llm-evaluation

Guidance for measuring the quality of features powered by large language models or agents using fixed test examples and defined metrics.

In plain words
What is it for?
Use it to create golden test sets, compare model or prompt versions, run offline or online evaluations, and preserve production failures as tests.
Why use it?
It replaces subjective guesses with repeatable checks that reveal regressions after prompt or model changes.

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/phuonghx/aim-cli/llm-evaluation
Any agent
npx skills add phuonghx/aim-cli --skill llm-evaluation
Clone the repo
git clone --depth 1 https://github.com/phuonghx/aim-cli

Made for: Claude Code, Codex.

Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,523 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 $0.00095 $0.01523
Opus 5 $0.00048 $0.00762
Sonnet 5 $0.00019 $0.00305
Haiku 4.5 $0.00010 $0.00152

Measured yesterday against content hash bed81fb52e43, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

llm-evaluation 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.

aim/templates/aim-agents/skills/llm-evaluation/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM Evaluation

If you cannot measure it, you are tuning prompts in the dark. Build the eval before you tune.

When to add evals

  • Before tuning a prompt or swapping models — you need a baseline.
  • When shipping any LLM feature that real users or systems depend on.
  • After every production bug — turn the failing input into a permanent test case.
  • When "it feels better" is the only evidence a change is an improvement.

Skip formal evals only for throwaway scripts. Anything that ships gets at least a small fixed set.

Build a golden dataset

A golden set is a fixed collection of (input, expected) pairs that defines "correct" for your task.

  • Start small, start real. 20–50 hand-curated cases beat 5,000 synthetic ones. Grow over time.
  • Cover the distribution: common cases, edge cases, the null/empty case, and known past failures.
  • Freeze it. The set must be stable so scores are comparable across runs. Version it (eval/v2).
  • Label deliberately. Each expected should be defensible; ambiguous labels poison every metric.
  • Keep it in the repo, reviewed like code.

Avoid leakage

Leakage = your eval secretly rewards memorization or itself, inflating scores.

  • Do not put eval examples into the prompt's few-shot block. Test and demonstration sets must be disjoint.
  • Do not tune the prompt by staring at eval answers — tune on a separate dev split, report on a held-out split.
  • Watch for train/test contamination when inputs come from public data the model may have seen.
  • If you use an LLM judge, the judge should not be the same call that produced the answer.

Metrics: pick by task

Metric Use for How
Exact / normalized match Classification, extraction, enums Compare after normalizing case/whitespace
Field-level / JSON match Structured output Compare per key; report which fields fail
Rubric (LLM-as-judge) Open-ended generation, summaries Score against an explicit rubric, 1–5
pass@k Code / tasks with a verifier Sample k; pass if any sample passes the check
Task success Agents / tool use Did it reach the goal state? (programmatic check)
Regression rate Any fixed set % of previously-passing cases now failing

Read the full file on GitHub · 129 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. yesterday First seen · 129 lines · 95 tokens per session scan A bed81fb52e43

Subscribe to this mod's changes

llm-evaluation is a skill published in the GitHub repository phuonghx/aim-cli (1 stars, last pushed 2mo ago), licensed MIT. It adds 95 tokens to every session and 1,523 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

hs-release

Cut a core Hindsight release (vX.Y.Z) and open the changelog + blog PR. Use when asked to cut/start a release, bump the version, or publish a new Hindsight version.

vectorize-io/hindsight · 45 tokens

hindsight-local

Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).

vectorize-io/hindsight · 32 tokens

research-repository

Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.

Owl-Listener/designer-skills · 43 tokens

design-negotiation

Advocate for design quality, scope, and timeline with partners and leadership using evidence and shared goals. Use in the conversation itself. For the commercial vocabulary behind it, use business-design (ux-strategy).

Owl-Listener/designer-skills · 48 tokens

user-persona

Build research-grounded personas with goals, frustrations, and behavioural patterns. Use when decisions need a consistent user reference. For one session's emotional snapshot use empathy-map; for motivation framing use jobs-to-be-done.

Owl-Listener/designer-skills · 50 tokens

version-control-strategy

Define version control for design files, components, and libraries — branching, naming, and release. Use when file history is chaotic. For design system contribution rules, use design-system-governance (design-systems).

Owl-Listener/designer-skills · 50 tokens