Eyadkelleh/awesome-skills-security
Security testing toolkit for AI Agent: curated SecLists wordlists, injection payloads, and expert agents for authorized pentesting, CTFs, and bug bounties
Security testing toolkit for AI Agent: curated SecLists wordlists, injection payloads, and expert agents for authorized pentesting, CTFs, and bug bounties
npx skills add Eyadkelleh/awesome-skills-securitySecurity testing toolkit for AI Agent: curated SecLists wordlists, injection payloads, and expert agents for authorized pentesting, CTFs, and bug bounties
LibAFL is a modular fuzzing library for building custom fuzzers. Use for advanced fuzzing needs, custom mutators, or non-standard fuzzing targets.
Portable, stage-gated agentic-AI harness for Claude Code, Codex, and OpenCode.
Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, model selection/leaderboards and model persistence. Use for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
Research-backed AI self-audit skill for Claude Code / Codex / OpenClaw. Verifies high-stakes answers via independent re-solve + cross-method probe — not by critique. Honest about limits; every design choice has a paper citation.
Skills personales de Claude Code (procedimientos repetibles invocables como slash commands)
Life Scheduler — 拟人化生活状态生成器。让 AI Agent 每天自动拥有穿搭、日程和心情，像真人一样在过日子。OpenClaw Skill。灵感来自 astrbot_plugin_life_scheduler。