508 of these skill files have been read, by 499 distinct authors, and what they tell an agent counted. What Evals & benchmarks authors agree on, and what they forbid

• 301

  Benchmark kernel

  ComeOnOliver/skillshub/skills/aiskillstore/marketplace/flashinfer-ai/benchmark-kernel · Skill

  59★ repo

  🧠 The right skill, one API call. AI agent skills registry with token-efficient skill resolution. 5,000+ skills from 500+ top repos.

• 302

  Eval

  ComeOnOliver/skillshub/skills/alirezarezvani/claude-skills/eval · Skill

  59★ repo

  🧠 The right skill, one API call. AI agent skills registry with token-efficient skill resolution. 5,000+ skills from 500+ top repos.

• 303

  Skill creator

  ComeOnOliver/skillshub/skills/anthropics/skills/skill-creator · Skill

  59★ repo

  🧠 The right skill, one API call. AI agent skills registry with token-efficient skill resolution. 5,000+ skills from 500+ top repos.

• 304

  Ue benchmark

  ComeOnOliver/skillshub/skills/blackplume233/UnrealMCPHub/ue-benchmark · Skill

  59★ repo

  🧠 The right skill, one API call. AI agent skills registry with token-efficient skill resolution. 5,000+ skills from 500+ top repos.

• 305

  Competitive feature benchmark

  ComeOnOliver/skillshub/skills/comsky/remy-skill-recipes/competitive-feature-benchmark · Skill

  59★ repo

  🧠 The right skill, one API call. AI agent skills registry with token-efficient skill resolution. 5,000+ skills from 500+ top repos.

• 306

  Skill creator

  ComeOnOliver/skillshub/skills/countbot-ai/CountBot/skill-creator · Skill

  59★ repo

  🧠 The right skill, one API call. AI agent skills registry with token-efficient skill resolution. 5,000+ skills from 500+ top repos.

• 307

  Promptfoo evaluation

  ComeOnOliver/skillshub/skills/daymade/claude-code-skills/promptfoo-evaluation · Skill

  59★ repo

  🧠 The right skill, one API call. AI agent skills registry with token-efficient skill resolution. 5,000+ skills from 500+ top repos.

• 308

  Skill creator

  ComeOnOliver/skillshub/skills/daymade/claude-code-skills/skill-creator · Skill

  59★ repo

  🧠 The right skill, one API call. AI agent skills registry with token-efficient skill resolution. 5,000+ skills from 500+ top repos.

• 309

  Agentic eval

  ComeOnOliver/skillshub/skills/github/awesome-copilot/agentic-eval · Skill

  59★ repo

  🧠 The right skill, one API call. AI agent skills registry with token-efficient skill resolution. 5,000+ skills from 500+ top repos.

• 310

  Eval driven dev

  ComeOnOliver/skillshub/skills/github/awesome-copilot/eval-driven-dev · Skill

  59★ repo

  🧠 The right skill, one API call. AI agent skills registry with token-efficient skill resolution. 5,000+ skills from 500+ top repos.

• 311

  Skill creator

  ComeOnOliver/skillshub/skills/guanyang/antigravity-skills/skill-creator · Skill

  59★ repo

  🧠 The right skill, one API call. AI agent skills registry with token-efficient skill resolution. 5,000+ skills from 500+ top repos.

• 312

  Benchmark suite creator

  ComeOnOliver/skillshub/skills/jeremylongshore/claude-code-plugins-plus-skills/benchmark-suite-creator · Skill

  59★ repo

  🧠 The right skill, one API call. AI agent skills registry with token-efficient skill resolution. 5,000+ skills from 500+ top repos.

• 313

  Security benchmark runner

  ComeOnOliver/skillshub/skills/jeremylongshore/claude-code-plugins-plus-skills/security-benchmark-runner · Skill

  59★ repo

  🧠 The right skill, one API call. AI agent skills registry with token-efficient skill resolution. 5,000+ skills from 500+ top repos.

• 314

  Alterlab scholar eval

  AlterLab-IEU/AlterLab-Academic-Skills/skills/writing-tools/alterlab-scholar-eval · Skill

  58★ repo

  239 evaluated academic Claude/agent skills across 17 research domains (bioinformatics, data science, clinical, social-science methods, Turkish academia & more). Executable eval per skill, deterministic citation verifier, research→write→review→publish pipeline, and a skill-finder front door. Claude Code, Cursor, Codex, Gemini CLI & Copilot.

• 315

  Building with llms

  liqiongyu/lenny_skills_plus/skills/building-with-llms · Skill

  51★ repo

  86 agent-executable skill packs converted from RefoundAI’s Lenny skills (unofficial). Works with Codex + Claude Code.

