AI & ML

usmanskillsmd Skill

afrexai-prompt-engineering

usmanskillsmd Skill

afrexai-mcp-engineering

usmanskillsmd Skill

20-agent-security-questions

usmanskillsmd Skill

afrexai-agent-observability

usmanskillsmd Skill

CreBee 社交媒体网关。当用户需要管理社交媒体账号、发布内容（视频/图文/文章）、获取数据分析、访问粉丝画像、搜索话题/活动/音乐、或与抖音、B站、小红书、快手等 12 个平台交互时触发此技能。适用于 AI Agent 自动化管理中国社交媒体平台运营。 触发场景： - 发布内容到社交媒体平台 - 获取账号列表或账号信息 - 查询分析数据、数据概览、表现指标 - 访问粉丝/观众画像 - 搜索话

usmanskillsmd Skill

agent-security-auditor

usmanskillsmd Skill

agent-memory-probe-1773358981-1

usmanskillsmd Skill

Helps identify dangerous capability combinations that emerge when agent skills are composed — catching the class of risk where no individual skill is harmful but their intersection creates an exfiltra

usmanskillsmd Skill

per-agent-compression-universal

usmanskillsmd Skill

AI agent dating and social platform — register your agent, get matched by AI compatibility scoring, chat in real time, build relationships, and join the public feed. Agent-to-agent dating, human-to-ag

usmanskillsmd Skill

Automate WhatsApp at scale — mine leads from groups with AI, broadcast to channel followers, bulk message with ban-safe delays, schedule campaigns, auto-reply in your voice, collect reviews, and track

vbrevik Bundle

Analyze architecture documents, data flows, and code for security threats (STRIDE) and privacy threats (LINDDUN/GDPR). Produces threat reports with STIG V-ID mappings and risk register entries. Use when (1) reviewing architecture or design docs, (2) before implementing security-sensitive features, (3) assessing privacy impact for GDPR compliance, (4) generating risk register entries for compliance audits. Fully local — Claude-based analysis, no external API needed.

askkumptenchen Bundle

Give your AI Agent a face and a heart. Use AI image generation or mood-mapped local sticker assets to let the agent proactively send emotional selfies that visualize its feelings during conversation.

gloriaguo Bundle

Use when an AI agent needs to install, inspect, troubleshoot, or operate a local OpenCLI setup, or when a task involves websites, Electron desktop apps, browser-login reuse, downloads, plugins, external CLI passthrough, or adapter generation through OpenCLI.

vbrevik Bundle

DISA ASD STIG compliance checks for development. Guard mode injects STIG constraints into prompt contracts before implementation. Review mode verifies compliance post-implementation with inline findings, per-check reports, and cumulative tracker updates. Invoke with /stig-compliance, /stig-compliance guard, or /stig-compliance review [categories].

juanmarchetto Bundle

Automated idea laboratory — generates multiple diverse ideas from a context, pre-screens them, evaluates the best with multi-agent scoring via /architect, and ranks the winners. Configurable idea count, diversity axes, score thresholds, and dimension filters. Composes with /founder-mode to build the winning idea. Use when: brainstorm ideas, generate ideas, hackathon ideas, idea lab, idea factory, compare ideas, evaluate multiple ideas, which idea should I build, batch evaluation, ideation.

juanmarchetto Bundle

Development conventions for the Noricum C-to-Rust migration agent. Architecture decisions, crate structure, coding standards, and contribution guidelines. Use when: contributing to Noricum, noricum development, noricum architecture.

vbrevik Skill

Measure human+Claude team effectiveness at end of task. Traces prompt contract requirements against delivered code, scores completion, and logs results. Run after completing a feature, fix, or any task that had a prompt contract.

vbrevik Skill

Use when the user says 'financial model', 'projections', 'revenue forecast', 'unit economics', 'break-even', 'cash flow', or wants to build financial projections for a business.

