 ## Examples
 
@@ -140,7 +140,7 @@ If the workflow fails, you'll see:
 ls src/simple/scenarios/
 
 # Run using a scenario file
-output workflow run simple --input src/simple/scenarios/basic_sum.json
+npx output workflow run simple --input src/simple/scenarios/basic_sum.json
 
 # Output:
 # { "sum": 6, "count": 3 }
@@ -158,20 +158,20 @@ cat > src/my_workflow/scenarios/test_case_1.json << 'EOF'
 EOF
 
 # Run the workflow
-output workflow run my_workflow --input src/my_workflow/scenarios/test_case_1.json
+npx output workflow run my_workflow --input src/my_workflow/scenarios/test_case_1.json
 ```
 
 **Scenario**: Quick inline test during development
 
 ```bash
-output workflow run example --input '{"question": "explain quantum computing"}'
+npx output workflow run example --input '{"question": "explain quantum computing"}'
 ```
 
 **Scenario**: Re-run a workflow with different input for debugging
 
 ```bash
 # First attempt with scenario file
-output workflow run process-data --input src/process_data/scenarios/user_abc.json
+npx output workflow run process-data --input src/process_data/scenarios/user_abc.json
 # Error occurs
 
 # Create a new scenario to isolate the issue
@@ -179,17 +179,17 @@ cat > src/process_data/scenarios/debug_minimal.json << 'EOF'
 {"id": "test", "debug": true}
 EOF
 
-output workflow run process-data --input src/process_data/scenarios/debug_minimal.json
+npx output workflow run process-data --input src/process_data/scenarios/debug_minimal.json
 ```
 
 **Scenario**: Capture output for further processing
 
 ```bash
 # Save result to a file
-output workflow run generate-report --input src/generate_report/scenarios/jan_2024.json > report.json
+npx output workflow run generate-report --input src/generate_report/scenarios/jan_2024.json > report.json
 
 # Pipe to jq for processing
-output workflow run get-users --input src/get_users/scenarios/active.json | jq '.users[].name'
+npx output workflow run get-users --input src/get_users/scenarios/active.json | jq '.users[].name'
 ```
 
 ## Error Handling
@@ -198,7 +198,7 @@ output workflow run get-users --input src/get_users/scenarios/active.json | jq '
 
 | Error | Cause | Solution |
 |-------|-------|----------|
-| "Workflow not found" | Workflow name is incorrect | Check with `output workflow list` |
+| "Workflow not found" | Workflow name is incorrect | Check with `npx output workflow list` |
 | "Invalid input" | JSON doesn't match schema | Verify input matches workflow's inputSchema |
 | "Parse error" | Malformed JSON or file not found | Check JSON syntax or file path |
 | "Timeout" | Workflow took too long | Use async execution for long workflows |
@@ -208,10 +208,10 @@ output workflow run get-users --input src/get_users/scenarios/active.json | jq '
 When a workflow fails, the output includes the workflow ID. Use it to get the full trace:
 
 ```bash
-output workflow run my-workflow --input src/my_workflow/scenarios/test.json
+npx output workflow run my-workflow --input src/my_workflow/scenarios/test.json
 # Output: Workflow failed. ID: abc123xyz
 
-output workflow debug abc123xyz --format json
+npx output workflow debug abc123xyz --format json
 ```
 
 ## Input Schema Tips
@@ -223,6 +223,6 @@ output workflow debug abc123xyz --format json
 
 ## Related Commands
 
-- `output workflow start <name> --input` - Start asynchronously
-- `output workflow list` - See available workflows
-- `output workflow debug <id>` - Debug a failed run
+- `npx output workflow start <name> --input` - Start asynchronously
+- `npx output workflow list` - See available workflows
+- `npx output workflow debug <id>` - Debug a failed run

package/dist/templates/agent_instructions/skills/output-workflow-runs-list/SKILL.md.template

@@ -23,7 +23,7 @@ This skill helps you view the execution history of workflows. Use it to find fai
 ### List All Recent Runs
 
