agentsclimarketplace

Evals & benchmarks

946 rows, by stacks then stars

  • Skill creator

    FridrichMethod/awesome-skills/skills/skill-creator Skill

    no license11 repo

    Curated, auto-synced collection of 2,000+ Claude Code & Codex skills for AI4Protein, bioinformatics, AI development, and academic paper writing. One curl command installs them all.

  • Lm evaluation harness

    kevinnft/ai-agent-skills/skills/mlops/evaluation/lm-evaluation-harness Skill

    11 repo

    191 attribution-first agent skills for Hermes Agent, Claude Code, Cursor — one installer, 28 categories, searchable catalog. See NOTICE for upstream attribution.

  • Hardening windows endpoint with cis benchmark

    Mikaru0Mystic/sectinel/arsenal/Anthropic-Cybersecurity-Skills/skills/hardening-windows-endpoint-with-cis-benchmark Skill

    11 repo

    Open-source security arsenal for AI coding agents: 784 cybersecurity skills, scanner integrations, and a security MCP for Claude Code, Cursor, opencode, Gemini CLI, Cline, and any agentskills.io agent. Mapped to OWASP, MITRE ATT&CK, NIST CSF, D3FEND, ATLAS.

  • Hardening linux endpoint with cis benchmark

    Mikaru0Mystic/sectinel/arsenal/Anthropic-Cybersecurity-Skills/skills/hardening-linux-endpoint-with-cis-benchmark Skill

    11 repo

    Open-source security arsenal for AI coding agents: 784 cybersecurity skills, scanner integrations, and a security MCP for Claude Code, Cursor, opencode, Gemini CLI, Cline, and any agentskills.io agent. Mapped to OWASP, MITRE ATT&CK, NIST CSF, D3FEND, ATLAS.

  • Performing kubernetes cis benchmark with kube bench

    Mikaru0Mystic/sectinel/arsenal/Anthropic-Cybersecurity-Skills/skills/performing-kubernetes-cis-benchmark-with-kube-bench Skill

    11 repo

    Open-source security arsenal for AI coding agents: 784 cybersecurity skills, scanner integrations, and a security MCP for Claude Code, Cursor, opencode, Gemini CLI, Cline, and any agentskills.io agent. Mapped to OWASP, MITRE ATT&CK, NIST CSF, D3FEND, ATLAS.

  • Nasde benchmark calibration

    NoesisVision/nasde-toolkit/.claude/skills/nasde-benchmark-calibration Skill

    11 repo

    CLI for benchmarks & evals of AI coding agents — on tasks you already understand, using your Claude / Codex / Gemini individual subscriptions or API keys.

  • Nasde benchmark creator

    NoesisVision/nasde-toolkit/.claude/skills/nasde-benchmark-creator Skill

    11 repo

    CLI for benchmarks & evals of AI coding agents — on tasks you already understand, using your Claude / Codex / Gemini individual subscriptions or API keys.

  • Nasde benchmark from history

    NoesisVision/nasde-toolkit/.claude/skills/nasde-benchmark-from-history Skill

    11 repo

    CLI for benchmarks & evals of AI coding agents — on tasks you already understand, using your Claude / Codex / Gemini individual subscriptions or API keys.

  • Nasde benchmark from public repos

    NoesisVision/nasde-toolkit/.claude/skills/nasde-benchmark-from-public-repos Skill

    11 repo

    CLI for benchmarks & evals of AI coding agents — on tasks you already understand, using your Claude / Codex / Gemini individual subscriptions or API keys.

  • Nasde benchmark runner

    NoesisVision/nasde-toolkit/.claude/skills/nasde-benchmark-runner Skill

    11 repo

    CLI for benchmarks & evals of AI coding agents — on tasks you already understand, using your Claude / Codex / Gemini individual subscriptions or API keys.

  • Trtc eval

    Tencent-RTC/agent-skills/.claude/skills/trtc-eval Skill

    11 repo

    TRTC AI Integration Assistant - helps developers integrate Tencent Real-Time Communication SDKs (Chat, Call, RTC Engine, Live, Conference) across Web, Android, iOS, Flutter, and Electron.

  • Ml model eval benchmark

    0x-Professor/Agent-Skills-Hub/skills/ml-model-eval-benchmark Skill

    10 repo

    Public skill pack for AI coding/automation/penetration-testing agents.

  • Llm evaluation

    ckorhonen/claude-skills/skills/llm-evaluation Skill

    10 repo

    A curated collection of skills for Claude Code and Codex — specialized capabilities across development, design, AI, security, and more. Part of the cdd.dev/skills family.

  • Eval surfer

    di37/EvalSurfer/.cursor/skills/eval-surfer Skill

    28 days old10 repo

    Skill-first, agent-native evaluation protocol for AI apps

  • Eval surfer

    di37/EvalSurfer/skills/eval-surfer Skill

    28 days old10 repo

    Skill-first, agent-native evaluation protocol for AI apps

  • Skill creator

    Flexonze/claude-init/.claude/skills/skill-creator Skill

    10 repo

    Automatically generate Claude Code configs tailored for your project.

