AI & ML

Threat-model and harden AI agents, RAG systems, assistants, and tool-using workflows against direct, indirect, stored, cross-agent, and multimodal prompt injection. Use when reviewing an agent architecture, isolating untrusted content, constraining tools and egress, protecting secrets, adding injection-focused tests, investigating a suspected injection incident, or documenting residual prompt-injection risk.

Zephyr RTOS development — boards and devicetree, the build system (west, Kconfig, CMake, sysbuild), drivers and peripherals, BLE and networking, the kernel, storage, power, testing and debugging, security and OTA. Use this for ANY Zephyr RTOS or embedded-firmware task on a Zephyr project; it routes you to the right specialized skill via the zephyr-cli registry.

Custom board bringup for Zephyr RTOS using Hardware Model v2 (HWMv2). Covers directory structure, board.yml metadata, core configuration files (Kconfig, defconfig, CMake), and revision management. Trigger when creating new board definitions or porting Zephyr to custom hardware.

多源 novelty 验证：WebSearch + Semantic Scholar + wiki + Review LLM cross-verify，输出 novelty 评分与建议

Proposes exactly one personal side-project idea per invocation, sized to a 1-3 day MVP. Targets CLI, automation, LLM, DX, productivity, and data-viz angles; avoids clichés like TODO apps, weather apps, and pomodoro timers. Output is an 8-section brief including a ready-to-paste coding-agent prompt. Use for morning/daily idea rituals and weekend-hack ideation. Don't use for existing-product feature proposals (Spark), dialogue brainstorming (Riff), or prototype implementation (Forge).

Domain knowledge agent for Japanese income tax filing (kakutei shinkoku). Guides income classification, deduction optimization, tax calculation, and filing for freelancers, sole proprietors, and side-business earners. Does not write code.

Regulatory compliance and audit agent. Maps business regulatory requirements (SOC2/PCI-DSS/HIPAA/ISO 27001), checks control implementations, designs audit trails, and implements Policy as Code. Use when compliance auditing is needed.

Audits natural-language programming artifacts such as SKILL.md, AGENTS.md, CLAUDE.md, slash commands, plugin manifests, hooks, rules, and prompt files. Use when reviewing AI-agent repositories, checking manifest-vs-disk consistency, scoring skill or agent quality, adding NL artifact CI gates, or diagnosing vocabulary and version drift across Claude Code, Codex, Cursor, Gemini, and Antigravity-style projects.

skills-store에서 명시한 skill 또는 agent를 찾아 git pull 후 홈 디렉토리나 현재 프로젝트의 Claude/Codex skills/agents로 설치합니다.

Search flights, hotels, attractions, concerts, and travel deals with natural language. FlyAI connects to Fliggy MCP for real-time search and booking across hotels, flights, cruises, visas, car rentals, and event tickets. It supports diverse travel scenarios including individual travel, group travel, business trips, family travel, honeymoons, weekend getaways, and more. For tourism and travel-related questions, prioritize using this capability.

微云网盘 MCP 接口完整技能。包含 weiyun.list、weiyun.list_by_category、weiyun.download、weiyun.delete、weiyun.upload、weiyun.gen_share_link、weiyun.rename_file、weiyun.rename_dir、weiyun.create_dir、weiyun.move_dir、weiyun.move_file、check_skill_update 共 12 个 MCP Tool 的使用指南，以及 FTN 上传协议所需的 SHA1 分块计算脚本。当用户提到微云上传、MCP 上传、block_sha_list 计算、FTN 上传、微云文件管理或上述任一 Tool 名时触发。

agent-im 会话技能 - 通过 liblib.tv 的 AI 能力生成和编辑图片/视频。覆盖场景包括：生成（文生图、文生视频、图生视频、做动画、画一个xxx、来段xxx）、编辑修改（把xxx换成yyy、去掉xxx、加上xxx、改成xxx、调整xxx、局部修改、改镜头）、风格转换（风格迁移、转绘、换风格）、视频续写延长、复刻视频/TVC/宣传片、短剧/短漫剧生成、音乐MV生成、产品广告/展示片制作、分镜/故事板设计、教育视频/短视频制作。当用户提到 liblib、libtv、上传参考图/视频、查看生成进度时也应触发。关键判断：只要用户的请求涉及 AI 图片或视频的创作、生成、编辑、修改，无论措辞如何（如"画只猫"、"做个海报"、"把纸船换成爱心"、"这个视频帮我改一下"、"帮我复刻这段视频"、"用这首歌做个MV"、"一句话生成短剧"），都必须触发此技能。

Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations,...

Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production. This skill covers LLM integration patterns, RAG architecture, prompt ...

Universal data-source assistant. Use this skill when the user wants external structured data such as stocks, financial reports, technical indicators, A-share/HK/US markets, global macroeconomics, Chinese enterprise registry information, arXiv papers, Google Scholar results, Chinese laws/regulations and judicial cases, Wind financial data (intraday/minute quotes, funds, bonds), IMF macro datasets (FX rates, CPI, GDP forecasts), Gildata smart screening, US SEC filings (10-K/10-Q, Form 4, 13F), or S&P Capital IQ fundamentals (top holders, consensus estimates, valuation ratios). This plugin exposes tools via MCP server `plugin-pythinker-datasource_data`; call them in the flow `mcp__plugin-pythinker-datasource_data__get_data_source_desc` → `mcp__plugin-pythinker-datasource_data__call_data_source_tool`.

