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

• 361

  Aiconfig online evals

  launchdarkly/ai-tooling/skills/agentcontrol/aiconfig-online-evals · Skill

  no license25★ repo

  LaunchDarkly's official AI tooling

• 362

  Online evals

  launchdarkly/ai-tooling/skills/agentcontrol/online-evals · Skill

  no license25★ repo

  LaunchDarkly's official AI tooling

• 363

  Gstack benchmark models

  charlieviettq/awesome-agent-skill/.claude/skills/gstack-benchmark-models · Skill

  24★ repo

  Curated skill pack for LLM agents in engineer and science workflow (Cursor & Claude ready).

• 364

  Gstack benchmark

  charlieviettq/awesome-agent-skill/.claude/skills/gstack-benchmark · Skill

  24★ repo

  Curated skill pack for LLM agents in engineer and science workflow (Cursor & Claude ready).

• 365

  Agent evaluation

  charlieviettq/awesome-agent-skill/.cursor/skills/ai-agent-systems/agent-evaluation · Skill

  24★ repo

  Curated skill pack for LLM agents in engineer and science workflow (Cursor & Claude ready).

• 366

  Benchmark models

  charlieviettq/awesome-agent-skill/.cursor/skills/gstack/browser-qa/benchmark-models · Skill

  24★ repo

  Curated skill pack for LLM agents in engineer and science workflow (Cursor & Claude ready).

• 367

  Benchmark

  charlieviettq/awesome-agent-skill/.cursor/skills/gstack/browser-qa/benchmark · Skill

  24★ repo

  Curated skill pack for LLM agents in engineer and science workflow (Cursor & Claude ready).

• 368

  Benchmark paper

  ShaishavMaisuria/research-paper-lifecycle-skills/skills/benchmark-paper · Skill

  23★ repo

  42 AI agent skills for literature review, academic writing, citation verification, conference submission, rebuttal, publication, and presentations.

• 369

  Eval grader

  byerlikaya/claude-starter-kit/claude-starter/skills/eval-grader · Skill

  22★ repo

  Enterprise engineering workflow for Claude Code — not just prompts. AI agents that plan, build, audit, and ship with security gates, privacy checks, and approval-controlled commits. Safely adopt it into new or existing repositories.

• 370

  Eval grader

  byerlikaya/claude-starter-kit/plugin/skills/eval-grader · Skill

  22★ repo

  Enterprise engineering workflow for Claude Code — not just prompts. AI agents that plan, build, audit, and ship with security gates, privacy checks, and approval-controlled commits. Safely adopt it into new or existing repositories.

• 371

  Skill creator

  ur-grue/autopunk-media-skills/.claude/skills/skill-creator · Skill

  21★ repo

  394 free AI skills and 6 agents for media professionals — journalists, producers, podcasters, YouTubers. Quality-tested. Works with Claude, ChatGPT, Cursor, Codex CLI, and more.

• 372

  Fluentcrm funnel benchmark

  Lonsdale201/wp-agent-skills/fluentcrm/fluentcrm-funnel-benchmark · Skill

  21★ repo

  A community-maintained collection of agent skills for WordPress plugin and theme development.

• 373

  Llm overreliance hallucination

  ShulkwiSEC/bb-huge/skills/curated/llm-overreliance-hallucination · Skill

  21★ repo

  bb-huge 🤗 , Personal bug bounty findings hub and bug bounty orchestration for multiple agents

• 374

  Ds eval

  Dataslayer-AI/Marketing-skills/skills/ds-eval · Skill

  19★ repo

  Marketing agent skills powered by real data. Connect Claude Code to your actual Google Ads, GA4, Search Console, Meta Ads, LinkedIn Ads and 50+ platforms via Dataslayer MCP — no copy-pasting required.

• 375

  Skill creator

  archubbuck/workspace-architect/assets/skills/skill-creator · Skill

  18★ repo

  Workspace Architect is a zero-friction CLI tool that provides curated collections of specialized agents, instructions, and prompts to supercharge your GitHub Copilot experience.