 ```bash
-output workflow runs list
+npx output workflow runs list
 ```
 
 By default, this shows the 100 most recent workflow executions across all workflow types.
@@ -38,7 +38,7 @@ By default, this shows the 100 most recent workflow executions across all workfl
 ### Filter by Workflow Name
 
 ```bash
-output workflow runs list <workflowName>
+npx output workflow runs list <workflowName>
 ```
 
 This shows only runs for the specified workflow type.
@@ -46,7 +46,7 @@ This shows only runs for the specified workflow type.
 ### Get Detailed JSON Output
 
 ```bash
-output workflow runs list --format json
+npx output workflow runs list --format json
 ```
 
 Use JSON format for programmatic analysis or when you need full details.
@@ -79,42 +79,42 @@ When viewing runs, pay attention to:
 
 ```bash
 # List recent runs and look for FAILED status
-output workflow runs list --limit 20
+npx output workflow runs list --limit 20
 
 # Or use JSON format with jq to filter
-output workflow runs list --format json | jq '.[] | select(.status == "FAILED")'
+npx output workflow runs list --format json | jq '.[] | select(.status == "FAILED")'
 ```
 
 **Scenario**: Get workflow ID for debugging
 
 ```bash
 # List runs for a specific workflow
-output workflow runs list my-workflow --limit 5
+npx output workflow runs list my-workflow --limit 5
 
 # Note the workflow ID from the output (e.g., "abc123xyz")
 # Then debug it
-output workflow debug abc123xyz --format json
+npx output workflow debug abc123xyz --format json
 ```
 
 **Scenario**: Review recent activity for a specific workflow
 
 ```bash
 # See the last 10 runs of the data-pipeline workflow
-output workflow runs list data-pipeline --limit 10
+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
-output workflow runs list --format json > workflow-runs.json
+npx output workflow runs list --format json > workflow-runs.json
 ```
 
 **Scenario**: Find when failures started
 
 ```bash
 # Look at more history to find patterns
-output workflow runs list --limit 50 --format json | jq 'group_by(.status) | map({status: .[0].status, count: length})'
+npx output workflow runs list --limit 50 --format json | jq 'group_by(.status) | map({status: .[0].status, count: length})'
 ```
 
 ## Identifying Problems
@@ -129,13 +129,13 @@ output workflow runs list --limit 50 --format json | jq 'group_by(.status) | map
 ### Next Steps After Finding a Failed Run
 
 1. Copy the workflow ID from the run
-2. Get the execution trace: `output workflow debug <workflowId> --format json`
+2. Get the execution trace: `npx output workflow debug <workflowId> --format json`
 3. Analyze the trace to identify the failure
 4. Apply the appropriate fix based on the error pattern
 
 ## Related Commands
 
-- `output workflow debug <id>` - Analyze execution trace
-- `output workflow status <id>` - Check current status
-- `output workflow result <id>` - Get execution result
-- `output workflow list` - List available workflows
+- `npx output workflow debug <id>` - Analyze execution trace
+- `npx output workflow status <id>` - Check current status
+- `npx output workflow result <id>` - Get execution result
+- `npx output workflow list` - List available workflows

package/dist/templates/agent_instructions/skills/output-workflow-start/SKILL.md.template

@@ -20,7 +20,7 @@ This skill starts a workflow asynchronously, meaning the command returns immedia
 
 ## When to Use Sync Instead
 
-Consider using `output workflow run` (sync) when:
+Consider using `npx output workflow run` (sync) when:
 - Workflow completes quickly (seconds)
 - You need the result immediately in your terminal
 - Simple testing during development
@@ -31,8 +31,8 @@ Consider using `output workflow run` (sync) when:
 ### Basic Syntax
 
