Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Workflow Trace Analysis · growthxai | DecimalAI

agent toolingby growthxai

Workflow Trace Analysis

growthxai/output-workflow-trace

Source growthxai/output ↗License Apache-2.0

Analyze Output SDK workflow execution traces.

SkillScore91Maintained

Automatic

Coding pack

Last verified 8/20/2026

What it changes

Passed 19 of 21 test cases with the skill, and 11 of 21 without it.

Without skill55%

With skill91%

Checks it passed that the model alone missed

Identifies missing step schema definitions
Recommends checking step status fields for FAILED
Specifies `npx output workflow debug wf_30291 --json`

and 6 more in the full report

8 fixed12 passed either way2 still failing0 broke

Pass-rate lift: +36 pp
Tokens: +9%
Agent turns: 0%
Response time: -57%

Model gemini-3.6-flashMeasured 8/20/2026v120 of 22 cases passed with skill · 21 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/growthxai-output-workflow-trace/SKILL.md https://app.decimal.ai/s/growthxai-output-workflow-trace/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add growthxai-output-workflow-trace, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/growthxai-output-workflow-trace/ and pins it in .decimal/skills.lock

decimalai skills add growthxai-output-workflow-trace

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/growthxai-output-workflow-trace/SKILL.md https://app.decimal.ai/s/growthxai-output-workflow-trace/SKILL.md

Raw file: /s/growthxai-output-workflow-trace/SKILL.md ↗ · machine-readable summary at /s/growthxai-output-workflow-trace.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 8

Prompt

My workflow run with ID `wf_99218a` failed unexpectedly during execution. Can you run the CLI command to get its full trace data and analyze what failed, showing me the broken step and its error message?

What was checked, without and with the skill
Checked	Without skill	With skill
Includes the command `npx output workflow debug wf_99218a --json`	Missed	Passed

case-01 · gemini-3.6-flash · 8/20/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md128 linessingle file

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):

npx output workflow debug <workflowId>

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

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

Track record

Benchmark

19 / 21

test cases passed, vs 11 / 21 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

growthxai / output

coding_assistants/claude/plugins/outputai/skills/output-workflow-trace/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Workflow Trace Analysis

Overview

When to Use This Skill

Instructions

Step 1: Retrieve the Execution Trace

Step 2: Analyze the Trace

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills