creating-workflow-evals

creating-workflow-evals is a skill for Claude Code, Codex from apify/apify-mcp-server. It costs 69 tokens per session (1,850 once invoked), scanned A, original, MIT.

Use when adding Langfuse workflow evals for a tool family of the Apify MCP server ("create evals for the storage tools"), when eval cases fail and you must decide whether the case, the tool, or its description is at fault, or when eval runs show tool errors in Langfuse traces.

Skill for Claude CodeCodex

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/apify/apify-mcp-server/creating-workflow-evals
Any agent
npx skills add apify/apify-mcp-server --skill creating-workflow-evals
Clone the repo
git clone --depth 1 https://github.com/apify/apify-mcp-server

Made for: Claude Code, Codex.

Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,850 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 $0.00069 $0.01850
Opus 5 $0.00034 $0.00925
Sonnet 5 $0.00014 $0.00370
Haiku 4.5 $0.00007 $0.00185

Measured yesterday against content hash c5f7dbe446d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

creating-workflow-evals 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 yesterday.

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.

.claude/skills/creating-workflow-evals/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Creating workflow evals for an MCP tool family

Overview

Build a small, calibrated Langfuse eval suite for one tool family (tasks, storage, runs, …), then use its failures to fix the tools. Core principle: evals are designed from user intent, never from tool descriptions — the eval defines what should work; descriptions get fixed afterward to make naive agents pass it.

Commands, item shapes, probe patterns, and sweep queries: reference.md.

The flow

  1. Inventory the tools — every tool and every argument group needs at least one case (the coverage matrix at the end proves it).
  2. Probe the platform first. Before writing any case that depends on API behavior (required fields, uniqueness rules, limits, error messages), verify it with a throwaway tsx script against the real API. Never write a case on an assumed contract — that's how you get input values the schema rejects.
  3. Two datasets, never one: <family>-evals (proper suite, zero tool errors tolerated) and <family>-evals-errors (cases that provoke errors on purpose: collisions, not-found, requirement discovery). Mixing them masks real failures.
  4. Write cases in waves: 2–3 easy (single tool, explicit input) → 1–2 medium (cross-tool chains, run options) → 2–3 hard (vague user language, error recovery, collisions). Run and review each wave before writing the next.
  5. Calibrate on the strongest model first (Opus). A failure there is a case defect or a product gap — never a description problem. Only a calibrated suite (strong model 100%) can attribute weaker-model failures to descriptions.
  6. Ladder down (Sonnet → Haiku). Passes-on-Opus-fails-on-Haiku = the tool description or output doesn't carry a naive agent. That's the signal you built the suite for.
  7. Fix tools via outputs before descriptions. A steering sentence in the tool's response summary/nextStep reaches every agent on every call; description text gets skimmed. Both output nudges that fixed Haiku failures in the original build were response-text changes.

Read the full file on GitHub · 69 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 69 lines · 69 tokens per session scan A c5f7dbe446d3

Subscribe to this mod's changes

creating-workflow-evals is a skill published in the GitHub repository apify/apify-mcp-server (5,636 stars, last pushed 2d ago), licensed MIT. It adds 69 tokens to every session and 1,850 once invoked, about $0.0003 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 2026-09-02.

Related

Other skills, from other repositories

unity-model-agnostic-inference

Use for on-device or server inference that is not tied to one vendor model: ONNX Runtime, Sentis, Barracuda legacy, custom .onnx/.tflite/.pb assets, and swapping models without rewriting gameplay code.

rachitkumarrastogi/unity-mcp-server · 56 tokens

unity-llm-integration

Use when adding LLM/chat/RAG features to a Unity game or tool: API keys, prompt assets, safety, latency, and server-side vs client-side calls.

rachitkumarrastogi/unity-mcp-server · 41 tokens

unity-ml-agents

Use when working on Unity ML-Agents: training configs, BehaviorParameters, sensors, actuators, inference in builds, or com.unity.ml-agents packages.

rachitkumarrastogi/unity-mcp-server · 39 tokens

unity-sentis-inference

Use when integrating ONNX/Sentis/Unity Inference in Unity: model assets, IWorker, runtime performance, or com.unity.sentis packages.

rachitkumarrastogi/unity-mcp-server · 39 tokens

ai-elements

Build AI chat interfaces using ai-elements components — conversations, messages, tool displays, prompt inputs, and more. Use when the user wants to build a chatbot, AI assistant UI, or any AI-powered chat interface.

ssdeanx/AgentStack · 46 tokens

grpo-finetune

Fine-tune a model with GRPO on Fireworks-managed GPUs from a plain-English task description and a dataset. Use this skill whenever the user wants to fine-tune, RL-tune, or GRPO-train a model on their own data — or says things like "train a model to extract/classify/score X", "fine-tune on this dataset", "set up a GRPO…

patchy631/ai-engineering-hub · 122 tokens