  • Pydantic evals

    Fuenfgeld/pydantic-ai-skills/skills/pydantic-evals Skill

    10 repo

    Production-ready Claude Code skills for building AI agents with Pydantic AI. Includes dependency injection, tools, validators, streaming, multi-agent orchestration, and evaluation framework patterns.

  • Skill creator

    isomoes/skills/.agents/skills/skill-creator Skill

    10 repo

    Custom skills for agents to support academic paper writing and thesis management

  • Hardening linux endpoint with cis benchmark

    autohandai/community-skills/hardening-linux-endpoint-with-cis-benchmark Skill

    9 repo

    A collection of curated, useful, and safe skills for Autohand Code CLI Agent

  • Hardening windows endpoint with cis benchmark

    autohandai/community-skills/hardening-windows-endpoint-with-cis-benchmark Skill

    9 repo

    A collection of curated, useful, and safe skills for Autohand Code CLI Agent

  • Nvidia model optimizer launching evals

    autohandai/community-skills/nvidia-model-optimizer-launching-evals Skill

    9 repo

    A collection of curated, useful, and safe skills for Autohand Code CLI Agent

  • Nvidia nemo evaluator byob

    autohandai/community-skills/nvidia-nemo-evaluator-byob Skill

    9 repo

    A collection of curated, useful, and safe skills for Autohand Code CLI Agent

  • Nvidia nemo evaluator launcher launching evals

    autohandai/community-skills/nvidia-nemo-evaluator-launcher-launching-evals Skill

    9 repo

    A collection of curated, useful, and safe skills for Autohand Code CLI Agent

  • Nvidia nemo gym add benchmark

    autohandai/community-skills/nvidia-nemo-gym-add-benchmark Skill

    9 repo

    A collection of curated, useful, and safe skills for Autohand Code CLI Agent

  • Performing kubernetes cis benchmark with kube bench

    autohandai/community-skills/performing-kubernetes-cis-benchmark-with-kube-bench Skill

    9 repo

    A collection of curated, useful, and safe skills for Autohand Code CLI Agent

  • Skill creator

    autohandai/community-skills/skill-creator Skill

    9 repo

    A collection of curated, useful, and safe skills for Autohand Code CLI Agent

  • Prompt eval debug

    emaraschio/cursor-commands/.cursor/skill-contracts/prompt-eval-debug Skill

    9 repo

    Production-grade Cursor slash commands with paired skill contracts, behavioral evals, and ship-gate CI. Install as a user plugin.

  • Prompt eval debug

    emaraschio/cursor-commands/plugin/.cursor/skill-contracts/prompt-eval-debug Skill

    9 repo

    Production-grade Cursor slash commands with paired skill contracts, behavioral evals, and ship-gate CI. Install as a user plugin.

  • Factory verification

    nonlinear-xyz/factory-kit/skills/factory-verification Skill

    9 repo

    Personal Claude Code factory — synthesized cross-build skills, specialist subagents, and slash commands. Phase 0.

  • Agent eval framework builder

    Notysoty/openagentskills/skills/agent-eval-framework-builder Skill

    9 repo

    A community-driven library of reusable AI agent skills for Claude Code, Cursor, Codex, Cline, and more.

  • Hallucination risk reviewer

    Notysoty/openagentskills/skills/hallucination-risk-reviewer Skill

    9 repo

    A community-driven library of reusable AI agent skills for Claude Code, Cursor, Codex, Cline, and more.

  • Reproduce benchmark

    pantheon-org/tekhne/skills/documentation/research/reproduce-benchmark Skill

    9 repo

    Agents Skills

  • Create a skill

    psenger/ai-agent-skills/skills/create-a-skill Skill

    9 repo

    Production-ready AI agent skills for Claude Code, Codex, Cursor, and the Agent Skills Open Standard

  • Skill creator

    s-hiraoku/synapse-a2a/plugins/synapse-a2a/skills/skill-creator Skill

    no license9 repo
  • Skill creator

    s-hiraoku/synapse-a2a/.agents/skills/skill-creator Skill

    no license9 repo
  • Benchmark email automation

    sinhoneyy/master-skills/skills/benchmark-email-automation Skill

    no license9 repo

    Unified skill library for Claude, Codex, Cursor, Antigravity & AI agents — 2,658 skills across 15 domains

  • Cross eval

    sinhoneyy/master-skills/skills/cross-eval Skill

    no license9 repo

    Unified skill library for Claude, Codex, Cursor, Antigravity & AI agents — 2,658 skills across 15 domains

  • Eval

    sinhoneyy/master-skills/skills/eval Skill

    no license9 repo

    Unified skill library for Claude, Codex, Cursor, Antigravity & AI agents — 2,658 skills across 15 domains

  • Hugging face community evals

    sinhoneyy/master-skills/skills/hugging-face-community-evals Skill

    no license9 repo

    Unified skill library for Claude, Codex, Cursor, Antigravity & AI agents — 2,658 skills across 15 domains

  • Eval

    sinhoneyy/master-skills/plugins/master-skills-ai-agent-builder/skills/eval Skill

    no license9 repo

    Unified skill library for Claude, Codex, Cursor, Antigravity & AI agents — 2,658 skills across 15 domains

