Best agent evaluation and testing skills for Claude Code, Codex and other agents.

Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

anthropics/skills

Investigates a session where Superpowers went wrong, reads the transcripts on disk and produces an evidence-cited report, optionally prepared as a bug report for the maintainers.

obra/superpowers

Scores SKILL.md files on a nine-dimension rubric, then improves them in a keep-or-revert loop with independent judge agents, test prompts, git history and human checkpoints.

alchaincyf/darwin-skill

Validates OpenHarness features by running real multi-turn agent loops with live LLM calls against an unfamiliar codebase, checking actual tool execution.

HKUDS/OpenHarness

Evaluates an Agent Skill bundle before release for structure, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity and host portability.

rohitg00/ai-engineering-from-scratch

Benchmarks how much CodeGraph helps a coding agent on a real repository, comparing runs with and without it for a chosen local or published version.

colbymchenry/codegraph

Mines local Copilot CLI session logs for dotnet/maui to rank costly or failing runs, tag recurring failure modes, propose repo edits and emit guard evals.

dotnet/maui

Creates, revises, evaluates and publishes skills in the Open-Science app through its native host.skills composer, with optional test prompts and benchmarks.

aipoch/open-science

Evaluates the design quality of an agent skill against official specifications and patterns from existing examples, scoring it and suggesting improvements.

shareAI-lab/Kode-CLI

Scores a skill across description, content organization, writing style and structure, then produces letter grades and a prioritized improvement plan.

Galaxy-Dawn/claude-scholar

Testing framework for evaluating Databricks skills. An agent skill from databricks-solutions/ai-dev-kit.

databricks-solutions/ai-dev-kit

Diagnoses where an agent failed across runs and turns the findings into new skills, system prompt patches and knowledge entries, using the A-Evolve loop.

aiming-lab/AutoResearchClaw

Evaluate skill quality, find the weakest dimension, and apply directed improvements.

Evol-ai/SkillCompass

Call any REST API dynamically. An agent skill from NVIDIA/SkillEvaluator.

NVIDIA/SkillEvaluator

Writes and runs black-box benchmark cases for Windmill's flow, app, script, CLI and global AI generation modes, including before-and-after comparisons.

windmill-labs/windmill

Builds agent evaluations in stages: inspect the repository and traces, agree a Task Spec with you, then build, audit and run a Harbor task with an independent verifier.

langchain-ai/langchain-skills

Lets a Hermes agent run Autocontext scenarios, inspect Hermes curator state, export reusable knowledge and prepare local MLX or CUDA training data through the autoctx CLI.

greyhaven-ai/autocontext

Designs and verifies a deterministic grader that measures whether a GitHub Agentic Workflow run reached its real-world or repository outcome.

github/gh-aw

End-to-end agent evaluation and improvement pipeline. An agent skill from kayba-ai/agentic-context-engine.

kayba-ai/agentic-context-engine

Coordinate multi-agent development pipelines using shared JSON task files.

win4r/team-tasks

Runs blind pairwise comparisons of Octocode against a gh-based baseline over markdown research questions, scored by total characters through the model rather than self-report.

bgauryy/octocode

Checks changes to the senpi coding agent by driving the real CLI from source in an isolated sandbox, over RPC, terminal UI, mock model and CLI smoke channels.

code-yeongyu/senpi

驱动 One-Eval 对 API 或本地模型做端到端评测，覆盖纯文本、多模态、代码生成、函数调用和 Agent benchmark。当用户想评测模型在一个或多个 benchmark 上的表现、比较分数、补充 metric，或生成图文评测报告时使用本 skill。

OpenDCAI/One-Eval

Runs LLM-based rubric judging on agent output and loops revise-and-rejudge rounds until a quality threshold is met.

greyhaven-ai/autocontext

Runs existing Harbor evaluation jobs against a local LobeHub build or LobeHub Cloud, with preflight checks, resume support, and failure triage.

lobehub/lobehub

Operates or analyzes a LoopX-managed benchmark experiment: launching runs, maintaining the experiment board, qualifying integrity, and writing case insights.

loopx-project/loopx

AWS Bedrock AgentCore comprehensive expert for deploying and managing AI agents at scale.

zxkane/aws-skills

Evaluates a repository's agent harness (AGENTS.md, rules, skills) for broken paths, redundant instructions and usefulness, and stops at reports.

tech-leads-club/agent-skills

Runs a reference agent (Codex or Claude Code) and Qwen Code on the same scenario, captures HTTP and terminal traces, and compares them until behavior matches.

QwenLM/qwen-code

Required for 4+ step requests; add tasks at start and update status after each step.

NVIDIA/SkillEvaluator

A skill your agent uses when a user wants to create, run, or analyze evaluation suites for Microsoft 365 Copilot declarative agents with the public @microsoft/m365-copilot-eval CLI.

microsoft/work-iq

Measures whether agents actually follow a skill, rule or agent definition by generating scenarios at three strictness levels and scoring tool-call traces.

affaan-m/ECC

Walks you through drafting, testing, evaluating and tuning a skill for OpenCode, from an intake interview to description optimization.

antongulin/opencode-skill-creator

Agent Script DSL for deterministic Agentforce agents. An agent skill from Jaganpro/sf-skills.

Jaganpro/sf-skills

Runs and interprets a skill's Caliper eval: how often it succeeds over repeated attempts, whether it triggers at all, and whether it beats the agent without it.

edonadei/caliper

Ultimate Claude Code skill creator and architect. An agent skill from AgriciDaniel/skill-forge.

AgriciDaniel/skill-forge

Scores an agent's finished work with a three-stage pipeline: free mechanical checks, an advisory semantic review, and an optional multi-model consensus vote.

Q00/ouroboros

Adds a new task to the bench-swe pipeline from a real GitHub bug-fix issue or pull request, then checks the generated task file and patch.

ory/lumen

Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end.

microsoft/GitHub-Copilot-for-Azure

A skill your agent uses when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation.

NVIDIA/SkillEvaluator

Run the weak-agent adversarial test harness against docx-cli.

kklimuk/docx-cli

Mines local Claude Code session transcripts with a deterministic Python pipeline to show what the agent is actually used for, how often it fails and what it costs.

amd/gaia

Runs caliper's smoke evals against the real agent CLIs after a harness or MCP change, with a dry-run plan, failure triage and a report to attach to the PR.

edonadei/caliper

Contrasts successful and failed agent runs of the same task and derives guidelines backed by evidence from transcripts, tool calls and outcome judgments.

AgentToolkit/altk-evolve

Evaluates agent skills with a Go CLI that runs YAML-defined benchmarks, compares runs and scores the quality of SKILL.md frontmatter.

microsoft/waza

Evaluate Expo skills in this repo end-to-end - trigger accuracy, generated code quality, and runtime screenshots on iOS simulator and Android emulator via Expo Go (web optional).

expo/skills

Score one analytical answer against a verified golden, and score which of the entities the golden depends on retrieval delivered to the answerer.

malloydata/publisher

Designs, evaluates and improves the harness around an AI agent: tool permissions, approval gates, state, memory, evals and observability, with phased plans.

NateBJones-Projects/OB1