AI Ml AI Skills

Wibi Style 官方视觉风格。将单人儿童老照片重新拍摄式地转换成明亮可爱的现代儿童摄影大头卡贴，严格去掉脖子肩膀身体，并在原片露齿时制作满钻牙；生成前询问默认白色、复古大波点、柔和双色渐变、蜡笔手绘小星星、柔粉纯色五种背景。当用户要求钻牙大头、儿童头像卡贴、老照片萌化，或明确调用 $diamond-kid-head-card 时使用。

Initialize or update project for Claude Code and MPM

This skill should be used when the user asks to "optimize prompts", "design prompt templates", "evaluate LLM outputs", "build agentic systems", "implement RAG", "create few-shot examples", "analyze…

Unofficial read-only Flytoday: Iranian and international flights, hotels, villas, trains, buses. Use when the user asks about Flytoday (flytoday.ir) or wants flights, trains, buses, hotels, villas or…

Audits SharePoint pages, news posts, and hyperlink fields for broken or risky links and saves a self-contained HTML link-health report to the site. It is strictly read-only for content and only writes…

使用纳瓦尔·拉维坎特式的重新定义、欲望审计、特定知识和杠杆框架澄清职业、创业、财富、幸福、自由与人生选择。用于识别错误问题、冲突欲望、独特竞争力、AI替代风险、许可依赖、边际成本和长期复利方向。

Reviews pull requests for code quality, readability, security, and best practices. Use when analyzing code changes or reviewing a PR.

Use when building CSS animations, JavaScript transitions, React/Vue motion, or any browser-based animation work.

Post-Ship Growth Intelligence — track how your shipped product is performing. Use when user wants to check growth metrics, SEO trajectory, uptime, deploy frequency, or overall project health over…

Implement NFT standards (ERC-721, ERC-1155) with proper metadata handling, minting strategies, and marketplace integration. Use when creating NFT contracts, building NFT marketplaces, or implementing…

OpenTelemetry in Ruby — SDK setup, manual tracing, experimental metrics and logs, Bundler integration, contrib instrumentation for Rails/Rack/Sinatra/Sidekiq and other gems, propagation, performance,…

Creates and reviews executable implementation plans grounded in repository evidence, with vertical slices, explicit decisions, and verification criteria. Use when asked to "plan this feature",…

| 专家包的全生命周期运营：转化(从开源仓库/本地项目创建专家包)、修改已有专家、合规检查、批量更新、质量审查。 触发词：创建专家、转化专家、转成专家、生成专家包、导入专家、convert expert、修改专家、编辑专家、更新专家、modify expert、检查专家、审查专家包、专家合规、专家运营、expert ops。

Query the PharmKG knowledge graph (180k entities, 39 relation types, >1M triples). Use whenever the user asks about biomedical relationships among genes, drugs/chemicals, and diseases — e.g. drug–gene…

AI safety, guardrails (NeMo, Llama Guard), bias audit, EU AI Act / Keamanan AI, guardrail (NeMo, Llama Guard), dan tata kelola AI.

Optimizes database queries and improves performance across PostgreSQL and MySQL systems. Use when investigating slow queries, analyzing execution plans, or optimizing database performance. Invoke for…

Answers impact, affected-tests, anchors and symbols queries on a plant's code via docs/graph/source-index.py, without a model.

Qualify and promote a pinned Bun fork build for a Linux OpenClaw service, including upstream sync, release proof, native workload admission, and rollback planning.

Conversion Tracking Debugger — diagnose discrepancies across GTM, GA4, Google Ads & Meta Pixel with live API access, BigQuery validation queries, and troubleshooting flowcharts

The closed catalog of CometChat Android v6 UI Kit components for the Kotlin XML Views cohort — what exists, the XML tag and import for each, what each one is for, and how to swap custom UI into a…

Generate structured paper outline adapted to target journal

Master ES6+ features including async/await, destructuring, spread operators, arrow functions, promises, modules, iterators, generators, and functional programming patterns for writing clean, efficient…

Organizes screens and popups in a Defold game using Monarch screen manager. Use when creating new screens, popups, or setting up navigation between them.

Update and patch the managed hosts and their containers safely. Use whenever the user asks to update, upgrade, or patch a host, VM, node, or app; asks "are we patched", "any updates", "update…

Delete one or more organizations from a live LiteLLM proxy. Ask for the organization_id(s) and confirm before calling DELETE /organization/delete.

