Agent building

Security audit and vulnerability scanning for AI agent skills before install.

Validate and score Claude Code skill packages for quality, completeness, and best-practice compliance.

This skill helps users extract basic product details other sellers prices and seller ratings from Amazon via ASIN automatically using the BrowserAct API.

This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API.

This skill helps users extract GitHub repository project details and contributor contact information using keywords, stars, and update dates.

This skill helps users automatically scrape business data from Google Maps using the BrowserAct Google Maps API.

This skill helps users discover key contacts across industries, roles, and social platforms via the BrowserAct API.

This skill helps users extract structured video list data and comment data from YouTube using the BrowserAct API.

This skill helps users automatically extract YouTube video transcripts and metadata via the BrowserAct API.

This skill helps users automatically extract channel-level and video detail data from a specific YouTube channel via BrowserAct API.

Agent 专用邮箱统一管理：让 Claude Code、Codex 等平台的 Agent 用一套命令收发邮件、整理收件箱、分发任务。支持网易 ClawEmail（claw.163.com）和腾讯 Agent Mail（QQ 邮箱，agent.qq.com）两家后端，通过 MAIL_PROVIDER…

poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work.

Set up GitHub authentication for the agent using git (universally available) or the gh CLI.

Set up a graphify knowledge graph for the current project — in-project committed graph.json, AST extraction + external labelling, tracked refresh hooks…

Shared taskwarrior/timewarrior conventions for the task-mode skills: db layout, tasks/context/ folder, stage/human-in-the-loop tag vocabulary, scaffolding.

Spaced-repetition flashcard system.

Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals.

Chooses single-branch or wt-stack review topology and uses task-specific Git worktrees before changing files in a repository.

Use when asked to audit, measure, implement, or operate rules-based human-in-the-loop autonomy for agent-operated repositories.

中文去 AI 腔一整套（装完即用，零 API Key —— 装了本 skill 的 agent 自己就是那个 LLM）。 六个流程：① 生成即去 AI —— 写中文时按本 skill 的写作指南落笔，初稿就不带 AI 腔； ② 复查改写 —— 产出后对照本 skill 的清单再过一遍，定点拆模板句式； ③…

Push a React design system to claude.ai/design.

Manages Datadog dashboards, SLOs, monitors, and synthetic tests as code — push (create/update), pull (download), and list resources via the Datadog API.

Review one finished or running worktree build (a Builder or any agent that worked in an Orca worktree) and produce an HTML report of where the time and tokens…

Generates a brand-new attack skill with a novel technique when existing skills are not well-suited for the target seed prompt.