• 376

  Hallucination red team

  zgbrenner/agentcounsel/skills/legal-methodology/hallucination-red-team · Skill

  17★ repo

  Open-source, AI-agnostic skills for legal teams.

• 377

  Recipe eval prompt

  shinpr/rashomon/skills/recipe-eval-prompt · Skill

  17★ repo

  Measure prompt and skill improvements with blind A/B comparison.

• 378

  Recipe eval skill

  shinpr/rashomon/skills/recipe-eval-skill · Skill

  17★ repo

  Measure prompt and skill improvements with blind A/B comparison.

• 379

  Skill creator

  codeclawd/fable-mode/skills/skill-creator · Skill

  no license16★ repo

  Run Claude Fable 5 on Opus 4.8 in Claude Code. The Mythos-class model pulled by export controls — brought back as a native agentic distillation (FABLE_CODE.md), measured playbook, verification hooks, and design/MCP/test skills. "Fable 5 Lite," done right.

• 380

  Borderline eval usage 15

  Teycir/SkillsGuard/testskills/realworld/skills/borderline-eval-usage-15 · Skill

  no license15★ repo

  Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts before they run.

• 381

  Borderline eval usage 21

  Teycir/SkillsGuard/testskills/realworld/skills/borderline-eval-usage-21 · Skill

  no license15★ repo

  Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts before they run.

• 382

  Borderline eval usage 3

  Teycir/SkillsGuard/testskills/realworld/skills/borderline-eval-usage-3 · Skill

  no license15★ repo

  Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts before they run.

• 383

  Borderline eval usage 9

  Teycir/SkillsGuard/testskills/realworld/skills/borderline-eval-usage-9 · Skill

  no license15★ repo

  Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts before they run.

• 384

  Iblai api agent eval

  iblai/api/skills/iblai-api-agent-eval · Skill

  15★ repo

  Agent skills + a chat MCP server to operate the ibl.ai platform via its REST API. Install: npx skills add iblai/api

• 385

  Agentv dev

  EntityProcess/agentv/plugins/agentv-dev/skills/agentv-dev · Skill

  15★ repo

  Light-weight AI agent evaluation and optimization framework

• 386

  Agentv bench

  EntityProcess/agentv/skills-data/agentv-bench · Skill

  15★ repo

  Light-weight AI agent evaluation and optimization framework

• 387

  Agentv eval migrations

  EntityProcess/agentv/skills-data/agentv-eval-migrations · Skill

  15★ repo

  Light-weight AI agent evaluation and optimization framework

• 388

  Agentv eval review

  EntityProcess/agentv/skills-data/agentv-eval-review · Skill

  15★ repo

  Light-weight AI agent evaluation and optimization framework

• 389

  Agentv eval writer

  EntityProcess/agentv/skills-data/agentv-eval-writer · Skill

  15★ repo

  Light-weight AI agent evaluation and optimization framework

• 390

  Agentv governance

  EntityProcess/agentv/skills-data/agentv-governance · Skill

  15★ repo

  Light-weight AI agent evaluation and optimization framework

• 391

  Benchmark table parsing and aggregation

  HolobiomicsLab/asb-skill-collections/collections/epigenomics/v1/skills/benchmark-table-parsing-and-aggregation · Skill

  15★ repo

  Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

• 392

  Epic array simulation benchmark

  HolobiomicsLab/asb-skill-collections/collections/epigenomics/v1/skills/epic-array-simulation-benchmark · Skill

  15★ repo

  Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

• 393

  Cross validation benchmark evaluation

  HolobiomicsLab/asb-skill-collections/collections/metabolomics/v1/skills/cross-validation-benchmark-evaluation · Skill

  15★ repo

  Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

• 394

  Mass spectrometry benchmark analysis

  HolobiomicsLab/asb-skill-collections/collections/metabolomics/v1/skills/mass-spectrometry-benchmark-analysis · Skill

