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

• 901

  Eval

  srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/eval · Skill

  0★ repo

  Native macOS skill-catalog studio for Claude Code — browse 1,492 Markdown skills, customize with variables or AI (hosted or local), export to .claude/skills. SwiftUI + Liquid Glass.

• 902

  Skill creator

  srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Development/skill-creator · Skill

  0★ repo

  Native macOS skill-catalog studio for Claude Code — browse 1,492 Markdown skills, customize with variables or AI (hosted or local), export to .claude/skills. SwiftUI + Liquid Glass.

• 903

  Hugging face community evals

  srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Product/hugging-face-community-evals · Skill

  0★ repo

  Native macOS skill-catalog studio for Claude Code — browse 1,492 Markdown skills, customize with variables or AI (hosted or local), export to .claude/skills. SwiftUI + Liquid Glass.

• 904

  Self eval

  srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Research/self-eval · Skill

  0★ repo

  Native macOS skill-catalog studio for Claude Code — browse 1,492 Markdown skills, customize with variables or AI (hosted or local), export to .claude/skills. SwiftUI + Liquid Glass.

• 905

  Output scoring en

  matematicsolutions/awesome-matematic-skills-en/verification-foundation/skills/output-scoring-en · Skill

  0★ repo

  English hub of method-neutral legal AI skills (verification core, content quality, EU law) - bundle model. Polish-jurisdiction skills live in awesome-matematic-skills-pl.

• 906

  Ecc eval harness

  Pdbjork/hermosskills-site/skills/ecc-eval-harness · Skill

  no license0★ repo

  Hermesskills — a curated marketplace & repository of AI-agent skills. OpenClaw-compatible catalog at /catalog/v1/skills.json. 30% of commissions fund public-good AI.

• 907

  Stayingapi comp set benchmark

  stayingapi/travel-skills/skills/stayingapi-comp-set-benchmark · Skill

  0★ repo

  Portable AI-agent skills (SKILL.md) for accommodation search, availability, pricing, cross-OTA comparison & reviews via StayingAPI. Works with Claude, MCP and more. MIT-0.

• 908

  Eval grader

  SamyakJhaveri/loam/seed/_research/skills/eval-grader · Skill

  0★ repo

  Copier template that bootstraps AI-agent-optimized project setups: layered context routing, curated skills, and an enforced validation gate — synced across projects.

• 909

  Eval run

  SamyakJhaveri/loam/seed/_research/skills/eval-run · Skill

  0★ repo

  Copier template that bootstraps AI-agent-optimized project setups: layered context routing, curated skills, and an enforced validation gate — synced across projects.

• 910

  Overnight eval

  SamyakJhaveri/loam/seed/_research/skills/overnight-eval · Skill

  0★ repo

  Copier template that bootstraps AI-agent-optimized project setups: layered context routing, curated skills, and an enforced validation gate — synced across projects.

• 911

  Post eval

  SamyakJhaveri/loam/seed/_research/skills/post-eval · Skill

  0★ repo

  Copier template that bootstraps AI-agent-optimized project setups: layered context routing, curated skills, and an enforced validation gate — synced across projects.

• 912

  Evaluation frameworks

  ats4321/claude-engineering-skills/skills/evaluation-frameworks · Skill

  0★ repo

  26 repository-agnostic engineering skills for Claude Code — debugging, design, review, validation, and AI engineering as operational runbooks.

• 913

  Case 00228

  knownasnaffy/prompthound/dataset/case_00228 · Skill

  no license0★ repo

  A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

• 914

  Case 00490

  knownasnaffy/prompthound/dataset/case_00490 · Skill

  no license0★ repo

  A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

• 915

  Case 01169

  knownasnaffy/prompthound/dataset/case_01169 · Skill

  no license0★ repo

  A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

• 916

  Case 01745

  knownasnaffy/prompthound/dataset/case_01745 · Skill

  no license0★ repo

  A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

• 917

  Case 02998

  knownasnaffy/prompthound/dataset/case_02998 · Skill

  no license0★ repo

  A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

• 918

  Case 03442

  knownasnaffy/prompthound/dataset/case_03442 · Skill

  no license0★ repo

  A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

• 919

  Case 03796

  knownasnaffy/prompthound/dataset/case_03796 · Skill

  no license0★ repo

  A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

• 920

  Case 05375

  knownasnaffy/prompthound/dataset/case_05375 · Skill

  no license0★ repo

  A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

• 921

  Ai forge eval

  robcsaszar/ai-forge/skills/ai-forge-eval · Skill

  0★ repo

  Claude Code skills covering the skill-authoring lifecycle — create, judge, eval with persisted regression suites, audit for ecosystem-wide coherence, review, and update

• 922

  Inngest agent evals

  DrOlu/agent-skills/skills/inngest-agent-evals · Skill

  no license0★ repo

  Open agent skills for the skills.sh ecosystem — browser, docs, mail, media, security, networking, orchestration, and more.

• 923

  Inngest brownfield audit

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

  no license0★ repo

  Open agent skills for the skills.sh ecosystem — browser, docs, mail, media, security, networking, orchestration, and more.

• 924

  Benchmark decoder

  aoli0919/learn-anything-skills/skills/benchmark-decoder · Skill

  0★ repo

  Beginner-first agent skills that turn 'I want to learn X' into a 30-day path, tutor loop, projects, and learning memory.

