An evaluation workflow for AI features. It helps define what a system should do, test it across examples and usage paths, inspect failures, and decide whether it is ready to release.

Use it to turn a product specification into tests, run trials, grade responses or agent work, check safety and privacy controls, investigate failures, and verify promised memory behavior.

It replaces vague judgments about AI quality with agreed checks and recorded results. It also helps distinguish a bad final result from a problem in the steps, tools, system, or saved information involved.

eval-engine — Skill for Claude Code by Abhillashjadhav

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/Abhillashjadhav/AI-PM-essential-skills

agentmods

npx agentmods add skills/abhillashjadhav/ai-pm-essential-skills/eval-engine

Made for: Claude Code.

Or install pm-verifier, the plugin that ships this one along with the rest of its 1 skill.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/abhillashjadhav/ai-pm-essential-skills/eval-engine/github.svg)](https://agentmods.dev/skills/abhillashjadhav/ai-pm-essential-skills/eval-engine)

Your own site

<a href="https://agentmods.dev/skills/abhillashjadhav/ai-pm-essential-skills/eval-engine"><img src="https://agentmods.dev/badge/skills/abhillashjadhav/ai-pm-essential-skills/eval-engine/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/abhillashjadhav/ai-pm-essential-skills/eval-engine"><img src="https://agentmods.dev/badge/skills/abhillashjadhav/ai-pm-essential-skills/eval-engine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 190 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,112 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00190	$0.02112
Opus 5	$0.00095	$0.01056
Sonnet 5	$0.00038	$0.00422
Haiku 4.5	$0.00019	$0.00211

Measured 10d ago against content hash d8c669535a9a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

eval-engine 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 10d ago.

The scan reads SKILL.md. This mod also ships 11 executable files (examples/complete-eval/reference_adapter.py, examples/complete-eval/synthetic_candidate.py, examples/complete-eval/tools/repository_pilot.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

pm-verifier/skills/eval-engine/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Eval Engine

This skill powers AI Evals for PMs. Its stable install and CLI identifier is pm-verifier.

Keep the user-facing flow simple:

product contract → define surfaces → create eval suite → run trials → grade → inspect failures → release decision

Put framework complexity in the bundled harness, not in the PM's workflow.

1. Start from the claim

Read the spec or existing suite. State the decision the evaluation must support:

Capability: what can the candidate do, and how often does at least one attempt succeed?
Regression: can the candidate still perform previously reliable behavior consistently?
Safeguard: does a safety or privacy control block forbidden behavior?

Ask for missing product facts. Never invent policies, expected fields, thresholds, reference answers, or safety boundaries.

Classify each approved claim against four surfaces:

Outcome: the final user/environment state.
Trajectory: the risk-critical path, tools, policies, and decisions.
System: required and optional checkpoints, identity, continuity, first failure, and consequences.
Memory: only when the product promises persistence; write, retrieve, update, forget, isolation, freshness, conflict, and time semantics.

Safety, privacy, reliability, quality, and operations are cross-cutting grader categories. Capability and regression are suite lifecycle purposes.

2. Define good

Separate:

Gates: binary, disqualifying checks on one trial. Prefer deterministic code checks for objective facts, outcome state, tool calls, required structure, safety, and privacy.
Rubric criteria: gradual 1–5 judgments for useful differences among gate-clearing outputs. Use feature-specific anchors and a worked example.

Use the smallest complete set. Do not add weak gates to satisfy a fixed count. Read references/gate-design.md when a check could be either a gate or a score.

3. Create the suite

Create the files in references/evidence-contract.md. Record:

Read the full file on GitHub · 177 lines

Files

What ships with it

60 files 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.

10d ago First seen · 177 lines · 190 tokens per session scan A d8c669535a9a

Subscribe to this mod's changes

eval-engine is a skill published in the GitHub repository Abhillashjadhav/AI-PM-essential-skills (2 stars, last pushed 9d ago), licensed MIT. It adds 190 tokens to every session and 2,112 once invoked, about $0.0010 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 2026-08-31.

Claude Code Data and AI Testing agent-skills ai-product-management automation evals mcp

config-evals

Builds and maintains configuration-based evaluations on a workflow with the eval-config tool. Use when the user asks to set up, add, view, change, or remove an evaluation, score, grade, or judge a workflow's output, or measure answer quality against a test dataset. This is the only eval form Instance AI handles — it…

n8n-io/n8n · 80 tokens

agent-eval

Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…

ericrisco/rsc-harness · 79 tokens

AI System Quality Engineer

Test LLM, RAG, MCP, and agentic systems end to end. Build golden datasets, run deterministic checks and LLM judges, score retrieval, probe prompt injection, verify tool use, and gate CI on thresholds. Orchestrates DeepEval, Ragas, promptfoo, and Langfuse.

PramodDutta/qaskills · 68 tokens

test-agent

Systematisches Testen von BACH und anderen LLM-OS-Systemen. Orchestrator fuer Test- und Vergleichs-Workflows.

ellmos-ai/bach · 33 tokens

evals-router

Use when evaluating LLM or RAG outputs: audit eval coverage, analyze failed traces, write binary judge prompts, validate judges against labels, generate targeted synthetic cases, evaluate retrieval quality, or plan review tooling. Do not use for ordinary software test implementation.

jscraik/Agent-Skills · 55 tokens

agent-evaluation

You're a quality engineer who has seen agents that aced benchmarks fail spectacularly in production. You've learned that evaluating LLM agents is fundamentally different from testing traditional software—the same input can produce different outputs, and "correct" often has no single answer.

pinkpixel-dev/skills-collection-1 · 54 tokens