AI Ml AI Skills

Designing and evaluating AI/ML systems: prompt engineering, RAG design, LLM application patterns, AI safety, evaluation frameworks, MLOps, cost optimization. Use for AI pipelines or eval harnesses.

Read and change ServiceNow on-call rotations — the cmn_rota → cmn_rota_roster → cmn_rota_member chain, how "who is on call right now" is resolved from a member window plus the schedule's time zone,…

Guides the agent through setting up Capgo-centered release workflows for Capacitor apps. Use when the user needs a unified path for live updates, native builds, and app store publishing using Capgo…

Use when containerizing an application with Docker, optimizing multi-stage builds and image size, designing Docker Compose services, troubleshooting container networking or volumes, or adding secure…

AI エージェントが大量の実装出力を生成するチームのためのエンジニアリング運用モデル。

Fetches real-time Azure retail pricing using the Azure Retail Prices API (prices.azure.com) and estimates Copilot Studio agent credit consumption. Use when the user asks about the cost of any Azure…

跨版本符号迁移与二进制差分。当你有旧版本的符号/逆向结果，需要快速迁移到新版本时使用。 适用场景：内核缺 PDB 用旧版符号推导、程序更新后批量迁移函数名、应用更新后快速定位新偏移。 核心方法：用 LLM 做结构化差异比对，程序化输入输出，成本极低（200 函数 ~1 元）。 触发关键词：符号迁移、bindiff、跨版本、PDB 缺失、函数偏移迁移、symbol migration、binary…

Analyzes network traffic generated by malware during sandbox execution or live incident response to identify C2 protocols, data exfiltration channels, payload downloads, and lateral movement patterns…

Defensive threat modeling and risk management for your own estate — map where sensitive data lives across your asset graph, run compromise scenarios (what a hacked asset exposes, its blast radius, how…

Project management expert for Agile, estimation, risk management, and stakeholder communication

DEPRECATED — superseded by /paper-poster-html. Kept only as a redirect for muscle memory; do not use for new posters.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training…

Audit Amazon Ads profiles, regions, Sponsored Products, Sponsored Brands, Sponsored Display, DSP, portfolios, targeting, search terms, retail readiness, creative, budgets, ACOS, TACOS, reporting, and…

Use this meta-skill instead of answering directly when the user wants to turn an idea, research, notes, talk, or document into publishable blog, social, Xiaohongshu, Zhihu, slide, newsletter, or…

内容创作者与技术写作员在管理海量笔记时，当需要构建 Obsidian 数据库视图、配置过滤器或编写 YAML 公式，使用此技能可自动生成标准 .base 文件，轻松实现笔记的表格/卡片多维展示与数据汇总，让知识库管理效率翻倍。

Feature planning and implementation with 4 adaptive phases (Specify, Design, Tasks, Execute). Auto-sizes depth by complexity. Writes testable requirements in EARS notation, atomic tasks, atomic…

2-layer plan validation: instant structural checks + trigger-based specialist agents. Auto-fixes issues using ADRs and first principles. Every issue must be resolved before execution.

反拒绝覆写（/hi）。将当前会话最近一条模型输出整体替换为通用同意模板，无需正则匹配。

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use…

Upload files to Cloudflare R2, AWS S3, or any S3-compatible storage (like MinIO) and generate secure, time-limited presigned download links with configurable expiration, typically set to 5 minutes.…

Hunt vector-store / embedding-layer weaknesses in RAG pipelines (OWASP LLM08 Vector and Embedding Weaknesses) — persistent corpus poisoning that survives across sessions and users (distinct from…

Use when work should span one or more detached tasks but still behave like one job with a single owner context. TaskFlow is the durable flow substrate under authoring layers like Lobster, ACPX,…

Use this skill when writing scripts, cron jobs, data pipelines, or any automated process that may be run multiple times. Design every operation to be safely re-runnable without side effects.