• 925

  Hallucination checker

  aoli0919/learn-anything-skills/skills/hallucination-checker · Skill

  0★ repo

  Beginner-first agent skills that turn 'I want to learn X' into a 30-day path, tutor loop, projects, and learning memory.

• 926

  Vezir yetistirme

  trugurpala/divan/plugins/sadrazam/skills/vezir-yetistirme · Skill

  0★ repo

  Open-source workflow layer for Codex, Claude Code and other coding agents: planning, persistent context, explicit execution and verifiable delivery.

• 927

  Dynamic eval

  awesome-liuxiao/agent-skill-doctor/benchmarks/public/v1/fixtures/dynamic-eval · Skill

  no license0★ repo

  Find broken and risky Codex or Claude Code skills locally

• 928

  Skill creator

  awesome-liuxiao/agent-skill-doctor/benchmarks/public/v1/upstream/anthropic/skill-creator · Skill

  no license0★ repo

  Find broken and risky Codex or Claude Code skills locally

• 929

  Evaluate prompts

  Paldom/promptimize/skills/evaluate-prompts · Skill

  0★ repo

  Agent Skills for prompt optimization - tune prompts for the latest frontier models like Fable 5 and GPT 5.6, write effective goals and success criteria, and engineer agentic loops that converge.

• 930

  Eval audit and sweep

  YosukeIida/personal-agent-skills/eval-audit-and-sweep · Skill

  no license0★ repo

  Personal agent skills (Claude Code / Codex) — SKILL.md collection

• 931

  Eval audit

  avnath13/evalpilot/skills/eval-audit · Skill

  0★ repo

  Agent evals on autopilot: find quality bugs in your AI agent, ship a targeted fix, and prove it on a held-out set. Zero-dependency Agent Skill + CLI.

• 932

  Grade

  avnath13/evalpilot/skills/grade · Skill

  0★ repo

  Agent evals on autopilot: find quality bugs in your AI agent, ship a targeted fix, and prove it on a held-out set. Zero-dependency Agent Skill + CLI.

• 933

  Arbor

  lhbsaa/apex-discovery/skills/arbor · Skill

  0★ repo

  Scientific research extension for apex-unified - 149 scientific skills for biology, chemistry, medicine, materials research. Powered by Scientific Agent Skills (31.4k star).

• 934

  Skill creator

  sorinLupaIonut/digital-fte/.claude/skills/skill-creator · Skill

  no license0★ repo

  A customer-support Digital FTE (AI Worker): OpenAI Agents SDK on a sandboxed runtime, capabilities as portable Skills, a scoped customer-data MCP server instead of raw SQL, pgvector semantic search on Neon Postgres, and a transactional audit row behind every action.

• 935

  Behavior spec canvas

  VJDiPaola/skill-forge/behavior-spec-canvas · Skill

  no license0★ repo

  A skill library for AI coding agents with a CI quality gate: 38 skills, four-target sync, and an 18-check eval harness that fails the build on malformed skills.

• 936

  Eval framework

  VJDiPaola/skill-forge/eval-framework · Skill

  no license0★ repo

  A skill library for AI coding agents with a CI quality gate: 38 skills, four-target sync, and an 18-check eval harness that fails the build on malformed skills.

• 937

  Revenue benchmark

  getappniche/aso-skills/skills/revenue-benchmark · Skill

  0★ repo

  ASO & app-market research skills for AI agents — Claude Code, Cursor, and any MCP client. Install: npx skills add getappniche/aso-skills

• 938

  Eval harness

  sairam0424/MindForge/.mindforge/skills/eval-harness · Skill

  0★ repo

  MindForge: The Enterprise Agentic Framework for Claude Code & Antigravity. High-performance autonomous execution, wave-parallelism, and multi-tier governance for production-grade AI engineering.

• 939

  Benchmark optimization loop

  asong56/skills/03-build/universal/benchmark-optimization-loop · Skill

  0★ repo

  268 AI coding assistant skills, organized across 12 workflow layers. Sources include Anthropic official, FRM, SKC, LRN, SKA, and other mainstream AI coding frameworks.

• 940

  Agent eval

  asong56/skills/04-assure/agent-eval · Skill

  0★ repo

  268 AI coding assistant skills, organized across 12 workflow layers. Sources include Anthropic official, FRM, SKC, LRN, SKA, and other mainstream AI coding frameworks.

• 941

  Benchmark

  asong56/skills/04-assure/benchmark · Skill

  0★ repo

  268 AI coding assistant skills, organized across 12 workflow layers. Sources include Anthropic official, FRM, SKC, LRN, SKA, and other mainstream AI coding frameworks.

• 942

  Eval FRM

  asong56/skills/04-assure/eval-FRM · Skill

  0★ repo

  268 AI coding assistant skills, organized across 12 workflow layers. Sources include Anthropic official, FRM, SKC, LRN, SKA, and other mainstream AI coding frameworks.

• 943

  Ai extensions

  asong56/skills/08-extend/ai-extensions · Skill

  0★ repo

  268 AI coding assistant skills, organized across 12 workflow layers. Sources include Anthropic official, FRM, SKC, LRN, SKA, and other mainstream AI coding frameworks.

• 944

  Healthcare eval FRM

  asong56/skills/11-vertical/healthcare/healthcare-eval-FRM · Skill

  0★ repo

  268 AI coding assistant skills, organized across 12 workflow layers. Sources include Anthropic official, FRM, SKC, LRN, SKA, and other mainstream AI coding frameworks.