 ```bash
-output workflow start <workflowName> --input '<json-input>'
-output workflow start <workflowName> --input <path-to-json-file>
+npx output workflow start <workflowName> --input '<json-input>'
+npx output workflow start <workflowName> --input <path-to-json-file>
 ```
 
 The `--input` flag is required when the workflow expects input data.
@@ -44,7 +44,7 @@ The `--input` flag is required when the workflow expects input data.
 Pass JSON directly on the command line:
 
 ```bash
-output workflow start data-migration --input '{"batchSize": 1000}'
+npx output workflow start data-migration --input '{"batchSize": 1000}'
 ```
 
 #### 2. File Path (Recommended)
@@ -52,7 +52,7 @@ output workflow start data-migration --input '{"batchSize": 1000}'
 Reference a JSON file containing the input:
 
 ```bash
-output workflow start data-migration --input src/data_migration/scenarios/large_batch.json
+npx output workflow start data-migration --input src/data_migration/scenarios/large_batch.json
 ```
 
 This is the recommended approach because:
@@ -63,30 +63,30 @@ This is the recommended approach because:
 ### Getting the Workflow ID
 
 The command outputs the workflow ID which you'll need for:
-- Checking status: `output workflow status <id>`
-- Getting results: `output workflow result <id>`
-- Debugging: `output workflow debug <id>`
+- Checking status: `npx output workflow status <id>`
+- Getting results: `npx output workflow result <id>`
+- Debugging: `npx output workflow debug <id>`
 
 ## Examples
 
 **Scenario**: Start a long-running workflow with scenario file
 
 ```bash
-output workflow start data-migration --input src/data_migration/scenarios/full_migration.json
+npx output workflow start data-migration --input src/data_migration/scenarios/full_migration.json
 
 # Output:
 # Started workflow: data-migration
 # Workflow ID: abc123xyz
-# Use 'output workflow status abc123xyz' to check progress
+# Use 'npx output workflow status abc123xyz' to check progress
 ```
 
 **Scenario**: Start multiple workflows in parallel using scenario files
 
 ```bash
 # Start several workflows with different scenario files
-output workflow start process-batch --input src/process_batch/scenarios/batch_1.json
-output workflow start process-batch --input src/process_batch/scenarios/batch_2.json
-output workflow start process-batch --input src/process_batch/scenarios/batch_3.json
+npx output workflow start process-batch --input src/process_batch/scenarios/batch_1.json
+npx output workflow start process-batch --input src/process_batch/scenarios/batch_2.json
+npx output workflow start process-batch --input src/process_batch/scenarios/batch_3.json
 
 # Note: Save the workflow IDs to check them later
 ```
@@ -105,37 +105,37 @@ cat > src/generate_report/scenarios/annual_2024.json << 'EOF'
 EOF
 
 # Start the workflow
-output workflow start generate-report --input src/generate_report/scenarios/annual_2024.json
+npx output workflow start generate-report --input src/generate_report/scenarios/annual_2024.json
 # Output: Workflow ID: report-2024-abc
 
 # Check status periodically
-output workflow status report-2024-abc
+npx output workflow status report-2024-abc
 # Output: Status: RUNNING
 
 # Later, check again
-output workflow status report-2024-abc
+npx output workflow status report-2024-abc
 # Output: Status: COMPLETED
 
 # Get the result
-output workflow result report-2024-abc
+npx output workflow result report-2024-abc
 ```
 
 **Scenario**: Quick inline test for development
 
 ```bash
-output workflow start quick-job --input '{"test": true}'
+npx output workflow start quick-job --input '{"test": true}'
 ```
 
