Agent skill

Output Workflow Trace

Analyze Output SDK workflow execution traces. An agent skill from growthxai/output.

Apache-2.0Auto-check: notesDevelopment

Install Output Workflow Trace

skills CLI

$ npx skills add growthxai/output --skill output-workflow-trace -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install growthxai/output output-workflow-trace --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/growthxai/output.git skills-src && mkdir -p .claude/skills && cp -r skills-src/coding_assistants/claude/plugins/outputai/skills/output-workflow-trace .claude/skills/output-workflow-trace && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "output-workflow-trace" agent skill from https://github.com/growthxai/output/tree/main/coding_assistants/claude/plugins/outputai/skills/output-workflow-trace into .claude/skills/output-workflow-trace/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "output-workflow-trace", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/growthxai/output/tree/main/coding_assistants/claude/plugins/outputai/skills/output-workflow-trace

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add growthxai/output --skill output-workflow-trace -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install growthxai/output output-workflow-trace --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/growthxai/output.git skills-src && mkdir -p .agents/skills && cp -r skills-src/coding_assistants/claude/plugins/outputai/skills/output-workflow-trace .agents/skills/output-workflow-trace && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "output-workflow-trace" agent skill from https://github.com/growthxai/output/tree/main/coding_assistants/claude/plugins/outputai/skills/output-workflow-trace into .agents/skills/output-workflow-trace/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "output-workflow-trace", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add growthxai/output --skill output-workflow-trace -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install growthxai/output output-workflow-trace --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/growthxai/output.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/coding_assistants/claude/plugins/outputai/skills/output-workflow-trace .cursor/skills/output-workflow-trace && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "output-workflow-trace" agent skill from https://github.com/growthxai/output/tree/main/coding_assistants/claude/plugins/outputai/skills/output-workflow-trace into .cursor/skills/output-workflow-trace/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "output-workflow-trace", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/growthxai/output.git --path coding_assistants/claude/plugins/outputai/skills/output-workflow-trace

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add growthxai/output --skill output-workflow-trace -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install growthxai/output output-workflow-trace --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/growthxai/output.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/coding_assistants/claude/plugins/outputai/skills/output-workflow-trace .gemini/skills/output-workflow-trace && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "output-workflow-trace" agent skill from https://github.com/growthxai/output/tree/main/coding_assistants/claude/plugins/outputai/skills/output-workflow-trace into .gemini/skills/output-workflow-trace/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "output-workflow-trace", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install growthxai/output output-workflow-trace

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add growthxai/output --skill output-workflow-trace -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/growthxai/output.git skills-src && mkdir -p .github/skills && cp -r skills-src/coding_assistants/claude/plugins/outputai/skills/output-workflow-trace .github/skills/output-workflow-trace && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "output-workflow-trace" agent skill from https://github.com/growthxai/output/tree/main/coding_assistants/claude/plugins/outputai/skills/output-workflow-trace into .github/skills/output-workflow-trace/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "output-workflow-trace", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add growthxai/output --skill output-workflow-trace -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install growthxai/output output-workflow-trace --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/growthxai/output.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/coding_assistants/claude/plugins/outputai/skills/output-workflow-trace .opencode/skills/output-workflow-trace && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "output-workflow-trace" agent skill from https://github.com/growthxai/output/tree/main/coding_assistants/claude/plugins/outputai/skills/output-workflow-trace into .opencode/skills/output-workflow-trace/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "output-workflow-trace", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: output-workflow-trace
GitHub stars: 442
Token cost: ~1.1k tokens
SKILL.md length: 491 words
Files: 1
Skills in repo: 50
Repo updated: Oct 9, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Analyze Output SDK workflow execution traces. An agent skill from growthxai/output.

Works in 3 steps: Retrieve the Execution Trace → Analyze the Trace → Use the Temporal UI for Visual Analysis
Debugging a specific workflow
SKILL.md covers Overview, When to Use This Skill, Instructions and What to Look For in Traces, plus 2 more sections
Calls npx and jq

What it does

Output Workflow Trace is an agent skill from growthxai/output. Analyze Output SDK workflow execution traces. Use when debugging a specific workflow, examining step failures, analyzing input/output data, understanding execution flow, or when you have a workflow ID to investigate.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Debugging. The repository describes itself as: 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… The licence is Apache-2.0.

When your agent uses it

Debugging a specific workflow
Examining step failures
Analyzing input/output data
Understanding execution flow

Example prompts

“/output-workflow-trace”

Requirements

Node.js
Pre-approved tools (allowed-tools): Bash, Read

Workflow steps

3 steps, taken from the step headings in SKILL.md.