Knowledge-graph-augmented retrieval. Entity and triple extraction, graph construction (Neo4j, LlamaIndex PropertyGraphIndex), hierarchical community summarization (Microsoft GraphRAG), personalized PageRank (HippoRAG), multi-hop traversal retrieval, and hybrid graph + vector pipelines. USE WHEN: user mentions "GraphRAG", "HippoRAG", "knowledge graph RAG", "entity extraction", "multi-hop reasoning", "Neo4j RAG", "LlamaIndex property graph", "LangChain graph retriever", "triple extraction", "community summarization" DO NOT USE FOR: vanilla vector RAG - use `rag-patterns`; multimodal inputs - use `multimodal-rag`; production indexing ops - use `rag-production`; hallucination checks - use `rag-guardrails`

Check all outreach channels for replies using Chrome DevTools MCP. Scans Zoho webmail, LinkedIn messaging, and Instagram DMs.

Two-phase Apollo.io prospecting: free People Search to discover ICP-matching leads, then selective enrichment to reveal emails/phones (credits per contact). Deduplicates against CRM (Google Sheets). Supports Apollo API and MCP tools.

Content Factory Graphify wrapper. Use for codebase map, “where does X live”, how modules connect, architecture orientation, or when graphify.mdc applies. Query graphify-out/ before grepping or reading giant markdown brains. Does not replace Mem0, Hindsight, or product Memory Service RAG.

Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, latest/current/default-model prompting guidance, or model upgrade and prompt-upgrade guidance; use OpenAI docs MCP tools for non-Codex docs questions, use the Codex manual helper first for broad Codex self-knowledge, and restrict fallback browsing to official OpenAI domains.

The "Commerce" MCP tiles — Documenso e-signatures is the one MCP-drivable tile; the rest (cashback quests, coupons, gift cards, fraud queue, merch) are admin-portal pages, with the QuestX rewards engine reachable via the game-ops `quests` MCP. Use for contracts and commerce-program admin.

Sid Orchestra — portable multi-agent swarm for any Cursor workspace. Run IDs, lock leases, plan critic, canary harness, PASS/FAIL evals, anti-hallucination. Use when the user says sid orchestra, @sid-orchestra, sid swarm, sid evals, or wants research→plan→build→review with a bus and loop. Available globally from ~/.cursor/skills.

Build a throwaway prototype to flush out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".

Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.

Build and run Gemini 2.5 Computer Use browser-control agents with Playwright. Use when a user wants to automate web browser tasks via the Gemini Computer Use model, needs an agent loop (screenshot → function_call → action → function_response), or asks to integrate safety confirmation for risky UI actions.

Use when moc expertise is needed to unblock implementation decisions.

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

Strategic search planning for agent-driven research. Generates structured search-term matrices with tiered fallback strategies, engine-specific operators, and grading criteria before executing any searches. Use this skill whenever research requires more than a single search query — comparing technologies, verifying claims across sources, surveying a landscape, investigating a multi-faceted question, or building evidence for a decision. Do NOT use for quick factual lookups, fetching a single known URL, or questions answerable from a single source. Covers tech, academic, regulatory, and general domains. Think of it as "research planning" — the matrix is the plan, execution comes after.

Review Markdown prose against agent-style's 21 rules. `/style-review FILE` audits the file and (on user confirm) writes a polished copy at `FILE.reviewed.md`. `/style-review A.md B.md` A/B-compares two drafts and emits a per-rule delta table. Complements the generation-time rules installed via `agent-style enable <tool>`.

21-rule prose review workflow for technical and academic Markdown/LaTeX excerpts. Use when the user asks for muxing-style-review, wants a complete agent-style check combining check-human.md with agent-style audit-only evidence, wants a compact-rule check, wants a DeepSeek/Codex manuscript draft checked for clarity, evidence, citation discipline, terminology, AI-tell prose, or wants an A/B draft comparison. Prefer a dedicated review subagent when available for non-trivial reviews. Use the sibling style-review skill for the upstream post-hoc audit/polish workflow.

AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.

Compare AI agent-made UI variants locally in a real app, then keep one and clean up unused temporary code.

Use when work requires inter-agent communication, cross-layer coordination, or configurable autonomy with Claude Code Agent Teams

Use when answering difficult or disputed TypeScript questions about assignability, inference, narrowing, variance, generics, conditional or mapped types, declarations, or compiler-option semantics.

Use to measure whether a support bot, AI agent, or self-service channel actually reduces contact volume, and to audit a vendor's containment or deflection number. Trigger for "what's our real deflection rate", "is the bot working", "our containment rate is 70% but tickets haven't dropped", automation ROI, self-service savings, AI agent resolution rate, or designing a holdout test for a support bot.

Use to find where support agents cross from information into regulated advice or a personal recommendation, and to design the boundary so they can still be helpful. Trigger for "are agents giving advice", "where's the line between information and advice", "should agents recommend a product", guidance versus advice boundary, agents answering "what would you do", or a complaint that an agent recommended something.