  15★ repo

  Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

• 395

  Mass spectrometry benchmark design

  HolobiomicsLab/asb-skill-collections/collections/metabolomics/v1/skills/mass-spectrometry-benchmark-design · Skill

  15★ repo

  Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

• 396

  Annotation benchmark performance evaluation

  HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/annotation-benchmark-performance-evaluation · Skill

  15★ repo

  Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

• 397

  Benchmark dataset generation from reference metabolites

  HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/benchmark-dataset-generation-from-reference-metabolites · Skill

  15★ repo

  Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

• 398

  Benchmark harness execution

  HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/benchmark-harness-execution · Skill

  15★ repo

  Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

• 399

  Benchmark table generation and reporting

  HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/benchmark-table-generation-and-reporting · Skill

  15★ repo

  Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

• 400

  Cross validation benchmark evaluation

  HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/cross-validation-benchmark-evaluation · Skill

  15★ repo

  Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

• 401

  Gallery benchmark data extraction

  HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/gallery-benchmark-data-extraction · Skill

  15★ repo

  Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

• 402

  Mass spectral library benchmark execution

  HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/mass-spectral-library-benchmark-execution · Skill

  15★ repo

  Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

• 403

  Mass spectrometry benchmark analysis

  HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/mass-spectrometry-benchmark-analysis · Skill

  15★ repo

  Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

• 404

  Mass spectrometry benchmark design

  HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/mass-spectrometry-benchmark-design · Skill

  15★ repo

  Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

• 405

  Metabolite benchmark dataset validation

  HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/metabolite-benchmark-dataset-validation · Skill

  15★ repo

  Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

• 406

  Metabolite benchmark peak matching

  HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/metabolite-benchmark-peak-matching · Skill

  15★ repo

  Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

• 407

  Molecular model benchmark comparison

  HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/molecular-model-benchmark-comparison · Skill

  15★ repo

  Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

• 408

  Performance benchmark execution

  HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/performance-benchmark-execution · Skill

  15★ repo

  Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

• 409

  Transcript quantification benchmark comparison

  HolobiomicsLab/asb-skill-collections/collections/transcriptomics/v1/skills/transcript-quantification-benchmark-comparison · Skill

  15★ repo

  Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

• 410

  Annotation benchmark performance evaluation

  HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/annotation-benchmark-performance-evaluation · Skill

  15★ repo

  Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

• 411

  Benchmark harness execution

  HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/benchmark-harness-execution · Skill

  15★ repo

  Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

• 412

  Mass spectrometry benchmark analysis

  HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/mass-spectrometry-benchmark-analysis · Skill

  15★ repo

  Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

• 413

  Benchmark dataset generation from reference metabolites

  HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/benchmark-dataset-generation-from-reference-metabolites · Skill

  15★ repo

  Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

• 414

  Benchmark table generation and reporting

  HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/benchmark-table-generation-and-reporting · Skill

  15★ repo

  Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

• 415

  Gallery benchmark data extraction

  HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/gallery-benchmark-data-extraction · Skill

  15★ repo

  Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

• 416

  Mass spectral library benchmark execution

  HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/mass-spectral-library-benchmark-execution · Skill

  15★ repo

  Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

• 417

  Mass spectrometry benchmark design

  HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/mass-spectrometry-benchmark-design · Skill

  15★ repo

  Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

• 418

  Metabolite benchmark dataset validation

  HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/metabolite-benchmark-dataset-validation · Skill

  15★ repo

  Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

• 419

  Benchmark

  ngocsangyem/MeowKit/.claude/skills/benchmark · Skill

  14★ repo

  Production ready. AI Agent Workflow System for Claude Code

• 420

  Mk benchmark

  ngocsangyem/MeowKit/packages/mewkit/src/migrate/modules/codex/root/.agents/skills/mk-benchmark · Skill

  14★ repo

  Production ready. AI Agent Workflow System for Claude Code