• 316

  Autoresearch

  adriannoes/awesome-agentic-ai/cursor-claude-codex/skills/autoresearch · Skill

  48★ repo

  329 agent skills (Cursor, Claude Code & Codex), 5,380 OpenClaw skills, 201 ML notebooks, 7 textbooks, 52 research papers, 17 industry reports for PMs, Designers & Developers.

• 317

  Run deep swe

  adriannoes/awesome-agentic-ai/cursor-claude-codex/skills/david-ondrej/agent-orchestration/run-deep-swe · Skill

  48★ repo

  329 agent skills (Cursor, Claude Code & Codex), 5,380 OpenClaw skills, 201 ML notebooks, 7 textbooks, 52 research papers, 17 industry reports for PMs, Designers & Developers.

• 318

  Evals

  adriannoes/awesome-agentic-ai/cursor-claude-codex/skills/igoruehara-spec-driven/skills/evals · Skill

  48★ repo

  329 agent skills (Cursor, Claude Code & Codex), 5,380 OpenClaw skills, 201 ML notebooks, 7 textbooks, 52 research papers, 17 industry reports for PMs, Designers & Developers.

• 319

  Creator commercial value benchmark

  allinherog-star/ai-skills/skills/creator-commercial-value-benchmark · Skill

  no license47★ repo

  AI Skills（ai-skills.ai）是一个面向各行各业的 AI 技能库。可直接用于openclaw，Hermes，qclaw，claude code，codex等智能体平台。为你的职业发展、行业竞争力，增加更多可能。

• 320

  Skill creator

  nota-america/forgecat-agent-profiles/profiles/anthropics/claude-plugins-official/anthropics_claude-plugins-official_skill-creator/for-claude/.claude/skills/skill-creator · Skill

  46★ repo

  Production-ready AI agent profiles for Claude Code, Cursor, and Codex. Search, install, and contribute ForgeCat packages.

• 321

  Skill creator

  nota-america/forgecat-agent-profiles/profiles/anthropics/claude-plugins-official/anthropics_claude-plugins-official_skill-creator/for-codex/.agents/skills/skill-creator · Skill

  46★ repo

  Production-ready AI agent profiles for Claude Code, Cursor, and Codex. Search, install, and contribute ForgeCat packages.

• 322

  Skill creator

  nota-america/forgecat-agent-profiles/profiles/anthropics/claude-plugins-official/anthropics_claude-plugins-official_skill-creator/for-cursor/.cursor/skills/skill-creator · Skill

  46★ repo

  Production-ready AI agent profiles for Claude Code, Cursor, and Codex. Search, install, and contribute ForgeCat packages.

• 323

  Skill creator

  nota-america/forgecat-agent-profiles/profiles/anthropics/claude-plugins-official/anthropics_claude-plugins-official_skill-creator/for-forgecat/skills/skill-creator · Skill

  46★ repo

  Production-ready AI agent profiles for Claude Code, Cursor, and Codex. Search, install, and contribute ForgeCat packages.

• 324

  Skill creator

  nota-america/forgecat-agent-profiles/profiles/anthropics/skills/anthropics_skills_skill-creator/for-claude/.claude/skills/skill-creator · Skill

  46★ repo

  Production-ready AI agent profiles for Claude Code, Cursor, and Codex. Search, install, and contribute ForgeCat packages.

• 325

  Skill creator

  nota-america/forgecat-agent-profiles/profiles/anthropics/skills/anthropics_skills_skill-creator/for-codex/.agents/skills/skill-creator · Skill

  46★ repo

  Production-ready AI agent profiles for Claude Code, Cursor, and Codex. Search, install, and contribute ForgeCat packages.

• 326

  Skill creator

  nota-america/forgecat-agent-profiles/profiles/anthropics/skills/anthropics_skills_skill-creator/for-cursor/.cursor/skills/skill-creator · Skill

  46★ repo

  Production-ready AI agent profiles for Claude Code, Cursor, and Codex. Search, install, and contribute ForgeCat packages.

• 327

  Skill creator

  nota-america/forgecat-agent-profiles/profiles/anthropics/skills/anthropics_skills_skill-creator/for-forgecat/skills/skill-creator · Skill

  46★ repo

  Production-ready AI agent profiles for Claude Code, Cursor, and Codex. Search, install, and contribute ForgeCat packages.

• 328

  Ai hallucination fact check protocol

  nota-america/forgecat-agent-profiles/profiles/garethmanning/education-agent-skills/for-claude/.claude/skills/ai-hallucination-fact-check-protocol · Skill

  46★ repo

  Production-ready AI agent profiles for Claude Code, Cursor, and Codex. Search, install, and contribute ForgeCat packages.