Interacts with a running Friday daemon via CLI and HTTP — lists/creates/modifies workspaces, triggers signals, watches sessions, publishes skills and agents. Use whenever you need to poke at a local…

奇幻类型视觉设计预设。触发词：奇幻、魔法、森林、古堡、精灵、龙、巫师。用于明确需要此类型的画面设计、图像/视频提示词、视觉参数查询与诊断；保留摄影、光色、空间、动作、材质、连续性及 style_route/style_module 接口。

Writes or updates engineering documentation and architecture decision records from repository facts, explicit assumptions, trade-offs, and verification links. Use for README changes, design docs,…

Competitive battle card creation for sales teams combining competitive intelligence, sales enablement, and document formatting. Use when building battle cards, competitive analysis decks, or win/loss…

Doc-driven platform integration expert. Converts a web app to LINE MINI App (LIFF SDK), PWA (Next.js 16), and Capacitor (iOS/Android). Expo & Tauri are secondary/legacy. ปรัชญาหลัก: ดึง docs…

Unified Python interface to 40+ bioinformatics services. Use when querying multiple databases (UniProt, KEGG, ChEMBL, Reactome) in a single workflow with consistent API. Best for cross-database…

Download YouTube videos with yt-dlp and post-process them with ffmpeg — fetch best-quality video/audio, convert formats, extract audio, and burn in translated (e.g. Chinese) subtitles with a…

当实施Docker容器化时，分析容器架构设计，优化容器性能，解决容器相关问题。验证容器配置，设计微服务架构，和最佳实践。

Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS,…

PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform…

Turn a vague game idea into a 1-page brief (genre, scope, core loop, mechanics) in .summer/GameSoul.md.

When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program.

Анализ расширения конфигурации 1С (CFE) - состав, заимствованные объекты, перехватчики, проверка переноса. Используй когда нужно понять что содержит расширение или проверить перенесены ли вставки в…

Designs approval and permission systems for coding-agent runtimes. Use when modeling tool approvals, plan-mode transitions, sandbox prompts, or worker permission handoffs.

This skill should be used when managing movies in Radarr. Use when the user asks to "add a movie", "search Radarr", "find a film", "add to Radarr", "remove a movie", "add movie collection", "check if…

Use when starting feature work that needs isolation from the current workspace — sets up a secure safehouse with git worktrees for clean operational bases

This skill should be used when the user needs to design, review, or document complex software architectures. Use when creating C4 diagrams, writing Architecture Decision Records (ADRs), applying…

This skill should be used when writing, enhancing, or evaluating the launch prompt for a long-running autonomous agent or a parallel multi-agent orchestration attacking a hard problem: pseudo-formal…

初五的行业媒体研究Skill。通过媒体生态、可复核文章样本与同题比较，研究行业如何被不同媒体理解、解释和呈现，提炼样本内的共识、分歧、叙事模式和认知盲区。用于行业认知、国内外媒体比较与公关研究，不做媒体优劣排名。单篇报道交media-narrative-analysis，整体舆情交hot-public-opinion-analysis。

Rigorously evaluate an Agent Skill end-to-end across ANY coding-agent CLI — verify its scripts emit the documented numbers (deterministic checks), test whether its description triggers on the right…

Plan a head-to-head evaluation - a POC, POV, pilot, bake-off, or RFP response - against a competitor or competitive set, with the buyer's requirements mapped, table stakes separated from the criteria…

Register and implement PydanticAI tools with proper context handling, type annotations, and docstrings. Use when adding tool capabilities to agents, implementing function calling, or creating agent…

Casting personas: rapid generation from diverse inputs, registry-based persistence and lifecycle, data-driven evolution, inter-agent sync. Not for UI walkthroughs (Echo) or user research (Field).

Belastbaren Produktmarketing-Kontext für Positionierung, Zielgruppen, Botschaften, Einwände und Nachweise erstellen, prüfen und aktualisieren. Nutze diesen Skill, wenn die gemeinsame Grundlage fehlt,…

Use when the user wants to lint a Claude Code memory directory (~/.claude/memory or custom path) for index inconsistency, broken cross-links, stale project state, duplicate / conflicting feedback…

Undo a change already written to a ServiceNow instance — recover the prior payload from sys_update_version, write it back without corrupting it, and know which damage update set back-out, Deleted…