 **Scenario**: Script for parallel execution
 
 ```bash
 # Start workflows and capture IDs
-ID1=$(output workflow start job --input src/job/scenarios/type_a.json | grep "Workflow ID" | cut -d: -f2 | tr -d ' ')
-ID2=$(output workflow start job --input src/job/scenarios/type_b.json | grep "Workflow ID" | cut -d: -f2 | tr -d ' ')
+ID1=$(npx output workflow start job --input src/job/scenarios/type_a.json | grep "Workflow ID" | cut -d: -f2 | tr -d ' ')
+ID2=$(npx output workflow start job --input src/job/scenarios/type_b.json | grep "Workflow ID" | cut -d: -f2 | tr -d ' ')
 
 # Wait and check results
-output workflow result $ID1
-output workflow result $ID2
+npx output workflow result $ID1
+npx output workflow result $ID2
 ```
 
 ## Following Up After Starting
@@ -143,7 +143,7 @@ output workflow result $ID2
 ### Check Status
 
 ```bash
-output workflow status <workflowId>
+npx output workflow status <workflowId>
 ```
 
 Status values:
@@ -155,7 +155,7 @@ Status values:
 ### Get Result
 
 ```bash
-output workflow result <workflowId>
+npx output workflow result <workflowId>
 ```
 
 Only works for COMPLETED workflows. For FAILED workflows, use debug.
@@ -163,13 +163,13 @@ Only works for COMPLETED workflows. For FAILED workflows, use debug.
 ### Debug If Failed
 
 ```bash
-output workflow debug <workflowId> --format json
+npx output workflow debug <workflowId> --format json
 ```
 
 ### Stop If Needed
 
 ```bash
-output workflow stop <workflowId>
+npx output workflow stop <workflowId>
 ```
 
 ## Workflow ID Management
@@ -178,8 +178,8 @@ When starting multiple workflows, keep track of IDs:
 
 ```bash
 # Log IDs to a file
-output workflow start batch-job --input src/batch_job/scenarios/id_1.json >> workflow-ids.txt
-output workflow start batch-job --input src/batch_job/scenarios/id_2.json >> workflow-ids.txt
+npx output workflow start batch-job --input src/batch_job/scenarios/id_1.json >> workflow-ids.txt
+npx output workflow start batch-job --input src/batch_job/scenarios/id_2.json >> workflow-ids.txt
 
 # Or use a naming convention in your workflow that makes IDs predictable
 ```
@@ -188,14 +188,14 @@ output workflow start batch-job --input src/batch_job/scenarios/id_2.json >> wor
 
 1. **Use scenario files**: Store inputs in `src/<workflow>/scenarios/` for reproducibility
 2. **Save the workflow ID**: Always note the ID for later reference
-3. **Monitor long workflows**: Use `output workflow status` to check progress
+3. **Monitor long workflows**: Use `npx output workflow status` to check progress
 4. **Handle failures**: Check status before getting results
-5. **Clean up**: Stop any stuck workflows with `output workflow stop`
+5. **Clean up**: Stop any stuck workflows with `npx output workflow stop`
 
 ## Related Commands
 
-- `output workflow run <name> --input` - Execute synchronously
-- `output workflow status <id>` - Check execution status
-- `output workflow result <id>` - Get execution result
-- `output workflow stop <id>` - Stop a running workflow
-- `output workflow debug <id>` - Debug a workflow execution
+- `npx output workflow run <name> --input` - Execute synchronously
+- `npx output workflow status <id>` - Check execution status
+- `npx output workflow result <id>` - Get execution result
+- `npx output workflow stop <id>` - Stop a running workflow
+- `npx output workflow debug <id>` - Debug a workflow execution

package/dist/templates/agent_instructions/skills/output-workflow-status/SKILL.md.template

@@ -20,27 +20,27 @@ This skill checks the current execution status of a workflow. Use it to monitor
 
 ## When to Use Other Commands
 
-- **Getting results**: Use `output workflow result` after confirming COMPLETED status
-- **Debugging failures**: Use `output workflow debug` for FAILED workflows
-- **Execution history**: Use `output workflow runs list` for multiple runs
+- **Getting results**: Use `npx output workflow result` after confirming COMPLETED status
+- **Debugging failures**: Use `npx output workflow debug` for FAILED workflows
+- **Execution history**: Use `npx output workflow runs list` for multiple runs
 
 ## Instructions
 
 ### Check Status
 
 ```bash
-output workflow status <workflowId>
+npx output workflow status <workflowId>
 ```
 
-Replace `<workflowId>` with the ID from `output workflow start` or `output workflow runs list`.
+Replace `<workflowId>` with the ID from `npx output workflow start` or `npx output workflow runs list`.
 