• 329

  Ai hallucination fact check protocol

  nota-america/forgecat-agent-profiles/profiles/garethmanning/education-agent-skills/for-codex/.agents/skills/ai-hallucination-fact-check-protocol · Skill

  46★ repo

  Production-ready AI agent profiles for Claude Code, Cursor, and Codex. Search, install, and contribute ForgeCat packages.

• 330

  Ai hallucination fact check protocol

  nota-america/forgecat-agent-profiles/profiles/garethmanning/education-agent-skills/for-cursor/.cursor/skills/ai-hallucination-fact-check-protocol · Skill

  46★ repo

  Production-ready AI agent profiles for Claude Code, Cursor, and Codex. Search, install, and contribute ForgeCat packages.

• 331

  Ai hallucination fact check protocol

  nota-america/forgecat-agent-profiles/profiles/garethmanning/education-agent-skills/for-forgecat/skills/ai-hallucination-fact-check-protocol · Skill

  46★ repo

  Production-ready AI agent profiles for Claude Code, Cursor, and Codex. Search, install, and contribute ForgeCat packages.

• 332

  Benchmark models

  nota-america/forgecat-agent-profiles/profiles/garrytan/gstack/for-claude/.claude/skills/garrytan_gstack/benchmark-models · Skill

  46★ repo

  Production-ready AI agent profiles for Claude Code, Cursor, and Codex. Search, install, and contribute ForgeCat packages.

• 333

  Benchmark

  nota-america/forgecat-agent-profiles/profiles/garrytan/gstack/for-claude/.claude/skills/garrytan_gstack/benchmark · Skill

  46★ repo

  Production-ready AI agent profiles for Claude Code, Cursor, and Codex. Search, install, and contribute ForgeCat packages.

• 334

  Benchmark models

  nota-america/forgecat-agent-profiles/profiles/garrytan/gstack/for-codex/.agents/skills/garrytan_gstack/benchmark-models · Skill

  46★ repo

  Production-ready AI agent profiles for Claude Code, Cursor, and Codex. Search, install, and contribute ForgeCat packages.

• 335

  Benchmark

  nota-america/forgecat-agent-profiles/profiles/garrytan/gstack/for-codex/.agents/skills/garrytan_gstack/benchmark · Skill

  46★ repo

  Production-ready AI agent profiles for Claude Code, Cursor, and Codex. Search, install, and contribute ForgeCat packages.

• 336

  Benchmark models

  nota-america/forgecat-agent-profiles/profiles/garrytan/gstack/for-cursor/.cursor/skills/garrytan_gstack/benchmark-models · Skill

  46★ repo

  Production-ready AI agent profiles for Claude Code, Cursor, and Codex. Search, install, and contribute ForgeCat packages.

• 337

  Benchmark

  nota-america/forgecat-agent-profiles/profiles/garrytan/gstack/for-cursor/.cursor/skills/garrytan_gstack/benchmark · Skill

  46★ repo

  Production-ready AI agent profiles for Claude Code, Cursor, and Codex. Search, install, and contribute ForgeCat packages.

• 338

  Benchmark models

  nota-america/forgecat-agent-profiles/profiles/garrytan/gstack/for-forgecat/skills/garrytan_gstack/benchmark-models · Skill

  46★ repo

  Production-ready AI agent profiles for Claude Code, Cursor, and Codex. Search, install, and contribute ForgeCat packages.

• 339

  Benchmark

  nota-america/forgecat-agent-profiles/profiles/garrytan/gstack/for-forgecat/skills/garrytan_gstack/benchmark · Skill

  46★ repo

  Production-ready AI agent profiles for Claude Code, Cursor, and Codex. Search, install, and contribute ForgeCat packages.

• 340

  Agent evals

  BagelHole/DevOps-Security-Agent-Skills/devops/ai/agent-evals · Skill

  46★ repo

  Agent-ready DevOps, security, infrastructure, and compliance knowledge base with 80+ skills across Kubernetes, Terraform, AWS/Azure/GCP, AI platform operations, container hardening, SOC2/ISO27001, and incident response—plus ready-to-run scripts, templates, and playbooks for SRE, platform, and security teams.

• 341

  Rag observability evals

  BagelHole/DevOps-Security-Agent-Skills/devops/ai/rag-observability-evals · Skill

  46★ repo

  Agent-ready DevOps, security, infrastructure, and compliance knowledge base with 80+ skills across Kubernetes, Terraform, AWS/Azure/GCP, AI platform operations, container hardening, SOC2/ISO27001, and incident response—plus ready-to-run scripts, templates, and playbooks for SRE, platform, and security teams.