  • Self eval

    sinhoneyy/master-skills/plugins/master-skills-backend-engineer/skills/self-eval Skill

    no license9 repo

    Unified skill library for Claude, Codex, Cursor, Antigravity & AI agents — 2,658 skills across 15 domains

  • Benchmark email automation

    sinhoneyy/master-skills/plugins/master-skills-marketing-growth/skills/benchmark-email-automation Skill

    no license9 repo

    Unified skill library for Claude, Codex, Cursor, Antigravity & AI agents — 2,658 skills across 15 domains

  • Self eval

    sinhoneyy/master-skills/skills/self-eval Skill

    no license9 repo

    Unified skill library for Claude, Codex, Cursor, Antigravity & AI agents — 2,658 skills across 15 domains

  • Skill creator

    adryanmoldokkr32-pixel/anthropics-skills/skills/skill-creator Skill

    no license8 repo

    Official Anthropic Agent Skills — frontend-design, claude-api, docx, pptx, xlsx, pdf, canvas-design, mcp-builder and more

  • Uw skill creator

    IdoCohen560/claude-unity-game-studio/examples/my-first-game/.claude/skills/uw-skill-creator Skill

    8 repo

    AI-powered Unity game development studio for Claude Code - 49 agents, 120+ skills, and a full studio hierarchy that turns a single AI session into a coordinated game dev team. View more about me in my portfolio.

  • Uw skill creator

    IdoCohen560/claude-unity-game-studio/unity-ai-workflow/.claude/skills/uw-skill-creator Skill

    8 repo

    AI-powered Unity game development studio for Claude Code - 49 agents, 120+ skills, and a full studio hierarchy that turns a single AI session into a coordinated game dev team. View more about me in my portfolio.

  • Evals router

    jscraik/Agent-Skills/Skills/agent-ops/evals-router Skill

    8 repo

    Governed skill foundry and Skills SDK for Codex/AI coding agents: author, validate, evaluate, and sync runtime projections through ask.

  • Sdk scenario generator

    jscraik/Agent-Skills/Skills/agent-ops/sdk-scenario-generator Skill

    8 repo

    Governed skill foundry and Skills SDK for Codex/AI coding agents: author, validate, evaluate, and sync runtime projections through ask.

  • He eval report

    jscraik/Agent-Skills/Plugins/harness-engineering/skills/he-eval-report Skill

    8 repo

    Governed skill foundry and Skills SDK for Codex/AI coding agents: author, validate, evaluate, and sync runtime projections through ask.

  • Sy eval report

    jscraik/Agent-Skills/Plugins/synaipse-harness/skills/sy-eval-report Skill

    8 repo

    Governed skill foundry and Skills SDK for Codex/AI coding agents: author, validate, evaluate, and sync runtime projections through ask.

  • Eval

    julienamorgan/signal-prospecting-kit/eval Skill

    no license8 repo

    Find B2B prospects the moment they're in-market. Six Claude Code skills that detect buying signals, surface the accounts showing them, and write outreach that references something real.

  • Skill creator

    JustMichael-80/MasterVault/skills/anthropic/skills/skill-creator Skill

    21 days old8 repo

    An orientation protocol for LLM sessions — plus a curated Claude skills collection

  • Skill creator

    kyopark2014/sam-project/application/skills/skill-creator Skill

    8 repo

    It is an agent based on Strands SDK using MCP and SKILL.

  • Benchmark

    luiseiman/dotforge/skills/benchmark Skill

    8 repo

    Configuration governance for Claude Code. Bootstrap, audit, sync, and evolve .claude/ across projects.

  • Sota llm engineering

    martinholovsky/SOTA-skills/skills/sota-llm-engineering Skill

    8 repo

    State-of-the-Art (2026) AI/LLM engineering skills/agents for building and auditing software — 40+ domain & language skills, BUILD/AUDIT modes, audit checklists.

  • Hallucination guard

    Momo2323-ui/claude-orchestra/skills/hallucination-guard Skill

    8 repo

    An operating system for your Claude Code skills, agents & MCPs — organize everything into auto-routing orchestras.

  • Agentic eval

    mouadja02/skills/skills/agent-eval/agentic-eval Skill

    no license8 repo

    A curated collection of agent skills for your AI agents - engineering craft, prompt engineering, design, growth marketing, ...

  • Eval driven dev

    mouadja02/skills/skills/agent-eval/eval-driven-dev Skill

    no license8 repo

    A curated collection of agent skills for your AI agents - engineering craft, prompt engineering, design, growth marketing, ...

  • Harness benchmarking

    mouadja02/skills/skills/agent-eval/harness-benchmarking Skill

    no license8 repo

    A curated collection of agent skills for your AI agents - engineering craft, prompt engineering, design, growth marketing, ...

  • Arize evaluator

    mouadja02/skills/skills/llm-tooling/arize-evaluator Skill

    no license8 repo

    A curated collection of agent skills for your AI agents - engineering craft, prompt engineering, design, growth marketing, ...