 ## Understanding Status Values
 
 | Status | Meaning | Next Action |
 |--------|---------|-------------|
 | RUNNING | Workflow is currently executing | Wait and check again |
-| COMPLETED | Workflow finished successfully | Get result with `output workflow result` |
-| FAILED | Workflow encountered an error | Debug with `output workflow debug` |
+| COMPLETED | Workflow finished successfully | Get result with `npx output workflow result` |
+| FAILED | Workflow encountered an error | Debug with `npx output workflow debug` |
 | TERMINATED | Workflow was manually stopped | Review if expected, restart if needed |
 | TIMED_OUT | Workflow exceeded time limit | Check for long operations, adjust timeout |
 
@@ -50,16 +50,16 @@ Replace `<workflowId>` with the ID from `output workflow start` or `output workf
 
 ```bash
 # Start a workflow
-output workflow start data-sync '{"source": "external"}'
+npx output workflow start data-sync '{"source": "external"}'
 # Output: Workflow ID: sync-abc123
 
 # Check status
-output workflow status sync-abc123
+npx output workflow status sync-abc123
 # Output: Status: RUNNING
 
 # Wait and check again
 sleep 30
-output workflow status sync-abc123
+npx output workflow status sync-abc123
 # Output: Status: COMPLETED
 ```
 
@@ -69,16 +69,16 @@ output workflow status sync-abc123
 WORKFLOW_ID="abc123xyz"
 
 while true; do
-  STATUS=$(output workflow status $WORKFLOW_ID)
+  STATUS=$(npx output workflow status $WORKFLOW_ID)
   echo "Current status: $STATUS"
 
   if [[ "$STATUS" == *"COMPLETED"* ]]; then
     echo "Workflow completed!"
-    output workflow result $WORKFLOW_ID
+    npx output workflow result $WORKFLOW_ID
     break
   elif [[ "$STATUS" == *"FAILED"* ]]; then
     echo "Workflow failed!"
-    output workflow debug $WORKFLOW_ID --format json
+    npx output workflow debug $WORKFLOW_ID --format json
     break
   fi
 
@@ -90,13 +90,13 @@ done
 
 ```bash
 # Verify status first
-output workflow status my-workflow-123
+npx output workflow status my-workflow-123
 
 # If COMPLETED, get result
-output workflow result my-workflow-123
+npx output workflow result my-workflow-123
 
 # If FAILED, debug instead
-output workflow debug my-workflow-123 --format json
+npx output workflow debug my-workflow-123 --format json
 ```
 
 **Scenario**: Batch status check
@@ -104,7 +104,7 @@ output workflow debug my-workflow-123 --format json
 ```bash
 # Check multiple workflows
 for id in abc123 def456 ghi789; do
-  echo "Workflow $id: $(output workflow status $id)"
+  echo "Workflow $id: $(npx output workflow status $id)"
 done
 ```
 
@@ -131,21 +131,21 @@ The status command returns information including:
 ### "Workflow not found"
 - The workflow ID may be incorrect
 - The workflow may have been deleted from history
-- Check `output workflow runs list` to find the correct ID
+- Check `npx output workflow runs list` to find the correct ID
 
 ### Status stays RUNNING too long
-1. Check if the workflow is stuck: `output workflow debug <id>`
+1. Check if the workflow is stuck: `npx output workflow debug <id>`
 2. Look for infinite loops or waiting operations
-3. Consider stopping: `output workflow stop <id>`
+3. Consider stopping: `npx output workflow stop <id>`
 