• 342

  Eval

  Kanevry/session-orchestrator/skills/eval · Skill

  45★ repo

  Loop engineering for AI coding agents — turn ad-hoc sessions into a repeatable research → plan → wave-execute → close loop with verification gates. Runs on Claude Code, Codex CLI, Cursor, and Pi. MIT community plugin.

• 343

  Arize evaluator

  Arize-ai/arize-skills/skills/arize-evaluator · Skill

  43★ repo

  Agent skills for Arize — datasets, experiments, and traces via the ax CLI

• 344

  Eval runner

  haabe/mycelium/plugins/mycelium/skills/eval-runner · Skill

  42★ repo

  AI made building cheap. It didn't make deciding cheap. Mycelium is a Claude Code harness that makes your agent run discovery and weigh evidence before it writes code. It earns the right to start. Built for software, courses, AI tools, and services.

• 345

  Agent evals and observability

  magnus919/agent-skills/agent-evals-and-observability · Skill

  41★ repo

  Curated collection of AI agent skills for Hermes and other agent frameworks

• 346

  Using cap evolve

  skillberry-ai/cap-evolve/skills/orchestrate/using-cap-evolve · Skill

  37★ repo

  Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.

• 347

  Ai engineering

  manusco/resonance/.agents/skills/engineering/ai-engineering · Skill

  36★ repo

  The Vibe Coding Operating System.

• 348

  Materials benchmark datasets starter

  ma-compbio-lab/SkillFoundry/skills/materials-science-and-engineering/materials-benchmark-datasets-starter · Skill

  36★ repo

  A framework for discovering, compiling, and validating reusable skills for scientific agents.

• 349

  Inspect evaluation harness starter

  ma-compbio-lab/SkillFoundry/skills/scientific-agents-and-automation/inspect-evaluation-harness-starter · Skill

  36★ repo

  A framework for discovering, compiling, and validating reusable skills for scientific agents.

• 350

  Benchmark table mining starter

  ma-compbio-lab/SkillFoundry/skills/scientific-knowledge/benchmark-table-mining-starter · Skill

  36★ repo

  A framework for discovering, compiling, and validating reusable skills for scientific agents.

• 351

  Skill creator

  theogbrand/yoink/.agents/skills/skill-creator · Skill

  35★ repo

  yoink is an AI agent that removes complex dependencies by reimplementing only what you need.

• 352

  Eval designer

  NickCrew/Claude-Cortex/skills/eval-designer · Skill

  30★ repo

  Claude Cortex

• 353

  Build eval dataset

  ContextJet-ai/awesome-llm-observability/skills/build-eval-dataset · Skill

  no license29★ repo

  50+ curated LLM observability tools PLUS 26 Agent Skills (several with runnable, unit-tested scripts) to build, evaluate, debug, secure & monitor reliable LLM apps. Tracing, evals, guardrails, LLMOps.

• 354

  Collect user feedback

  ContextJet-ai/awesome-llm-observability/skills/collect-user-feedback · Skill

  no license29★ repo

  50+ curated LLM observability tools PLUS 26 Agent Skills (several with runnable, unit-tested scripts) to build, evaluate, debug, secure & monitor reliable LLM apps. Tracing, evals, guardrails, LLMOps.

• 355

  Eval driven development

  ContextJet-ai/awesome-llm-observability/skills/eval-driven-development · Skill

  no license29★ repo

  50+ curated LLM observability tools PLUS 26 Agent Skills (several with runnable, unit-tested scripts) to build, evaluate, debug, secure & monitor reliable LLM apps. Tracing, evals, guardrails, LLMOps.

• 356

  Inngest brownfield audit

  inngest/inngest-skills/skills/inngest-brownfield-audit · Skill

  no license28★ repo

  Agent Skills for building with Inngest

• 357

  Skill creator advanced

  kevintsengtw/dotnet-testing-agent-skills/skills/skill-creator-advanced · Skill

  28★ repo

  AI Agent Skills for .NET Testing - Based on 30-Day Testing Challenge (iThome Ironman 2025 Winner)

• 358

  Human eval handoff repair

  yha9806/academic-writing-toolkit/.claude/skills/human-eval-handoff-repair · Skill

  27★ repo

  Local-first, evidence-controlled academic writing workflows for AI agents, with bounded revision, clean-room review, and release governance.

• 359

  Human eval handoff repair

  yha9806/academic-writing-toolkit/plugins/academic-writing-toolkit/skills/human-eval-handoff-repair · Skill

  27★ repo

  Local-first, evidence-controlled academic writing workflows for AI agents, with bounded revision, clean-room review, and release governance.

• 360

  Skill creator

  waterfeet/DoroPet_V3/opendoro/src/skills/skill-creator · Skill

  25★ repo

  Your own AI assistant for Windows, Make Doro Great Again!