Best LLM evaluation skills, page 3

Finds top models for a task from official Hugging Face benchmark leaderboards, filters them to what fits your hardware, and returns a comparison table with scores.

huggingface/skills

Build an LLM evaluation and run it against the app, returning an Opik experiment with scores and its link.

comet-ml/opik-mcp

This skill should be used when the user wants to "run an evaluation", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs…

pifferologo/cloud-agents-cli

Sets up Arize Phoenix to trace, evaluate and monitor LLM applications, with instrumentation for OpenAI, LangChain and LlamaIndex and a self-hosted server.

Orchestra-Research/AI-Research-SKILLs

Investigate a single failing eval from the convex-evals system.

get-convex/convex-evals

Create new skills, modify and improve existing skills, and measure skill performance.

ZS520L/HanakoPro

Audit a website and deliver a one-page, plain-language SEO report anyone can act on, centered on a single do-this-week action.

Jwuthri/Tracely-ai

This skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison, rubric calibration, evaluator bias mitigation, confidence scoring, and automated…

guanyang/open-agent-hub

Add a new evaluator to the amp-evaluation Python library. An agent skill from wso2/agent-manager.

wso2/agent-manager

测试 use-self 替身会议的辩论质量。给定 persona + 3 个决策场景，运行完整三阶段辩论并按 5 个维度评分，输出质量报告。

YIKUAIBANZI/forge-skill

A skill your agent uses when the user wants to work on a Claude Code skill file (SKILL.md): writing one from scratch, testing whether an existing one works well, running evals or benchmarks…

avibebuilder/claude-prime

Decide which AI agent behaviors are worth an eval case, then write those cases — harness-, framework-, and language-agnostic.

agentailor/fullstack-langgraph-nextjs-agent

Написание и запуск Claude Code dynamic workflows (JS-оркестратор субагентов).

AnastasiyaW/codex-claude-code-config

Eval enablement accelerator — help customers think through "what does good look like" for their AI agent, then generate a structured eval plan and test cases they can use immediately.

microsoft/eval-guide

Analyze all failures in a convex-evals run, spawning parallel sub-agents to investigate each failure and producing a report with classifications and recommendations.

get-convex/convex-evals

Test a pre-built afm binary at any path — runs pre-flight safety checks, then any combination of unit tests, assertions, smart analysis, promptfoo evals, batch validation, OpenAI compat, GPU…

scouzi1966/maclocal-api

Best practices for creating expectations and grader files to evaluate guidance quality.

GoogleChrome/modern-web-guidance-src

AI quality judge that scores agent responses 0-10 across helpfulness, accuracy, completeness, and clarity.

Atmosphere/atmosphere

Score a Python generative-AI app's outputs on groundedness, relevance, coherence, and safety before it ships.

timothywarner-org/claude-code

Master comprehensive evaluation strategies for LLM applications, from automated metrics to human evaluation and A/B testing.

davila7/claude-code-templates

Runs a measurable keep-or-discard improvement loop against a runnable sensor, from framing a goal and KPI through baseline, judging and held-out verification.

bgauryy/octocode

Triage failing @novu/agent-evals scenarios to decide whether a failure is real or flaky, and whether to fix the playbook/prompt or the test (grader, tape, scenario, or judge).

novuhq/novu

Evaluate WooAIAssistant against a structured scenario suite with hard invariants + LLM-as-judge rubric scoring.

woocommerce/woocommerce-ios

Run evaluation pipelines on Claude Code skills to test triggering accuracy, workflow correctness, and output quality.

AgriciDaniel/skill-forge

Design well-structured agent loops with best-practice coaching and cross-model review gates before you run them.

fabricioctelles/skills

Build a repeatable eval loop that grades agent output with an LLM judge, so prompt/skill changes get scored against a baseline instead of eyeballed.

Archive228/loopkit

Creates and runs LLM evaluation suites from the omniroute CLI, follows live runs, shows scorecards, compares models and ties eval runs into CI.

diegosouzapw/OmniRoute

Conduct a local Publisher evaluation loop in five steps: scrape/run, eval, diagnose, improve, checkpoint.

malloydata/publisher

The step-by-step procedure for running this repo's Promptfoo evals with a generator and a judge over provider APIs.

maplibre/maplibre-agent-skills

Run offline Python (pydanticevals) or Node.js (logfire/evals) evaluations and review them in Logfire.

pydantic/skills

Verify a Nexus change — pick a Jest lane, write a test that can actually fail, run the in-app Obsidian CLI loop, drive the eval harness, or fix a shipped-docs drift failure.

ProfSynapse/nexus

Write or extend an E2E journey spec in evals/specs that proves a PR's change to a human reviewer.

different-ai/openwork

Inspect, query, compare, or explicitly export GitHits agent-eval history in Braintrust using the repository's verified workflow.

githits-com/githits-cli

Run a targeted local React Doctor Evals loop against an uncommitted rule change.

millionco/react-doctor

Help users build robust infrastructure for measuring, monitoring, and iterating on AI product performance using human, code-based, and LLM-as-a-judge methodologies.

RefoundAI/lenny-skills

Scaffold a new LLM evaluation suite package with Playwright config, evaluate fixture, and package files.

elastic/kibana

Trigger an on-demand @kbn/evals Buildkite run by describing what you want in plain English.

elastic/kibana

[Beta] CI-only eval regression runner using gh-aw (GitHub Agentic Workflows).

pskoett/pskoett-ai-skills

Choose, inspect, validate, and report Paperclip Runner or Product E2E evaluations while preserving evidence, provenance, cost, and failure classification.

paperclipai/paperclip

Run skill evals via evals/runner.js — wrapper validates skill names, captures stdout/stderr, persists JSON results.

ww-w-ai/bkit-claude-code

Builds an eval plan for an AI feature - error analysis on real traces, failure-mode ranking, code checks and binary LLM judges validated against human labels, CI tests, production monitoring, and a…

menkesu/awesome-pm-skills

You MUST load this skill before the skill-creator skill AND before making ANY change to, or conducting a review of ANY Agent Skill.

sammcj/agentic-coding

Audit supervised fine-tuning datasets against the behavior and task they are meant to teach.

tokenbender/agent-guides

A skill your agent uses 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…

ericrisco/rsc-harness

Set up compliance exports, drift detection, evaluations, scoring, and learning analytics

ucsandman/DashClaw

Patterns and techniques for evaluating and improving AI agent outputs.

github/awesome-copilot

Guides an interactive error analysis of LLM outputs: studies the dataset, builds a review interface, picks diverse samples and organizes the failure modes you annotate.

ai-evals-course/evals-skills

Writes fictional but realistic coaching or therapy session transcripts for evals, demos and few-shot examples, in several modalities and export formats.

glebis/claude-skills