 ### Unexpected TERMINATED status
 - Someone may have manually stopped the workflow
-- Check with `output workflow debug` for context
-- Restart if needed: `output workflow start`
+- Check with `npx output workflow debug` for context
+- Restart if needed: `npx output workflow start`
 
 ## Related Commands
 
-- `output workflow result <id>` - Get execution result (after COMPLETED)
-- `output workflow debug <id>` - Debug execution (after FAILED)
-- `output workflow stop <id>` - Stop a running workflow
-- `output workflow runs list` - View execution history
+- `npx output workflow result <id>` - Get execution result (after COMPLETED)
+- `npx output workflow debug <id>` - Debug execution (after FAILED)
+- `npx output workflow stop <id>` - Stop a running workflow
+- `npx output workflow runs list` - View execution history

package/dist/templates/agent_instructions/skills/output-workflow-stop/SKILL.md.template

@@ -22,7 +22,7 @@ This skill stops a running workflow execution. The workflow will be marked as TE
 
 - If the workflow is about to complete (let it finish)
 - If you're unsure whether stopping is safe
-- For debugging (use `output workflow debug` instead)
+- For debugging (use `npx output workflow debug` instead)
 - If the workflow has side effects that may leave data in an inconsistent state
 
 ## Instructions
@@ -30,7 +30,7 @@ This skill stops a running workflow execution. The workflow will be marked as TE
 ### Stop a Workflow
 
 ```bash
-output workflow stop <workflowId>
+npx output workflow stop <workflowId>
 ```
 
 ### Safety Considerations
@@ -48,15 +48,15 @@ Before stopping, consider:
 
 ```bash
 # Check status - workflow has been running too long
-output workflow status abc123xyz
+npx output workflow status abc123xyz
 # Status: RUNNING (for 2 hours)
 
 # Decide to stop it
-output workflow stop abc123xyz
+npx output workflow stop abc123xyz
 # Workflow abc123xyz has been stopped
 
 # Verify it's terminated
-output workflow status abc123xyz
+npx output workflow status abc123xyz
 # Status: TERMINATED
 ```
 
@@ -64,26 +64,26 @@ output workflow status abc123xyz
 
 ```bash
 # Realized input was wrong immediately after starting
-output workflow start expensive-job '{"wrong": "input"}'
+npx output workflow start expensive-job '{"wrong": "input"}'
 # Workflow ID: job-abc123
 
 # Stop before it processes too much
-output workflow stop job-abc123
+npx output workflow stop job-abc123
 
 # Start again with correct input
-output workflow start expensive-job '{"correct": "input"}'
+npx output workflow start expensive-job '{"correct": "input"}'
 ```
 
 **Scenario**: Stop multiple workflows
 
 ```bash
 # Get list of running workflows
-output workflow runs list --format json | jq '.[] | select(.status == "RUNNING") | .workflowId'
+npx output workflow runs list --format json | jq '.[] | select(.status == "RUNNING") | .workflowId'
 
 # Stop each one (carefully review first!)
 for id in abc123 def456; do
   echo "Stopping $id"
-  output workflow stop $id
+  npx output workflow stop $id
 done
 ```
 
@@ -92,14 +92,14 @@ done
 ### Check the State
 
 ```bash
-output workflow status <workflowId>
+npx output workflow status <workflowId>
 # Status: TERMINATED
 ```
 
 ### Review What Happened
 
 ```bash
-output workflow debug <workflowId> --format json
+npx output workflow debug <workflowId> --format json
 ```
 
 This shows:
@@ -118,7 +118,7 @@ If the workflow made partial changes:
 
 ```bash
 # Start a fresh execution
-output workflow start <workflowName> '<input>'
+npx output workflow start <workflowName> '<input>'
 ```
 
 ## What Happens When You Stop
@@ -133,7 +133,7 @@ output workflow start <workflowName> '<input>'
 
 ### "Workflow not found"
 - Check the workflow ID is correct
-- Use `output workflow runs list` to find valid IDs
+- Use `npx output workflow runs list` to find valid IDs
 
