output-eval-error-analysis

output-eval-error-analysis is a skill for Claude Code from growthxai/output. It costs 38 tokens per session (2,471 once invoked), scanned A, original, Apache-2.0.

A workflow for studying real workflow traces—records of how an automated process ran—to identify recurring failure types before building quality checks. It is intended for projects that evaluate automated workflows.

In plain words
What is it for?
Use it when starting an evaluation project, after major pipeline changes, or when production quality drops, using a collection of representative workflow runs.
Why use it?
It prevents evaluators from testing only generic qualities and helps them target the specific ways a workflow fails in practice.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the outputai plugin — 50 skills, 5 agents, 1 hook shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/growthxai/output/output-eval-error-analysis
Any agent
npx skills add growthxai/output --skill output-eval-error-analysis
Clone the repo
git clone --depth 1 https://github.com/growthxai/output

Made for: Claude Code.

Or install outputai, the plugin that ships this one along with the rest of its 50 skills, 5 agents, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for output-eval-error-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/growthxai/output/output-eval-error-analysis.svg)](https://agentmods.dev/skills/growthxai/output/output-eval-error-analysis)
Your own site
<a href="https://agentmods.dev/skills/growthxai/output/output-eval-error-analysis"><img src="https://agentmods.dev/badge/skills/growthxai/output/output-eval-error-analysis.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,471 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.02471
Opus 5 $0.00019 $0.01236
Sonnet 5 $0.00008 $0.00494
Haiku 4.5 $0.00004 $0.00247

Measured 6d ago against content hash fc18ff302158, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

output-eval-error-analysis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

coding_assistants/claude/plugins/outputai/skills/output-eval-error-analysis/SKILL.md · 260 lines

How it starts

The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Error Analysis for Workflow Evaluation

Overview

Review real workflow traces and categorize how your workflow fails before writing any evaluators. Evaluators built without error analysis target generic qualities ("is this good?") instead of the specific ways your workflow actually breaks. This skill walks you through the process.

When to Use

  • Starting a new eval project for an existing workflow
  • Production quality has dropped and you need to understand why
  • After significant prompt, model, or pipeline changes
  • Before building your first evaluator for a workflow

Step 1: Collect Traces

Gather 50-100 representative workflow executions. More traces = more reliable failure categories.

From recent runs

List recent workflow executions and pull their traces:

# List recent runs for a workflow
npx output workflow runs list <workflowName>

# Pull a specific trace as JSON
npx output workflow debug <workflowId> --json

From production (bulk download)

Download production traces directly into dataset YAML files:

# Download up to 20 recent traces as dataset files
npx output workflow dataset generate <workflowName> --download --limit 20

This creates YAML files in tests/datasets/ with the input and last_output fields populated from real executions.

From scenario-driven generation

If production traces are sparse, generate traces from scenario inputs:

# Generate a dataset from a scenario file
npx output workflow dataset generate <workflowName> basic --name basic_trace

# Generate from inline JSON
npx output workflow dataset generate <workflowName> --input '{"topic": "AI safety"}' --name ai_safety_trace

Run enough inputs to get 50+ traces. Prioritize diversity over volume — vary inputs across the dimensions you expect to matter.

Step 2: Review Traces Individually

Review each trace one at a time. For each trace, record:

Field What to write
Trace ID The workflow execution ID
Verdict Pass or Fail (binary — no "partial" at this stage)
Root cause If Fail: what specifically went wrong and why
Notes Anything surprising or worth remembering

Read the full file on GitHub · 260 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 260 lines · 38 tokens per session scan A fc18ff302158

Subscribe to this mod's changes

output-eval-error-analysis is a skill published in the GitHub repository growthxai/output (435 stars, last pushed yesterday), licensed Apache-2.0. It adds 38 tokens to every session and 2,471 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

technical-writing

Write, edit, review, or audit user-facing documentation for the eve repository. Use for changes under docs/, documentation tied to eve APIs or CLI behavior, docs work based on Slack or support feedback, and requests to make eve docs clearer, more natural, or less AI-patterned while verifying claims against current…

vercel/eve · 78 tokens

optimizing-clickhouse-and-hogql-queries

Workflow for optimizing ClickHouse and HogQL queries. Use when a HogQL query, query runner, insight, or report is too slow; when a hand-written ClickHouse query (via syncexecute or in a migration) is too slow; when ClickHouse times out or hits memory limits; when investigating a slow system.querylog row; or when…

PostHog/posthog · 183 tokens

dynamic-workflows

Designs and runs task-specific JavaScript harnesses with the workflow tool. Use for broad, long-running, highly structured, or adversarial work that benefits from many isolated agents: exhaustive audits, root-cause investigations, research, large triage queues, competing proposals, repeated verification, and…

PostHog/posthog · 93 tokens

adding-product-alerting

Recommended repo-engineering guide when adding alerting to a PostHog product or extending the shared alerts platform. Routes lifecycle state machines, AlertPolicy, destinations, HogFunction dispatch, email, fixed-cadence and calendar scheduling, insight evaluation, the AlertWizard, and shared alert editor components.…

PostHog/posthog · 97 tokens

adding-mcp-store-servers

Add a third-party MCP server (Linear, Notion, GitHub, ...) to the PostHog MCP store catalog. Use when asked to "add X to the MCP store", expand the MCP server marketplace, or fix a broken catalog entry. Covers finding the vendor's remote MCP endpoint, probing it (handshake, OAuth discovery, DCR), authoring the catalog…

PostHog/posthog · 107 tokens

subagent-orchestration

How and when to delegate work to subagents via the subagent tool (Explore, Plan, General). Use when a task involves codebase recon, implementation planning, or actual code changes that would benefit from an isolated context window instead of doing it all inline.

PostHog/posthog · 60 tokens