Retrieve the Execution Trace
Analyze the Trace
Use the Temporal UI for Visual Analysis

What it can do on your machine

Read from SKILL.md and the folder at commit 99ee298. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
- Bash
- Read
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- npx
- jq
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Output Workflow Trace loads about 1.1k tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 491 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~60
When it runs · the whole SKILL.md, loaded when a task matches: ~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
```
allowed-tools: Bash, Read
```

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from growthxai/output at commit 99ee298, republished under its Apache-2.0 licence (© growthxai). 491 words, ~1,142 tokens.

Download SKILL.mdSave it as .claude/skills/output-workflow-trace/SKILL.md (or your agent's skills folder).

name: output-workflow-trace
description: Analyze Output SDK workflow execution traces. Use when debugging a specific workflow, examining step failures, analyzing input/output data, understanding execution flow, or when you have a workflow ID to investigate.
allowed-tools: Bash, Read

Workflow Trace Analysis

Overview

This skill provides guidance on retrieving and analyzing workflow execution traces using the Output CLI. Traces show the complete execution history including step inputs, outputs, errors, and timing information.

When to Use This Skill

You have a workflow ID and need to understand what happened
A workflow failed and you need to identify which step failed
You need to examine the input/output data at each step
You want to understand the execution flow and timing
You need to find error messages and stack traces
Debugging retry behavior or unexpected results

Instructions

Step 1: Retrieve the Execution Trace

Basic trace (text format, may be truncated):

bash

npx output workflow debug <workflowId>

Full trace (JSON format, recommended for detailed analysis):

bash

npx output workflow debug <workflowId> --json

Tip: Always use --json when you need complete trace data. The text format truncates long values which can hide important debugging information.

Step 2: Analyze the Trace

Follow this checklist when examining a trace:

Identify the failed step: Look for steps with error status or failure indicators
Examine error messages: Find the exact error message and stack trace
Check step inputs: Verify the data passed to the failing step was correct
Check step outputs: Look at outputs from preceding steps
Review retry attempts: Note how many retries occurred and their outcomes
Check timing: Look for unusual delays that might indicate timeouts

Step 3: Use the Temporal UI for Visual Analysis

Open http://localhost:8080 in your browser for a visual workflow inspection:

Search for your workflow by ID
View the event history timeline
Click on individual events to see details
Inspect step inputs and outputs
See retry attempts and timing information
Export trace data if needed

What to Look For in Traces

Show full SKILL.md (203 more words)Show less

Error Patterns

Error Message	Likely Cause
"incompatible schema"	Zod import issue - using `zod` instead of `@outputai/core`
"non-deterministic"	Using Math.random(), Date.now(), etc. in workflow code
"FatalError" with retry context	Try-catch wrapping step calls
"undefined is not a function"	Missing schema definitions
"workflow must be deterministic"	Direct I/O in workflow function
"ECONNREFUSED" or timeout	Services not running or network issues

Step Status Values

COMPLETED: Step finished successfully
FAILED: Step threw an error (may retry)
RETRYING: Step is being retried after a failure
TIMED_OUT: Step exceeded its timeout
CANCELLED: Workflow was stopped before step completed

Key Trace Fields

When examining JSON traces, focus on these fields:

steps[].name: Step identifier
steps[].status: Execution result
steps[].input: Data passed to the step
steps[].output: Data returned from the step
steps[].error: Error details if failed
steps[].attempts: Number of execution attempts
steps[].duration: How long the step took

Examples

Scenario: Debug a failed workflow

bash

# Get the workflow ID from runs list
npx output workflow runs list --limit 5 --json

# Get detailed trace
npx output workflow debug abc123xyz --json

# Look for the failing step in the output
# Example output structure:
# {
#   "workflowId": "abc123xyz",
#   "status": "FAILED",
#   "steps": [
#     { "name": "fetchData", "status": "COMPLETED", ... },
#     { "name": "processData", "status": "FAILED", "error": "..." }
#   ]
# }

Scenario: Investigate retry behavior

bash

npx output workflow debug abc123xyz --json | jq '.steps[] | select(.attempts > 1)'

Scenario: Check inputs to a specific step

bash

npx output workflow debug abc123xyz --json | jq '.steps[] | select(.name == "processData") | .input'

Next Steps After Analysis

Match the error to common patterns (see error skills)
Consult the workflow-quality subagent for best practices
Make code fixes based on identified issues
Re-run the workflow: npx output workflow run <workflowName> --input '<input>'
Verify the fix with a new trace

Files

Just SKILL.md in coding_assistants/claude/plugins/outputai/skills/output-workflow-trace of growthxai/output.