 ### "Workflow already completed"
 - The workflow finished before the stop command
@@ -151,14 +151,14 @@ output workflow start <workflowName> '<input>'
 ## Best Practices
 
 1. **Always check status first**: Confirm the workflow is actually RUNNING
-2. **Review before stopping**: Use `output workflow debug` to understand state
+2. **Review before stopping**: Use `npx output workflow debug` to understand state
 3. **Document why**: Note why you stopped the workflow for future reference
 4. **Plan for cleanup**: Know what side effects may need manual handling
 5. **Consider alternatives**: Sometimes waiting is better than stopping
 
 ## Related Commands
 
-- `output workflow status <id>` - Check current status
-- `output workflow debug <id>` - Review execution details
-- `output workflow start <name>` - Start a new execution
-- `output workflow runs list` - View execution history
+- `npx output workflow status <id>` - Check current status
+- `npx output workflow debug <id>` - Review execution details
+- `npx output workflow start <name>` - Start a new execution
+- `npx output workflow runs list` - View execution history

package/dist/templates/agent_instructions/skills/output-workflow-trace/SKILL.md.template

@@ -25,12 +25,12 @@ This skill provides guidance on retrieving and analyzing workflow execution trac
 
 **Basic trace (text format, may be truncated):**
 ```bash
-output workflow debug <workflowId>
+npx output workflow debug <workflowId>
 ```
 
 **Full trace (JSON format, recommended for detailed analysis):**
 ```bash
-output workflow debug <workflowId> --format json
+npx output workflow debug <workflowId> --format json
 ```
 
 **Tip**: Always use `--format json` when you need complete trace data. The text format truncates long values which can hide important debugging information.
@@ -96,10 +96,10 @@ When examining JSON traces, focus on these fields:
 
 ```bash
 # Get the workflow ID from runs list
-output workflow runs list --limit 5 --format json
+npx output workflow runs list --limit 5 --format json
 
 # Get detailed trace
-output workflow debug abc123xyz --format json
+npx output workflow debug abc123xyz --format json
 
 # Look for the failing step in the output
 # Example output structure:
@@ -116,13 +116,13 @@ output workflow debug abc123xyz --format json
 **Scenario**: Investigate retry behavior
 
 ```bash
-output workflow debug abc123xyz --format json | jq '.steps[] | select(.attempts > 1)'
+npx output workflow debug abc123xyz --format json | jq '.steps[] | select(.attempts > 1)'
 ```
 
 **Scenario**: Check inputs to a specific step
 
 ```bash
-output workflow debug abc123xyz --format json | jq '.steps[] | select(.name == "processData") | .input'
+npx output workflow debug abc123xyz --format json | jq '.steps[] | select(.name == "processData") | .input'
 ```
 
 ## Next Steps After Analysis
@@ -130,5 +130,5 @@ output workflow debug abc123xyz --format json | jq '.steps[] | select(.name == "
 1. Match the error to common patterns (see error skills)
 2. Consult the `workflow-quality` subagent for best practices
 3. Make code fixes based on identified issues
-4. Re-run the workflow: `output workflow run <workflowName> <input>`
+4. Re-run the workflow: `npx output workflow run <workflowName> <input>`
 5. Verify the fix with a new trace

package/dist/templates/project/README.md.template

@@ -49,7 +49,7 @@ npx output workflow run simple --input '{"question": "who really is ada lovelace
 
 ### 5. Stop Services
 
-Press `Ctrl+C` in the terminal running `output dev` to stop all services gracefully.
+Press `Ctrl+C` in the terminal running `npm run dev` to stop all services gracefully.
 
 ### 6. View Logs
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@output.ai/cli",
-  "version": "0.5.0",
+  "version": "0.5.1",
   "description": "CLI for Output.ai workflow generation",
   "type": "module",
   "main": "dist/index.js",