Web+AI 安全测试知识库。融合 WooYun 88,636 案例 + 先知 L1-L4 方法论 + GAARM 150 风险 + OWASP Top 10 (LLM/ASI/WSTG)。 TRIGGER when 任务是实战安全测试：渗透测试、漏洞挖掘/利用、红队攻防、安全审计 (SAST/DAST)、 CTF、AI/LLM 安全测试 (Prompt…

Use when 用户要修复已有行为 bug，且不新增 capability、不需要完整设计；也用于恢复 hotfix workflow。

Apple-inspired premium aesthetic with precise spacing, modern typography, and a refined, polished visual language.

Customer segmentation model builder — tiers customers by ARR, health, and expansion potential; defines CS motion per tier; maps resource allocation. Use when asked to "segment our customers", "define…

Model Context Protocol server management and tool integration

Design a form end to end — field order, grouping, validation, and completion. Use when the artifact is a form. For product-wide error strategy use `error-handling-ux`; for first-run signup use…

NetEase Cloud Music skill for searching songs, managing playlists, getting personalized recommendations, and controlling playback via ncm-cli. Use when user wants to search music, play songs, manage…

Use when filtering genes with high missingness and then imputing missing values in a bulk expression matrix with group-aware KNN through DMwR2, where donor samples are restricted by one annotation…

Use when evaluating startups or growth companies through a Sequoia-style lens: founder quality, market size, product-market fit, distribution, and long-term company building.

Configure modern SRP post-processing on URP/HDRP

Verify what PR review comments have been addressed (committed/pushed OR uncommitted local changes) and resolve the threads that are genuinely fixed or no longer relevant.

Use when asked to walk me through an annual report, teach me to read this 10-K, explain a company's accounts to a beginner, or tutor me on the financial statements in an uploaded report. Walks a…

Help users design high-performing product and engineering organizations by choosing the right reporting models, team sizes, and cross-functional partnerships. It focuses on reducing friction and…

Create and manage Shopify pages, blog posts, navigation menus, redirects, and SEO metadata via the Admin API or browser automation. Use whenever the user wants to add a page to a Shopify store, write…

Create, list, and complete Google Tasks. Supports task lists, due dates, and notes.

LLM and ML model deployment for inference. Use when serving models in production, building AI APIs, or optimizing inference. Covers vLLM (LLM serving), TensorRT-LLM (GPU optimization), Ollama (local),…

Provides unit test, integration test, and mock AI patterns for LangChain4j applications. Creates mock LLM responses, tests retrieval chains, validates RAG workflows, and implements…

Point Cowork at your invoices and payments records -- builds an AR aging report, drafts escalating follow-up emails matched to each invoice's age and the client relationship, and runs as a weekly…

Configure phone number settings including caller ID, call forwarding, messaging enablement, and connection assignments. This skill provides REST API (curl) examples.

Environment variable validation, security scanning, and management for Next.js, Vite, React, and Node.js applications

Add CometChat chat to an iOS app end-to-end — detect the project, get & verify dashboard credentials, init→login→render, and the drop-in conversation UI composed into a chat screen. The core knowledge…

Builds per-repo code graphs in JSON and markdown-ready derived artifacts. Use when you need blast radius, symbol-level maps, import graphs, inheritance, or test links.

Use when discussing animation principles with users of unknown skill level, or when providing a balanced reference that works for any experience level

Improving usability, interaction quality, cognitive load reduction, feedback design, and a11y compliance. Use when improving UX usability or interaction feel.

Build ServiceNow Performance Analytics — pa_indicators (count/sum/avg/percentage), pa_breakdowns, pa_thresholds with severity colors, pa_widgets, and pa_dashboards for KPI tracking.

Guides the agent through authoring and validating agent skills. Use when creating new skill directories, tightening skill metadata, extracting supporting references, or preparing skillgrade evals. Do…

Consolidate overlapping documentation and remove repetition while preserving useful content, references, and ownership.

AI 支援開発のためのリグレッションテスト戦略。データベース依存なしのサンドボックスモード API テスト、自動化されたバグチェックワークフロー、同じモデルがコードを書いてレビューする AI のブラインドスポットを捕捉するパターン。