Open the folder on GitHubat commit 99ee298

Compare with similar skills

Output Workflow Trace next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Output Workflow Trace compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Output Workflow Trace this skillgrowthxai/output	442	—	~1.1k	Automated safety check: Notes	Apache-2.0	today
Trellis Session Insightmindfold-ai/Trellis	15k	4 repos	~1.7k	Automated safety check: Pass	AGPL-3.0	10 days ago
Native Data FetchingCherryHQ/cherry-studio-app	4k	6 repos	~2.9k	Automated safety check: Notes	MIT	today
Debugging Executionsn8n-io/n8n	207k	—	~2.6k	Automated safety check: Pass	Custom licence	today
Aoti Debugpytorch/pytorch	104k	1 repos	~1.7k	Automated safety check: Pass	Custom licence	today
Herdr Throwaway Reproductionherdrdev/herdr	43k	—	~2.4k	Automated safety check: Pass	Apache-2.0	yesterday

Similar skills

Trellis Session Insight
mindfold-ai/Trellis
Reach into past AI conversation history through the trellis mem CLI.
15k GitHub starsUsed in 4 repos~1.7k tokens
DevelopmentAuto-check passed
Native Data Fetching
CherryHQ/cherry-studio-app
A skill your agent uses when implementing or debugging ANY network request, API call, or data fetching.
4k GitHub starsUsed in 6 repos~2.9k tokens
DevelopmentAuto-check: notes
Debugging Executions
n8n-io/n8n
Official
Debug failed or wrong-output workflow executions using executions tools.
207k GitHub stars~2.6k tokensUpdated today
DevelopmentAuto-check passed
Aoti Debug
pytorch/pytorch
Debug AOTInductor (AOTI) errors and crashes. An agent skill from pytorch/pytorch.
104k GitHub starsUsed in 1 repo~1.7k tokens
DevelopmentAuto-check passed
Herdr Throwaway Reproduction
herdrdev/herdr
Runs a disposable, uniquely named Herdr session inside an existing one so runtime, pane, terminal or API bugs can be reproduced without touching the main session.
43k GitHub stars~2.4k tokensUpdated yesterday
DevelopmentAuto-check passed
Systematic Debugging
ultralisp/ultralisp
A skill your agent uses when encountering any bug, test failure, or unexpected behavior, before proposing fixes
258 GitHub starsUsed in 51 repos~2.4k tokens
DevelopmentAuto-check passed

Questions about Output Workflow Trace

What does Output Workflow Trace do?

Analyze Output SDK workflow execution traces. An agent skill from growthxai/output. Output Workflow Trace is an agent skill from growthxai/output. Analyze Output SDK workflow execution traces.

When should I use Output Workflow Trace?

Output Workflow Trace fits situations like: debugging a specific workflow; examining step failures; analyzing input/output data; understanding execution flow.

How do I install Output Workflow Trace in Claude Code?

Run `npx skills add growthxai/output --skill output-workflow-trace -a claude-code`. Or copy the skill folder (coding_assistants/claude/plugins/outputai/skills/output-workflow-trace in growthxai/output) into .claude/skills/output-workflow-trace in your project. Claude Code loads it when a task matches its description.

How do I install Output Workflow Trace in Codex?

Run `npx skills add growthxai/output --skill output-workflow-trace -a codex`. Or copy the skill folder (coding_assistants/claude/plugins/outputai/skills/output-workflow-trace in growthxai/output) into .agents/skills/output-workflow-trace in your project. Codex loads it when a task matches its description.

Can I use Output Workflow Trace in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add growthxai/output --skill output-workflow-trace -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/output-workflow-trace, .gemini/skills/output-workflow-trace, .github/skills/output-workflow-trace and .opencode/skills/output-workflow-trace in your project.

What does Output Workflow Trace need to run?

Going by SKILL.md and its folder, Output Workflow Trace needs the command-line tools its instructions call (npx and jq). Our summary lists: Node.js. Its frontmatter pre-approves these tools: Bash, Read.

Does Output Workflow Trace access the network?

SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Output Workflow Trace safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Output Workflow Trace use?

Output Workflow Trace is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Output Workflow Trace use?

About 1.1k tokens (SKILL.md is roughly 4.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Output Workflow Trace?

Skills that share tags, products or a category with Output Workflow Trace: Trellis Session Insight (mindfold-ai/Trellis, 15k stars), Native Data Fetching (CherryHQ/cherry-studio-app, 4k stars), Debugging Executions (n8n-io/n8n, 207k stars) and Aoti Debug (pytorch/pytorch, 104k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Output Workflow Trace?

growthxai (a GitHub organization) maintains it in growthxai/output, which has 442 GitHub stars. The repository holds 50 skills in this directory. The repository was last updated on October 9, 2026.

Source: growthxai/output on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Output Workflow Trace

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Workflow Trace Analysis

Overview

When to Use This Skill

Instructions

Step 1: Retrieve the Execution Trace

Step 2: Analyze the Trace

Step 3: Use the Temporal UI for Visual Analysis

What to Look For in Traces

Error Patterns

Step Status Values

Key Trace Fields

Examples

Next Steps After Analysis

Files

Compare with similar skills

Similar skills

More from growthxai/output

Related

Questions about Output Workflow Trace