evaluating-ai-output

evaluating-ai-output is a skill for Claude Code, Codex from Cristhianzl/claude-skills-czl. It costs 106 tokens per session (879 once invoked), scanned A, original, MIT.

A testing approach for language-model and other AI features, where outputs can vary between runs. It defines what good results mean and measures them across repeated attempts.

In plain words
What is it for?
Writing evaluations for agents, prompts, retrieval systems, classifiers, and other AI features, then grading results with code, models, or people.
Why use it?
A single successful response does not show that an AI feature is reliable.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Writing evaluations for agents, prompts, retrieval systems, classifiers, and other AI features, then grading results with code, models, or people.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cristhianzl/claude-skills-czl/evaluating-ai-output
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.

Any agent
npx skills add Cristhianzl/claude-skills-czl --skill evaluating-ai-output
Clone the repo
git clone --depth 1 https://github.com/Cristhianzl/claude-skills-czl

Made for: Claude Code, Codex.

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 evaluating-ai-output

README.md
[![agentmods](https://agentmods.dev/badge/skills/cristhianzl/claude-skills-czl/evaluating-ai-output/github.svg)](https://agentmods.dev/skills/cristhianzl/claude-skills-czl/evaluating-ai-output)
Your own site
<a href="https://agentmods.dev/skills/cristhianzl/claude-skills-czl/evaluating-ai-output"><img src="https://agentmods.dev/badge/skills/cristhianzl/claude-skills-czl/evaluating-ai-output/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.

agentmods 80×15 button for evaluating-ai-output

Your own site · 80×15
<a href="https://agentmods.dev/skills/cristhianzl/claude-skills-czl/evaluating-ai-output"><img src="https://agentmods.dev/badge/skills/cristhianzl/claude-skills-czl/evaluating-ai-output.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 879 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00106 $0.00879
Opus 5 $0.00053 $0.00439
Sonnet 5 $0.00021 $0.00176
Haiku 4.5 $0.00011 $0.00088

Measured 12d ago against content hash 347be76034c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

evaluating-ai-output 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 12d 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.

configs/agnostic/skills/evaluating-ai-output/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evaluating AI output

Code is deterministic; LLM output isn't. A feature that "worked once" can fail the next call on the same input. Evals are the unit tests of AI work — they measure how often and how well the output meets the bar, not just that it can.

Read first (always)

List learnings/ and read anything relevant — provider quirks, rubric calibration, and known-flaky cases for this project belong there.

Define expected behavior BEFORE you implement

Write the eval first: the inputs, what a good output looks like, and what must never happen. If you can't state how you'd grade it, you don't yet understand the feature.

Measure across repeated trials

Run each case k times (LLM output varies) and report:

  • pass@kat least one of k attempts succeeds. Measures capability ("can it do this at all?"). Typical target: pass@3 > 90%.
  • pass^kall k attempts succeed. Measures stability/reliability ("does it do this every time?"). Use for critical paths (auth, money, irreversible actions). pass^3 means 3 consecutive clean runs.

A feature can have high pass@k but low pass^k — impressive once, unreliable in production. Match the metric to the risk.

Three graders (use the cheapest that's trustworthy)

Grader How Use for
Code-based Deterministic check — regex/grep, schema/JSON validation, an assertion, a tool call that must appear Anything machine-verifiable (format, presence, exact values). Always prefer this.
Model-based A model scores the output 1–5 against a written rubric Quality/judgment that code can't check (relevance, tone, reasoning). Calibrate the rubric on a few human-labeled examples.
Human A person reviews, tagged risk LOW / MED / HIGH High-stakes or ambiguous cases. Never fully automate security review — keep a human in the loop there.

Build the eval set

Cover representative cases, adversarial/edge cases (the failure modes from your threat model — see skills/threat-modeling), and regression cases (every bug becomes a permanent eval). Keep a baseline (committed scores) and gate changes on "no regression vs. baseline". Store the eval set, the baseline, and run logs alongside the feature.

Read the full file on GitHub · 55 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. 12d ago First seen · 55 lines · 106 tokens per session scan A 347be76034c7

Subscribe to this mod's changes

evaluating-ai-output is a skill published in the GitHub repository Cristhianzl/claude-skills-czl (5 stars, last pushed yesterday), licensed MIT. It adds 106 tokens to every session and 879 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

oracle-grill-me

Grill the user relentlessly about a plan, decision, or idea, maintaining the project's domain model (CONTEXT.md, ADRs) as decisions crystallise. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

martinffx/atelier · 58 tokens

evaluating-llms-harness

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

NousResearch/hermes-agent · 29 tokens

cli-eval

Create and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with CI workflows from the CLI.

diegosouzapw/OmniRoute · 34 tokens

model-merging

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task…

davila7/claude-code-templates · 73 tokens

data-quality-frameworks

Implement data quality validation with Great Expectations, dbt tests, and data contracts. Use when building data quality pipelines, implementing validation rules, or establishing data contracts.

wshobson/agents · 37 tokens

dbt-transformation-patterns

Master dbt (data build tool) for analytics engineering with model organization, testing, documentation, and incremental strategies. Use when building data transformations, creating data models, or implementing analytics engineering best practices.

wshobson/agents · 47 tokens