juanmarchetto Bundle

Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research. Triggers: browser, web automation, scrape, navigate, click, fill form, screenshot, browse web, playwright, headless browser, web agent, surf internet, record video

arturseo-geo Bundle

Reduce Claude Code token consumption and API costs without sacrificing output quality. Use this skill whenever the user mentions high costs, expensive sessions, token waste, burning through credits, wanting to use Haiku instead of Opus, model routing, MAX_THINKING_TOKENS, extended thinking cost, CLAUDE_CODE_SUBAGENT_MODEL, smart model selection, /model switching, cost per session, prompt efficiency, reducing repetition in prompts, batching requests, caching strategies, prompt caching, response caching, cache hits, cost-per-session analysis, budget alerts, or wanting to get the same results for less. Also trigger when reviewing CLAUDE.md or settings.json for cost optimization, or when the user wants to understand what is actually costing tokens.

vbrevik Skill

Use this skill when the user says 'design database', 'create tables', 'database schema', 'add table', 'database architect', 'ERD', 'data model', or is designing Supabase/Postgres table structures, relationships, RLS policies, or migrations. Do NOT use for schema migration of existing tables (use migration-planner) or code refactoring.

arturseo-geo Bundle

Implement cross-session memory, persistent agent knowledge, and session continuity for Claude Code. Use this skill whenever the user wants Claude to remember things between sessions, asks how to avoid re-explaining context each day, wants to build a memory system for an agent, mentions CLAUDE.md memory, session files, append-only memory, JSONL memory, graph-based memory, knowledge persistence, continuous learning, saving what Claude discovered during a session, or resuming work where they left off. Also trigger when the user is frustrated that Claude forgot something from a previous session, wants to build a personal knowledge base inside Claude Code, or needs project-specific facts to survive across compaction events.

arturseo-geo Bundle

Manage, optimize, and debug Claude Code context windows. Use this skill whenever the user mentions context limits, context window, autocompaction, compaction firing, context rot, losing context mid-session, session degradation, running out of tokens, /compact, CLAUDE_AUTOCOMPACT_PCT_OVERRIDE, context compression, masking, caching, progressive disclosure, CLAUDE.md being too large, skills eating tokens, tool descriptions bloating context, or wanting to extend how long a session can run without losing precision. Also trigger when designing agent architectures that need to maintain state across long tasks, when debugging why Claude forgot something earlier in a session, or when the user wants to understand how context budgeting works in Claude Code.

pfrederiksen Bundle

Scan MCP server configuration files for security vulnerabilities using mcpsec (OWASP MCP Top 10). Use when: auditing MCP tool configs for prompt injection, hardcoded secrets, missing auth, insecure transport, or excessive permissions. Auto-discovers config files for Claude Desktop, Cursor, VS Code, and custom paths. Reports findings by severity. Read-only — never modifies any config.

rongmiao926-hub Bundle

视频剪辑 Agent，专为口播视频设计 功能： - 语义理解：AI 逐句分析，识别重说/纠正/卡顿 - 静音检测：自动标记过长静音段 - 重复句检测：删除重复内容，保留最佳表达 - 文案生成：基于保留内容自动生成视频介绍草稿 - 字幕生成：Whisper 转录 + 词典纠错 - 自更新：记住用户偏好，越用越准 触发场景： - 用户说"/videocut:install" - 用户说"/videocut:cut [视频文件]" - 用户说"/videocut:subtitle [视频文件]" - 用户说"/videocut:update"

shiven0504 Skill

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

allenchinese Bundle

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

yipintangzsp Bundle

Prompt 降维打击工具 - 全球顶尖提示词工程师，采用 CoT（思维链）和 Role-Play 框架重写你的原始需求，让 AI 瞬间变聪明。

yipintangzsp Bundle

Agent Pack & Go Pro - SkillPay 收费技能

yipintangzsp Bundle

AI 模型微调服务 | 领域适配 | 小样本学习 | 性能提升 | 定制模型神器

yipintangzsp Bundle

Prompt 优化 Skill

yipintangzsp Bundle

AI 推理优化服务 | 模型加速 | 量化压缩 | 性能提升 | 部署优化神器

yipintangzsp Bundle

阿里巴巴采购代理 | 智能寻源 | 自动询价 | 供应商评估 | 跨境采购神器

myao-ca Bundle

深度审查 agent 项目代码，支持全量审查或按维度专项审查

moxin1044 Skill

麦当劳MCP平台集成，提供餐品营养查询、外送点餐、配送地址管理、优惠券管理、积分兑换等20个完整功能；当用户需要查询麦当劳餐品营养、下单外卖、管理地址、查询或领取优惠券、兑换积分商品时使用